In just the past couple of weeks, I've noticed lots of machine generated cooking recipes. They follow the typical SEO pandering blog format, where there's an unnecessary story about the author's trip somewhere or their child's school play being the inspiration for making this particular recipe, followed by the actual recipe details. The machine generated stories are even more pointless and meandering than what humans come up with and the recipe details have steps that contradict each other and specify ingredients that shouldn't be in the dish and weren't on the ingredients list.
I don't know how many people are fooled by these recipes and end up with a cooking disaster but if we start seeing faulty machine generated instructions on how to do electrical work or engine repair, the consequences will be much greater when followed. The real annoyance is that because these machine generated articles learned from sites that maximize SEO, the generated articles are rapidly rising to the top of search results and crowding out actual good information that wasn't SEO maximized.
there's a paper that basically shows these LLMs are pretty much tapped out in terms of quality data to train on, not sure if there are any legit architecture improvements in the works to improve results quality but it seems brute force training with more data may be about over - https://arxiv.org/pdf/2211.04325.pdf
As for SEO, Google is going to have to stop being lazy and relying so much on backlinks and domain authority. They might have to consider allowing searchers to essentially vote on what they consider good. I don't see any other way low quality AI content doesn't dominate SERPs, established players will spin up entire sites and spam backlinks to them all. There are also people working on using AI to identify obvious AI content by finding patterns in the output which is probably our only hope.
For social media and forums they will have to rely even harder on captcha or they will be taken over by bots talking to other bots
An interesting idea but really then aren't you just recreating reddit to an extent. The things people like or that are popular are upvoted because the voter agrees whereas what is unpopular gets down voted regardless of veracity because people like the way it sounds.
Beyond that a once popular website or producer says or does something that offends the sensibilities of the internet crowd and then everyone goes and down votes their results because it violates the current ziegiest
People are already appending "reddit" to their search queries to filter out the SEO blogspam clogging up the results of a regular search. Reddit is already superior to base search results for anything that's not plain uncontroversial facts because at least you're getting an actual human's opinion, which you can treat and evaluate as such.
For all its flaws maybe becoming like reddit it what search needs. AI generated spam will likely always be better at gaming a search algorithm than a human. Human moderation has its flaws but at least we're very familiar with them - they might be worth dealing with if it keeps the internet vaguely usable.
Lots of reddit is already pretty useless, drowning in people who are desperate to sound clever by regurgitating one of the same 50 meme jokes with some minor twist to it. And the astroturfing on the political reddits are likely to start hitting the niche ones with products getting pushed by manufacturers. Just buy accounts that have been built by bots on front-page subreddits, then have them make AI-driven positive comments on the niche subreddits and now you've got organic-looking advertisement for your product. Moderators likely won't help since they are there mostly to keep the trolls out (or they're more focused on whatever political axe they're grinding).
Reddit is also having some pretty serious problems with bots reposting highly upvoted content, both in posts and comments. Sometimes it gets spotted -- especially when the bots pick content which was specific to some point in time, or when they repost a comment out of context -- but a lot of it goes unnoticed, especially in comment threads.
there are tons of ways to prevent that by weighting votes and only taking a random sample. SEO is basically a war where SEOs find a way to exploit Google's algorithm and Google tries to respond.
Backlinks were Google's original solution to keyword spam that made other search engines suck, they didn't expect people would create entire sites or pay other websites to send links to them so they could rank higher. Backlinks were themselves considered to be "votes" for quality similar to citations in academia. The problem is the barrier to entry to make a site and link to it is high, so SEOs themselves are often the only ones to do it. Adding some sort of voting mechanism would allow actual readers to give an opinion on quality, although you'd probably see SEOs pay people to vote on their link via a VPN switching IPs, so only people with established Google accounts could be allowed to vote. Obviously its a huge challenge, which is why Google is worth hundreds of billions for even partially solving it
I guess a return of "don't show this page in my results" could work better: it removes the worst results and it's hard to fake, no influencer is going to pay to downvote 200 pages and if they do, it would be easy to see that same user downvoted everything everything at random, without even clicking trough to read.
Helps for both search users and the platform. Like a free moderation service. Why have an employee too check if these pages should be removed if a crowd of tracked users can do it.
I wonder where is my view wrong because I wonder why isn't there such system yet...
You'd still have to deal with adversarial spam. Competitor A pays a botnet to visit and downvote Competitor B's links at will, thus tanking its ranking.
In order to detect malicious activity you'd have to use a bunch of other signals, and also to use the downvotes with some suspicion, so you're back at looking content quality, reputation, page speed, and many other signals. Which sounds very similar to status quo.
Personally I'd like to see some sort of explicit input. If not used collectively, at least to customize my own results, like it happens on YT/Netflix/Instagram/etc - e.g. "never show results again from this site", or "I dislike this type of content".
>The things people like or that are popular are upvoted because
You forgot to add "Because clever posters use bots to give an early upvote boost to their posts, and downvote competing posts" And the more eyeballs on the site, the more things will be manipulated this way by bad actors.
Google doesn’t actually have to do anything at all other than slurp personal data up and use it to improve ad margins. Once your the default search engine, the default home page, and the default browser, you’ve locked 99% of the world into your portal. You control what people see and do, and they have to accept it. That’s what triggered the browser wars of the 1990’s - the realization that that trifecta is the keys to world domination.
Saying “yeah but Kagi” is talking about you and your tribe only. The world isn’t going to pay for Kagi or take the N steps required to switch. Microsoft realized they could kill Netscape by simply not requiring the user to download anything, then failed to consolidate. Google managed to be better for just long enough to consolidate so pervasively that any further investment in improvement is a literal waste of energy and money.
So, don’t hold your breath from an improvement in SEO garbage. It’ll just get worse. Definitely use Kagi and hopefully we will have great niche subscription based tools that have an incentive to be better. But don’t expect that Google perceives ANY problems with the status quo or that they have to do anything about anything other than increasing ad margins.
I’m not sure it’s Google’s fault at this point. Maybe it’s just that every site thinks they need to be SEO spam in order to be noticed. And so the internet has become a cesspool of stories about how this is the same recipe passed down in your family since Julius Caesar.
There have been a ton of articles about how Google sucks lately. Well, maybe Google has gotten worse, but maybe the internet has just gotten worse.
If I search for “best gaming laptop” or “taco recipe” the results are pretty much uniformly spammy across Google, Bing, and Neeva, the latter being a paid search engine. All of them are just farms for ads, popups, and paid links sandwiched between AI generated copy.
Is that the search engine’s fault? Is there some oasis of quality results I don’t know about? I would like to know.
> If I search for “best gaming laptop” or “taco recipe” the results are pretty much uniformly spammy across Google, Bing, and Neeva, the latter being a paid search engine.
I believe you will find results on Kagi less spammy
I do like to hear a founder of a still developing startup describe their current results as “decently well” … it speaks volumes about what their aim is and how they assess their current position trying to reach those goals. If you thought it wasn’t possible you wouldn’t be trying but you know you aren’t there yet.
Thanks for being honest like this. I really should get around to trying Kagi … I think I’m just still in the current habit inertia between DDG and Google
Internet is extremly spammy and it is a result of ad-based monetization which provides incentive for the spam to be created. Luckilly an efficient mechanism to detect most such spam is to measure number of ads on a site and then downrank such results, which is what we do.
While there is certainly a lot of room for progress in architecture to improve training time, model size and inference speed, high quality data and curated data sets are the ultimate bottleneck in terms of what AI can actually do. Low quality data can be useful to a point, but once you have enough data all it's doing is teaching the model to produce low quality output.
The next wave of major progress in AI will come when we create image/text data sets that have been heavily annotated with aesthetic judgment metadata, and train models to make aesthetic judgments, then condition generative models on aesthetic judgment scores during training.
"The key roadblock to achieving human-level language understanding in AI systems is the lack of a comprehensive model of human language and cognition. While large amounts of data and powerful algorithms can help improve the performance of language models, ultimately a better understanding of how human language works and how it is processed by the brain is necessary to build truly intelligent language systems. In addition, the ability to integrate multiple modalities such as vision, speech, and gesture, and to handle the complexity and variability of real-world language use are also important challenges to be addressed." -- you know who
My understanding is that Google does essentially allow searchers to "vote" on what they consider good by looking for bounces. If the searcher follows on a search results link and then quickly returns to the search page then it's considered a failure.
true, but that's part of the reason for the life stories being told on recipe sites that the parent comment was talking about. Bounce rate is another metric that SEOs have gamed by throwing a bunch of fluff onto pages where people have to dig to find what they want
So that's why they're doing it. I've been wondering for a while now just why so many sites make you work hard to fish out the information you're after. I assumed ad exposure, but I had this feeling that it's not the whole story. Delaying people to fool Google bounce metrics is the idea I missed.
that’s not actually why they do it. it’s because recipes are not copyrightable. so they throw in a “story” to make it something they can copyright and try to prevent people from duplicating.
How would having additional content above the recipe change the copyright status of the recipe itself, divorced from the additional content? It prevents directly copying the entire article, but not the actual recipe (and Google already heavily penalizes exact duplicate content).
What would make more sense is that they are actually taking the recipes from elsewhere and adding the stories to avoid directly duplicating another page, and the Google ranking penalty associated with exact or close duplicates.
My moderate experience with SEO suggests it's a combination of factors. First, Google generally rewards longer content (https://www.sweor.com/seocontentlength), or at least content longer than the few hundred words a simple recipe would likely be limited to.
Secondly, there is (mixed) evidence that Google rewards sites on which people spend longer before clicking back.
Thirdly, the longer format allows them to insert more keywords/longer tail keywords vs. a short format where inserting lots of keywords would be seen as keyword stuffing.
I'd also guess that as much as some people dislike superfluous stories when looking for a recipe, it is a positive for a subset of users that are more likely to subscribe to/return to that site directly in the future.
That's specific to recipe. Here I meant in general - e.g. blogs and news articles that bury the core point / answer somewhere around the final 1/3 of text, but also don't seem to exploit the artificially elongated text to expose you to more ads.
They had upvotes working before! Just bring back google+! I found it incredibly useful to land on a page and see a high upvote in the little plugin widget I had in Chrome.
Thinking of my confusion as a British person, the first time I heard about Americans having “biscuits and gravy”. Or the time an American recipe guide got confused in the other direction about the British traditional Christmas “mince pie” and put minced meat in instead of mincemeat (which, despite the name, is vegetarian).
I still nurse disappointment, mixed with a hint of resentment, going back to the age of maybe 3 or 4 years old that mince pies contain mincemeat (which is fruit, not meat) rather than minced beef. In the view of my 4 year old mind, and frankly my 40-something year old mind, the names of ingredients and dishes ought not to provide a misleading impression of what they might be made out of. "Mincemeat" still feels a little like false advertising.
> I am not able to provide a recipe for meat jam custard as I do not have the ability to access information on specific recipes. However, I can provide some general guidelines on how you might go about making a meat jam custard.
> First, you will need to select a type of meat to use for the jam. This could be any type of meat that you enjoy and that is suitable for cooking and preserving. Some common options for meat jam include pork, beef, chicken, or lamb.
> Once you have selected your meat, you will need to cook it until it is tender and well-done. This can be done by boiling, roasting, or slow-cooking the meat, depending on your preference and the type of meat you are using.
> Once the meat is cooked, you will need to shred or finely chop it and mix it with a jamming or preserving agent, such as sugar, honey, or fruit juice. This will help to preserve the meat and give it a jam-like consistency.
> Next, you will need to prepare a custard base for the meat jam. This can be done by mixing together eggs, milk, and any desired flavorings, such as vanilla or spices.
> Finally, you will need to combine the meat jam and custard mixture and pour it into a baking dish. Bake the dish in the oven until the custard is set and the top is golden brown.
> Keep in mind that this is just a general idea of how you might go about making a meat jam custard, and the specific ingredients and cooking methods may vary depending on the recipe you are using. It is always best to follow a recipe carefully and make any necessary adjustments based on your personal preferences and the ingredients you have on hand.
That was actually the basis for a "Friends" sitcom episode. The pages of a recipe book got stuck together resulting in Rachel combining a bunch of random ingredients.
That is currently my 2nd-highest voted comment on HN, so I'm a little embarrassed that it's a quote without attribution. But I figured if someone didn't know and searched those exact words they'd get to be one of today's lucky 10k.
Holy crap. I just got an account with OpenAI set up last night so I've been looking for interesting prompts to play with. Can't say I'm going to try the recipe, but this looks at least as good as most blog-spam recipe sites.
Prompt: Write a recipe and blog post for onion soup.
GPT3 Response: Onion soup is a classic comfort food that can be enjoyed at any time of year. It’s a simple and delicious dish that comes together quickly and is sure to satisfy even the pickiest of eaters. Plus, it’s a great way to use up any extra onions you may have lying around! Today, I’m going to share with you my favorite recipe for onion soup.
To make this soup, you’ll need:
-4 large onions, sliced
-4 tablespoons butter
-4 cups chicken broth
-1 teaspoon dried thyme
-Salt and pepper to taste
First, melt the butter in a large pot over medium heat. Add the onions and cook until softened and lightly browned, about 8-10 minutes.
Next, add the chicken broth, thyme, and salt and pepper. Bring the mixture to a boil, then reduce the heat to low and simmer for 15 minutes.
Once the soup has simmered, it’s ready to serve. Ladle into bowls and enjoy with some crusty bread or a salad.
Onion soup is a simple and delicious dish that’s sure to please the whole family.
> A recipe is a statement of the ingredients and procedure required for making a dish of food. A mere listing of ingredients or contents, or a simple set of directions, is uncopyrightable. As a result, the Office cannot register recipes consisting of a set of ingredients and a process for preparing a dish. In contrast, a recipe that creatively explains or depicts how or why to perform a particular activity may be copyrightable. A registration for a recipe may cover the written description or explanation of a process that appears in the work, as well as any photographs or illustrations that are owned by the applicant. However, the registration will not cover the list of ingredients that appear in each recipe, the underlying process for making the dish, or the resulting dish itself. The registration will also not cover the activities described in the work that are procedures, processes, or methods of operation, which are not subject to copyright protection.
And so, you can grab a recipe and be 100% sure that it isn't copyrighted. Then you can add some SEO text around it and some advertisements on the side and you've got yourself a page that you are sure that no legal department will come after you for.
It may be that the 21st century Turing test will be 'whether an AI can tell that content is AI generated". Otherwise it may be much harder to filter the AI-generated content.
Whenever this technology is used in an accuracy-critical setting, it is a recipe for disaster.
These "AI systems" produce the MOST PREDICTED output whenever there is any ambiguity, and this REPLACES the ACTUAL UNEXPECTED value/ITEM. In information system terms, they are literally stripping out content with the highest information value.
I saw this first hand giving a deposition that was supposedly transcribed by an "Artificial Intelligence" system. The output looked beautiful, until I started checking it for errors. Normally an errata sheet has a dozen lines for errors. Mine had pages. And they were substantial and very meaningful. The most obvious site was a specific name that sounded vaguely similar (started with a "J" and "K" sounds) was replaced by "Jack Kennedy". It also replaced "you have" with "I have" and omitted "not" several times, literally reversing the meaning of the statement. There were 85+ errors that I caught, over an order of magnitude more than normal.
These things are basically fine as glorified type-ahead systems where it doesn't matter much and a human is in the loop. But using them in any situation where the results are critical is, at this point, basically fraud. They do not do what the proponents claim.
I guess I'm in the minority of actually appreciating a lot of the background. And it can't just be SEO given that cookbooks these days are hardly just lists of recipes for the most part and people do apparently buy them.
Well to me there's two distinct types of background:
1. Background directly related to the recipe/cooking in general.
2. The writer's personal anecdotes tangentially related to the recipe.
Some cooking blogs have great background (eg. J. Kenji Lopez-Alt's work on Serious Eats) but I would say they're mostly type 1 - information that informs you about the recipe, how they developed it, technique etc. They have type 2 background as well (jokes, what inspired them to make the recipe, snippets of their day-to-day lives) but it's definitely a small proportion of the body of the text. These blogs always have background that's work reading.
What I can't stand is the blogs with reams and reams of text of nothing but personal anecdotes, meandering stories, media references, what their kids are up to etc etc, occasionally returning to talk about something to do with the recipe. I don't have any examples because I now avoid untrusted recipe blogs like the plague, but it becomes very obvious to me when a recipe blog strays from useful background to worthless padding for the sake of copyright and SEO.
Absolutely. There is content around recipes that is good and content that is, well, not. But a lot of people seem to object to anything other than a recipe.
Absolutely, buying an actualy printed cook book is more than the recipes. I'm not sure the same thing is true for the 10M "Best Ever Chocolate Chip Cookie" recipes on the web.
I guess if I'm just looking for a recipe the text is easy enough to skip. Often there's even a jump to recipe button. But photos etc. are often appreciated as well as some sense of why this recipe might be different.
So? Someone else can (and often does) just copy the recipe. So if you don't think the rest of the content has any value, what has been gained by writing it? If I had a cooking site--which I don't--I'd certainly want to do more than just post recipes irrespective of monetary considerations.
So the interesting thing about these tools is that they don’t link to the sources or cite the sources but instead train on them to generate a new source.
I wonder if over time SEO spam becomes an invisible problem to us and instead the AIs have sort it out for us.
> I wonder if over time SEO spam becomes an invisible problem to us and instead the AIs have sort it out for us
There have been some good Twitter threads about this. Basically, this is the last generation of AI to be trained with inputs that were ~100% human. It probably won't take long until the bulk of the content online is generated by AI, at which point it will just be an AI feedback loop. Any new concept, idea, technology, whatever, that doesn't already have a bunch of content about it will never have a guaranteed fully-human-written corpus to start from.
Once there's a viable OpenAI competitor or two, it's probably only a matter of time until the AIs start an arms race to feed each other bad data. Tweak the model to generate subtly incorrect information, regenerate your training corpus in a way that it feeds into other AIs but ensures you ignore it, and now you're basically all the way back to having a few trusted "information gatekeepers".
Except at present we can also train classifiers that recognise GPT output, so ingressed text should be able to be filtered.
https://huggingface.co/openai-detector/ detects GPT2, but it still detects ChatGPT snippets most of the time, even though the algorithm has been improved and the training set is presumably quite different.
That said, I did just generate a complete lie https://news.ycombinator.com/item?id=33874757 using ChatGPT that scored 99.98% real on the detector, so adversaries can pre-filter too.
Also interesting is that historical corpora (every existing corpus) of data becomes more valuable, because they are untainted.
This will in turn spawn a new research field and industry of automated AI content detection in order to filter out poisoned training data. Also expect to see web browsers incorporate that technology with some sort of rating or color code to flag pages that seem to be AI generated. It's going to be a real arms race.
Similarly, I have found a ton of beginner coding tutorials that contain mountains of useless/unrelated text. I bet a ton of it is SEO, but you gotta wonder if its just generated by something.
Especially now that things like chatGPT seem to write coding tutorials pretty easy (with less bloat than the ones I find on google)
Same! I was trying to figure out async diesel in rust and I couldn’t figure out why the tutorials weren’t working. There were several that had similar code snippets, but different (and sometimes nonsensical) explanations. Couldn’t get anything to compile. I finally found a GitHub repo that they all seemed to be stealing from and managed to figure out the missing parts.
With content from humans, there has to be sufficient motivation to produce a significant quantity of coherent garbage (since it takes time and effort) which means that you can trust by default because intentionally generated garbage is rare unless the topic is one of the niches where there is motivation for it (e.g. politics, history related to politics, and sales). Like, sometimes people do put in exceptional effort to fabricate something as a practical joke, but that is sufficiently rare that you can ignore it in your daily life.
Without AI-generated content, cookie recipes would be "safe" from that, since only people who care about cookies would bother to write up articles about them - but now you suddenly have to mistrust all sources of all information, which is a new thing.
Create content with AI will be easier and faster, but it doesnt mean humans wont generate garbage. That is one of the main problems of the search engines. And as long as you can put ads in your content you can create any garbage and put ads there to make money, as long as the content sounds relevant for a lot of people.
For me the main issue with AI creating content in internet is going to be the echo chamber of that content being used to train new AI models.
The bullshit asymmetry principle puts forth that algorithmic 'bullshit' content is even worse as quantity is a quality all in itself when you're debunking the bullshit. In general the reader will not know if the producer of the bullshit is a real human or a bot. This makes the search engines job even harder as not only do you have the standard human bullshit you have to get rid of, you have an oceans torrent of AI generated bullshit that you have to waste energy on getting rid of.
HN has a common theme of saying that "Dead internet theory is wrong", I personally just think they've not waited long enough and it's becoming more true every day.
It's the mass production that is the problem. A lot of talk into how businesses will still need curators to trim down the content and such misses a vital assumption: that these businesses actually care. Content farms won't trim down their 100 outsourced artists or writers to 10 curators; they will cut the stack completely, and just pipe whatever noise the AI generates straight into the commons. Even if 99.999% of it is complete nonsensical garbage, if they produce fast enough the remaining 0.001% of actually good content can still result in massive profits
> A lot of talk into how businesses will still need curators to trim down the content and such misses a vital assumption: that these businesses actually care.
It's less about if the businesses care and more about if the consumers care. Businesses will respond to whatever consumers are willing to tolerate.
Honestly, it'll probably be a battle around requirements to label AI-generated content so that consumers can make an informed choice about what to trust. But, given the global nature of the internet, that's probably not possible. You probably end up with private/commercial reputation rating firms, and consumers can decide who they want to trust.
If people decide they don't care about the veracity of information or don't want to put in the extra work to ensure they are consuming "true" information they you'll end up with businesses built on auto-generated garbage.
Except for the fact that it does so on an unprecide dented scale allowing small groups of people to do things without necessarily being caught allowing for far more effective ways of control. Even without it, it's hard to argue for the existence of online forums when hackernews is a classic example of why it doesn't work when the majority of the 'intellectuals' have an inflated belief and understanding on topics they have no basic understand on. It's so bad that none of the actual subject matter experts talk here besides ones with financial interests in the products themselves and the experts fearful of retribution. The irony is almost comedic.
Yes - AI moves this to another level of scale but Google’s need to sell ad placements created the environment for that to work. When they can’t even be troubled to de-rank blatant StackExchange/GitHub/Wikipedia scrapers it created a big opportunity for these low-quality content farms limited only by their ability to generate content on every topic.
I have cookbooks, both physical and in digital formats, but it's usually faster to do a web search, especially when I mostly need cooking time and temperature. Perhaps this will motivate me to finally get around the setting up a local search function for my electronic cookbook collection as the web is going to be less and less trustworthy.
For all its flaws I find Youtube is one of the best sources for recipes these days. Especially when you search in the language of the country the dishes are from and use CC auto-translate.
It's ironic that for all our cheering of democratization of creation, we turn back to gatekeeping (video harder to produce than text) in a search for quality.
Although maybe that's more a comment on the inevitable end state of democratization of creation + centralization of search/discovery + monetization of traffic.
Why is it ironic? I think it's more of a "humans are unable to learn from history moment". Romans called it "the mob" because of the common problems that occurred when large groups of undirected people got together and chaos broke loose. Of course the opposite where the authoritarian leader ruled everything also lead to Rome burning.
There is a happier middleground where multiple gates exist to filter out the bullshit, but no said gatekeeper controls the entire market leading to monopoly behavior.
Video is just a better format than text for many recipes, at least for novice cooks. The results often depend on technique as much as ingredients, and it's hard to convey technique through text.
I have never encountered GPs problem where the recipe itself (the thing I was searching for) rather than the surrounding SEO fluff was AI generated trash. If this problem widely proliferates, especially into other domains, curation is going to become absolutely vital.
There's a lot of junk writing that may or may not be authored by humans about health and fitness. Search Google for "how to do more pull-ups" and you'll find thousands of long, meandering, trash articles of generic common sense with stock images and lots of ads on spammy domains.
I see parallels here with industrialization and automation in manufacturing and food production. Today, it's self-evident to us as consumers when a product is cheap, low-quality, manufactured garbage from China. In many cases we can choose to spend more and buy a handmade or custom version of the product we want.
In the future we might knowingly consume AI-generated cheap text for some purposes and opt for "the real thing" in other cases. Just like I buy manufactured wood furniture from Target for the spare bedroom, but not for things I want to keep forever.
The interesting thing is that a boom in AI-generated content makes gatekeepers like traditional publishers more relevant after two decades of decline. The narrative of the internet has always been the democratization of content, information, and news. Now, we might find that a stamp of approval has specific value. A publisher can promise that some certain content for medicine or engineering was not generated by AI. Whether fraud also exists is a different question.
Another way I'm thinking about it is with GMO food. GMO food supporters point out that GMOs help us feed more people, but it still makes others uneasy. Maybe there's a similar story with AI content. It makes some content cheaper, but what are the side effects?
Everyone is (rightfully) picking on your GMO example, but I want to address something else:
> Today, it's self-evident to us as consumers when a product is cheap, low-quality, manufactured garbage from China.
Correct.
> In many cases we can choose to spend more and buy a handmade or custom version of the product we want.
Not quite. It's increasingly hard to find a version of a product that's not low-quality garbage - the expensive option is often just the cheap option with extra markup for those who got fooled by marketing, or naively believe companies still care about their brands.
That's the unexpected side effect that, I feel, people still mostly failed to realize: because running a company and manufacturing anything has nontrivial costs, letting the market race to the bottom hollows out the middle. You're left with a bunch of specialty vendors who make quality goods for other businesses or governments, at ridiculous prices, and the low-quality throwaway garbage for everyone else. The "more expensive, reasonable quality" product group disappears - the vendors move either into low-quality crap or too-expensive-for-individuals specialty items (or sometimes both), as the middle can't compete with either end.
I imagine the threat of AI-generated content to be similar: as it completely blows the bottom across creative industry, it will hollow it out. Skilled creators will, when they can, move to the high-end Big Art, where you pay more for the work's provenance than for the enjoyment itself, because they won't be able to afford competing with somewhat worse but much cheaper AI-generated shovel-art.
(Also relevant is that regular people are usually as good at distinguishing between crap and good products as they're at distinguishing between crap and good art.)
As somebody who would ordinarily look for products in this "more expensive, reasonable quality" category, I feel this comment so hard :(
I've actually started building my own furniture from raw wood etc. just because it's impossible to find anything that costs less than $1000 that isn't just cardboard and MDF with a veneer. At least with furniture there's a market for "solid wood". But in so many other industries you get to pick between $3 garbage in a $0.20 box for $5, and $3 garbage in a $5 box for $20.
I feel this so much in my life. I used to be a mid price buyer but eventually what I bought ended up in the "expensive, but still crap" category far too many times. Now I just buy crap all the time, it lasts just as long, and at least I know I'm getting what I pay for.
Right. I still try to look for mid-prace quality goods, but in the recent years, I've started to realize it often had bad ROI.
What's extra annoying is that companies are burning brands on this, and as they're transitioning from selling quality goods to peddling cheap crap, they of course don't tell you about it. Instead, you see metal being swapped for plastics, screws for glue, assembly being worse and worse - while their marketing departments double down on highlighting how pretty, modern, quality and smart this years' model is.
This is an Amazon problem, not a markets-in-general problem. Amazon is currently completely taken over by cheap Chinese manufacturers and drop shippers. But, other sites are not. If you want something high-quality and handmade, go on Etsy.
Well, even so-called experts are not good at distinguishing between crap and good art. For example, Van Gogh and many other famous artists died in poverty.
> Another way I'm thinking about it is with GMO food. GMO food supporters point out that GMOs help us feed more people, but it still makes others uneasy.
a very apt analogy perhaps in a way you didn't intend. it makes people uneasy, there's a natural reaction towards the unnatural, maybe for emotional reasons. it's the same way with GMO crops and AI poems—they will not be able to tell the difference between actual creativity and "artificial artefacts"/"random statistical noise", but they're supposed to have mystical difference. One authentic, the other inauthentic. One that is actually good, and one that merely tricks you into thinking it is good. But don't attempt to scientifically determine if there's any difference... you'll be disappointed.
Australian Cane Toads and Kudzu are why GMOs make me uneasy. People have a poor track record of predicting the consequences of releasing life forms into new environments.
As a human, my reaction may still be emotional, but it's based on evidence.
GMO difference is not mystical. GMO allows for massive quantities of weed killer to enter our environment with not well understood effects. It has been recently linked to the bee collapse for example.
And that's before considering monocultivar risks which are well understood and the underhanded ways gmos are handled by corporations, which are well documented.
I had not there was as much non-mystical opposition to GM crops. A cursory Google search seems to suggest the evidence for GMs contributing to colony collapse disorder is very weak (and the amount of pesticides in the environment might not have much relation to GM crops). But going forward I will keep in mind that it's not as simple as I had imagined it to be.
You’ve illustrated two things, one spot on and one true but in the opposite direction.
100% agreed that AI is like early industrialization in that we don’t even know the messes we’re creating, and wild excess is likely to haunt us.
But GMO foods are the opposite: people feeling “uneasy” is not an indication of harm. All foods are GMO. People are just uncomfortable with the modifications being in a lab rather than over thousands of generations of selective breeding. The side effects of GMOs are the same as side effects of selectively bred food. There is no magic.
Genetic modification in a laboratory is not exactly the same as selective breeding as it can easily bring in a gene from a different species causing unexpected allergic reactions to the corresponding protein. This has caused at least one death of a human. I'm not opposed to all genetic modification, in fact I think it's generally a good thing, but the business has to be carefully regulated. Industry claims that it's totally safe are clearly inaccurate when someone has already been killed by it.
There's no point in having strict rules on food ingredients and labelling if manufacturers are allowed to, in effect, include any chemical whatsoever that can be built biologically: all they have to do is genetically engineer it into wheat (say) and write "wheat" in the ingredients. And the consumer has no idea what they're getting.
I suggest you do more research on the benefits and risks of GMOs from more reputable sources. From my understanding, the primary risks of GMOs are less to do with human health and more about environmental risks, such as creating superweeds that can outcompete native plants or negeative effects on soil microbes.
I'm skeptical of the claim that a protein included by GMO was both 1) the cause of a death, and 2) could not have been produced with traditional selective breeding.
I feel like an intelligence going in and messing with genetics is very different from hijacking the process of evolution. In natural evolution, genetic profiles change, not just individual genes.
Most of the dunking on people who hate GMOs always feels like reactionary garbage, basically people desperately trying to feel smarter than the "unenlightened housewives". It always has such a condescending patronizing tone, as if being queasy about multibillion dollar corporations directly meddling in natural processes using extremely new technologies to increase their own profit isn't a terrifying concept. No, science never has had unintended consequences, their feelings are just invalid.
Is there a even a remote chance that say bits of Mammalian dna ends up in a crop via natural selection? The economic issues around GMOs are clear. The biosphere impact is not clear and there are questions: what can happen if we introduce new vectors in ecologies that have evolved over many orders of magnitude longer timelines?
The “unease” comes from the knowledge that in Nature there is always a reaction to an action. And the nature of this natural reaction (which will unfold in time, just like humans picking up agriculture) is not fully understood. It is a reasonable (read: ~substantiated) emotional response, imo.
I agree with everything you wrote, but I really dislike contributing to the negative spin on GMOs. GMOs are super important for our future and a really amazing technology, they really do not deserve the bad wrap they've gotten from science ignorants and marketing departments. Please don't disparage GMOs :)
It isn't so much the "G" of GMOs, but that they are mono-crops usually licensed by near monopolies like Monsanto. Things are going to be bad when something goes wrong with one these, and there is no replacement and no way out of the licensing fees.
Monsanto is great, because you can immediately know that someone is just regurgitating points when they mention the company. Monsanto hasn't existed for years. And patents run out.
Being concerned about patents is a very weak argument against technology which saves lives around the world (using non patented crops, no less!) and is responsible for allowing more people to eat healthier food.
First, Monsanto and its way of operating very much still exist. Just because it was purchased by another company (which of course resulted in an even greater monopoly), does not make its impact to the world disappear.
Second, everytime this topic comes up, pro-GMOist make it sound like the technology is making some great strides with providing 'healthier food for everyone' with no downside. Why is it that the current model for GMO aims to increase resistance to pesticides instead of simply growing the yield? It probably has nothing to do with the fact that the company that provides you the seeds, also sells the pesticide. And how about the said pesticides tendency to destroy the micro-organisms in the soil, in effect making it harder to grow crops, and ultimately starting a loop for "more GMO, more pesticide, more land, repeat".
Figure a less disruptive business model, and I might be more pro-GMO myself.
> Why is it that the current model for GMO aims to increase resistance to pesticides instead of simply growing the yield? I
It doesn't; there are plenty of traits beyond pesticide resistance that have GM crops targeting them, including yield, drought resistance, nitrogen fixation, etc.
Pesticide resistance is the most established on the market becauae there happened to be particular success with it decades ago, that’s it.
Negative consumer sentiment toward GMOs means that neither the producers nor the growers of GM crops are seeking public attention to the fact that crops are GM, and their products are mostly sold in markets that don’t require GM labelling for the same reason, so the crops already in the public consciousness are all that stays there.
> Pesticide resistance is the most established on the market becauae there happened to be particular success with it decades ago, that’s it.
This might be the case, but still my original bone to pick remains. GMO is not without downside, and people cheering for it without a hint of scepticism reeks ignorance and unwillingness to learn from past mistakes that were made in the name of science.
As you've highlighted, said technique was used for decades, for the detriment of soil health, bees and all kinds of smaller organisms, without it being questioned.
As for your last paragraph, I'm not sure I understand. Are you saying that voicing these 'uneducated' opinions about GMO simply pushes the crops to incognito mode, making them less visible for consumers? Better to see your killer face-to-face than being stabbed to the back? Not sure about that.
from a more generalist viewpoint, we must consider not only the business models, but the mindsets behind them
consider an example from another area. the assembly line and "k12 education".
a 'raw material' (but it's actually a child) enters an assembly line, every year they will be passed to the next part of the process, another professional worker will receive the product and will work on it/them for a year.
Also notice how modern elementary education treats the teachers; they far too much like factory workers! low wages, they haven't much of a choice about how to do their jobs.
Now consider the mindsets behind the successful GMO crops (+pesticide combos) that have been the money makers for these corporations.
And consider the mono-crop mentalities and the above mentioned feedback cycle: gmo+pesticide kill the soil leading to more gmo+pesticide; it's a vicious cycle. it's a vicious cycle that keeps making more money!
(the assembly line was a great way to really manufacture lots and lots of munition for the war, it is a very effective technique to make stuff that will be sent to get wrecked in a war, in this sense it 'made a killing' as in made lots of 'money')
and again, consider the mindsets involved. why are we educating children like they were cars in a production line?
these corporations are full of people educated like I described, lowering our collective education quality in a longer feedback cycle far too large to be easily noticed; it's a 20-40 year feedback cycle, which has been reducing the quality of the living beings involved.
we have a difficult problem, and no power to do anything about it
>Why is it that the current model for GMO aims to increase resistance to pesticides instead of simply growing the yield?
What? TONS of GMO foods are made for things other than pesticides. Nutritional content, size, yield, taste - in fact one of the biggest uses of GMOs is making the plants need less pesticides! If you think the only reason GMOs exist is to sell more pesticides, you just do not know what you are talking about.
Of course not the only reason, but a reason nonetheless.
"Contrary to often-repeated claims that today’s genetically-engineered crops have, and are reducing pesticide use, the spread of glyphosate-resistant weeds in herbicide-resistant weed management systems has brought about substantial increases in the number and volume of herbicides applied. If new genetically engineered forms of corn and soybeans tolerant of 2,4-D are approved, the volume of 2,4-D sprayed could drive herbicide usage upward by another approximate 50%. The magnitude of increases in herbicide use on herbicide-resistant hectares has dwarfed the reduction in insecticide use on Bt crops over the past 16 years, and will continue to do so for the foreseeable future."[1]
Please bare in mind that I'm not advocating against GMO. I'm advocating against hailing GMO as a win:win to all of society and environment.
Monsanto was acquired by Bayer, yes, but did their business practices change? This feels like trying to play gotcha when someone says Comcast instead of Xfinity when they were referring to the reputation built under the earlier name.
Of course it has, Bayer just tried to ditch the bad brand image:
> The closing sets the stage for the 117-year-old agribusiness brand name “Monsanto” to be dropped by Bayer. Monsanto’s efforts to promote genetically modified crops have been the subject of much controversy from anti-GMO activists, and the U.S. company has spent millions of dollars over the years on brand and corporate ad campaigns to improve its overall image.
It's now called Bayer Crop Science Division and does the same thing.
Are you also outraged if someone says Facebook instead of Meta, although the social network is just one of the products from the company called Meta today?
It would be nice if people would differentiate between Facebook (the social network, a specific application) and Meta (a company that owns the aforementioned application and many others).
There is a useful tell here when someone uses the old name for the wrong purpose, it can be a flag that the person is possibly operating under old information. Anyways, if you want to remove all ambiguity and also signal that you know and aren't falling for the rebrand as reputation washing, just mention them both: Meta nee Facebook, Bayer nee Monsanto
GMOs are terrible which is why they're banned in most European countries.
> bad wrap they've gotten from science ignorants
Science is not about blind trust. How many times have scientists discovered wondrous new things like asbestos, Thalidomide, leaded gasoline, teflon, only to take decades to realize the consequences?
Even if we blindly trust science, there are various other issues like: patenting life, monopolization, reducing genetic diversity, GMO cross-pollination, &c.
> various other issues like: patenting life, monopolization, reducing genetic diversity, GMO cross-pollination
Agree these are all terrible, but nothing there is GMO-specific. That's all either bad agricultural practices like mono-cropping that can be done with any crop, or societal problems related to intellectual property or markets.
Because they're the exact equivalent of closed source in software.
There would be means to research, produce and use GMOs in good ways, but the way our economics work, they can't be used without either harming natural ones and/or involving NDAs, lawyers and all sort of things that in some contexts make closed source a nightmare for pretty much everyone except those selling it.
Asbestos is, sadly, completely natural and mined directly from the ground. The other things in your list are obviously not.
GMOs are a very complicated topic, and I can see both sides of the argument having some merit. Proving that new things don't actively do harm (both short- _and_ long-term) should be required before they go to market (or they should have to have very strong warning labels about being untested).
> It makes some content cheaper, but what are the side effects?
"Content" is already maximally cheap: just copy and paste. AI-generated material – at least, with the current genre of GPT-style predictive text algorithms – doesn't produce original content; it just serves to dilute our global knowledge base with semantic white noise and lossy copies of existing knowledge.
Yeah absolutely, acceptable in case of humans and not acceptable in case of GPT.
GPT is not human. It is employed by a human to get around having to benefit other humans with attention and money.
Meanwhile human world is structured around fate, happiness of humans -- such things guide our considerations as to what to consider legal and what not.
There are other differences that make it OK for humans and not GPT (like we can attribute and credit what we learned from, whose ideas we used in work and what inspired us) but they are less significant than above principle
Machines -- at least today -- are extensions of human beings, and pretty democratic, really, compared to history. You can't really talk about limiting machines without also limiting humans. GPT is a tool. Almost anyone can use tools much like it. So what are we trying to protect against?
Yes. Machines including GPT are not the ones doing things, they can't be compared to humans. And humans may desire to do things with machines that should not be considered acceptable because of how they affect human society, and humans may or should be limited (as they already are in all aspects of life that involve other humans).
That seems like saying a steam shovel is bad because it moves dirt at scale. Machines do increase the reach of people, that is exactly what they are for.
Mass spamming is the very raison d'etre for social network companies. It goes by different names though - "sponsored content", "fanpages", "influencers", etc.
The spam did not disappear with people moving away from e-mail. On the contrary, it's just been given legitimacy by the platform owners - who all happen to make money from spam.
Well, the uncomfortable truth is that our copyright regime doesn't really make sense. An AI is sort of the equivalent of a junior coder or an art student - it can look at existing work and mash it up and produce something in the same style that's novel (inspired by a prompt - which is like your teacher giving you an assignment). That's copyrightable when it's a human being doing it, and there is no inherent protection for art style, I can make all the Picasso-style artwork I want even if I'm blatantly ripping off his style, and I would own the copyright on the resulting works. Like, if I do a painting in the style of Picasso, should Picasso get the resulting copyright? Why?
And programmers are not without sin either - how many people here run to stackoverflow and copy some answer, or mash it up and produce something similar-but-cleaned-up? That's going to get a lot more powerful in not too many years too... and the thing is, is your little DTO file with blocks of fields and setters and getters really novel and worthy of a government license to cultural exclusivity, or is it a relatively obvious implementation of an API? Which (per Oracle v. Google) are also not really copyrightable...
Humanity hasn't squared the reality of most content being low-value generative trash already (despite being human-generated!) with the reality of a system that automatically awards up to ~150 years of exclusivity (lifetime of the author +75 years). Like, that's the long and short of it. A lot of what we do as humans is just building up a squishy water-filled neural net ("how to make a painting in the style of Picasso") and running random prompts and goal-seeking through it and cleaning up the generative output. Now AIs have gotten to the level of "average college student" and it turns out that's not actually all that difficult or interesting anymore, but we're still working in this model where that's supposed to be worth ~150 years of cultural exclusivity and protection automatically.
If you only get copyright on the things that are truly novel and have no previous creative basis or cultural/stylistic heritage... that's a pretty big change to the copyright system for humans too! Especially in light of the fact that there's only a few ways to implement most configurations/functions... does Spring own all the copyright to your config classes because they're basically doing the same thing as the spring demo projects? hard to see much novelty in that sort of thing pretty much ever, so those probably should not be copyrightable at all under a "totally novel" requirement, but if they do surely Spring owns the copyright.
As mentioned in a sibling comment, the "at scale" bit is surely relevant in a practical sense, but, it doesn't change the underlying-principles basis. This is a situation where "at scale" has just thrown the underlying problem into stark relief. A 2-lifetime (life of author +75 years) governmental grant of cultural exclusivity doesn't really make sense in a world where humans are constantly and trivially mashing up each others' ideas even within a single lifetime, it just doesn't fit the way we exchange ideas in general. And now you have the college-student-bot that can generate a million shitty DTO classes or artworks-in-the-style per day that makes that plain. But ultimately it's just doing the same thing as an art student but faster... if you put an art student in a Mechanical Turk box and made them draw whatever you demanded, would they not own the copyright? And would it be a problem if India had an art school that set up an "industrial art" process and employed a million students in boxes drawing whatever you said to draw? It would probably be problematic for DeviantArt commissioners, but would it violate the principle of copyright?
We just haven't managed to square that reality where most human works are fairly trivial derivatives of other works (your deviantart commissions really don't mash up any similar works or styles that came before? really?) and yet worthy of 150 years of license to cultural exclusivity. And the college-student-bot is blowing that model up. People still need to eat, of course, but that's an orthogonal problem to the societal framework we've set up not really making sense. We can solve the copyright problem and not the eating problem (as we have many times before - buggy whip manufacturers adapted too), or we can solve the eating problem and not the copyright problem, or solve both or neither. People not being able to eat and shelter themselves is a capitalism problem, not a GPT problem, and we will probably have to address the idea that everybody needs to work to survive as machines continue to displace the last strongholds of human labor (as I'd argue creative work has become). We should not be restricting our ideas on collaboration and cultural generation just because it produces inconvenient outcomes for the current copyright regime and capitalistic model, the model needs to bend to fit humans and not the other way around.
This isn't the only place the inherent contradictions and problems of copyright come up either. The idea that a nighttime photograph of the Paris skyline could be copyrighted by someone else other than the photographer who created it is pretty janky too. Is a photographer not adding significant creative value with composition/etc? Literally just having that one element makes my photo derivative? Maybe that's the analogy to GPT/stable-diffusion I guess - but the thing is, it still works the same with a human as with a robot, an AI-generated Paris skyline still would be copyrighted by the architect too. And if the argument is that the code owner or original artist owns the style, then, Pablo Picasso owns the copyright to all my paintings too, just like the architect of the Eiffel Tower owns the copyright to my photographs of the Paris nighttime skyline. And Spring (or Oracle!) owns the copyright to a great deal of your Java code. So that probably is not going to work out great for you either.
Are answers to Stack Overflow not supposed to be copy pasted, just right away? It seems hard to believe, i thought that was the whole purpose of the site!
Well, copyright suffers from the same problem communism suffers. For communism to work, everyone should be on board. For copyright and patents to work as expected, every country on earth, every town and every city's laws should be almost the same regarding to that. As soon as even just one municipality anywhere on the planet, is free of patent laws, the exact same moment a factory will pop up and produce an expensive patented pharmaceutical product which it will sell for half the price, or 1/10 of the price.
Capitalism on the other hand, works even almost everyone else doesn't like it, and 2 people agree on a peaceful exchange of commodities, following a price the market sets, or it is discovered right away.
As a rule of thumb, anything that requires everyone to implement rules and follow them, for it to work, will fail sooner than later. When a product in some part of the world is selling 100x of the normal price because of some patent, counter incentives are detonated in some other part to produce it and sell it for 50x the price. This huge profit margin creates a chain reaction of other economic actors producing it as well, and selling it for 25x the price.
Additionaly the eating problem can be solved by capitalism, not communism. Exchange of art for electronic money, a marketplace of information is what we need. Bitcoin (not BTC) will play an instrumental role in that.
A.I generated images of picasso, are awesome. I created many of them, one series of them are "Darth Vader riding a red tricycle, in the style of picasso". They are so good you're gonna fall of the chair.
Generative models do have a contribution - they adapt what is on the internet to a specific task or request. In the case of Copilot, it will use your variable names in the generated code. And not everything generated by a model should be saved. Some are just for one time use, for fun, therapy, brainstorming, etc.
We already do as you're saying with "content". The throwaway paperback novels are already predictable cheap trash (I still read them, not judging, but they're providing a different type of stimulation for which that bar is lower than something that makes you think). These are already written in a formulaic way that is equivalent to being computer generated, it just took a bit more human effort until now. Same for TV programming, art, I assume video games, etc...
> GMO food supporters point out that GMOs help us feed more people
That seems like an odd thing to point out to me.
More people is not an obviously positive thing for us or the planet. And we have enough food and wealth for everyone as it is. If feeding more people were the priority, it could be addressed in other ways. I think the primary motive behind GMO is increased control and profit. I guess I shouldn't be surprised that there's a whitewashed motive as well.
This is overly simplistic and conspiratory. Yes, Monsanto is evil, but that doesn't mean everyone involved in GMOs is, or that's the only motivation. Look up the argument over golden rice.
It's also ridiculous to just hand wave away crop productivity improvements with "but we already have enough food." We aren't going to revolutionize global food distribution any time soon, but we can do things that have concrete impact right now. We're also losing land to agriculture far too fast, particularly in the amazon. We need to be decreasing the amount of land used by agriculture, and GMOs are a very powerful tool in that interest.
GMOs need to be regulated, and I think the IP regime that Monsanto is protected by should be struct down (not that I expect that any time soon). But please don't wave away the entire discussion with strawman arguments.
> But please don't wave away the entire discussion with strawman arguments.
What strawman argument? I was responding specifically to the point I quoted that feeding more people is important. And I made a couple of points specifically against that position. So where's the straw?
That's a great parallel, especially since it supposes a possibility of a good(or at least acceptable) ending to all this, rather than just spiraling into chaos.
I only fear that there won't be enough profit motive for such gatekeeping/curation, which would only happen if very few people were willing to spend more money for human generated content. I can see this potentially not happening, either because the tech advances to quickly for people to even tell the difference, or people do realize but don't care because the AI learns to feed them exactly what they want(exactly what's happening with a lot of BS "news" already). Or maybe a decent group of people do see the value in real content, and pay for it, but the majority still remains oblivious or indifferent, and the effect it has on this majority is still enough to influence the direction of the world negatively enough that even those groups who avoid it will be forced to accept the consequences of living in a world created by AI and the majority of other people
"Makes me uneasy" stands for "makes me want to be careful", and imo this is an essential motif in engineering practice. The key is to remind ourselves that food is engineering, and with inputs and outputs which could have vast ramifications for human health and safety. GMO should be regulated and systematically evaluated by an array of public oversight systems. The concern is that it requires PhD levels of knowledge and scientific mindedness to understand and evaluate GMO in a pragmatic, effective way (that doesn't dive into religious pseudoscience---I'm looking at you DNA-free bottled water). An even huger problem is that understanding this issue in a broad sense requires renaissance person levels of capabilities and personal sensitivity. (Does it matter that food is complex, interesting, driving unique sensory experiences? Let's make it sweet baby, that hits in the taste tests.)
The same is true, perhaps even more so, for our information diet. It defines our reality.
another food analogy would be how farmers started grinding up dead animal carcasses and feeding the results back to live animals (i.e. making cannibals out of vegetarian ruminants), which resulted in an outbreak of prion diseases like Mad Cow / CJ.
The food analogy would probably be more along the lines of the mass availability of foods fashioned from refined ingredients designed for long shelf lives, i.e. "processed foods".
Produced at scale, durable, easily distributed, enticing flavor, if it's actually any good for eating is far down the list of priorities when devising these things, as its effects are noticed far after purchase.
> Another way I'm thinking about it is with GMO food. GMO food supporters point out that GMOs help us feed more people, but it still makes others uneasy. Maybe there's a similar story with AI content. It makes some content cheaper, but what are the side effects?
The analogy to GMOs seems more connected to the self-replicating nature than to any potential health side effects.
GMO's are a completely different thing though. A crop which who's gene's were hand picked by a human to be more drought resistant instead of naturally are completely different conversation and different morality. Vaccines make people uneasy, just like GMO's, but that doesn't mean that unease particularly equivalent to AI or the same moral issues.
AI already is drowning out human made content on websites for creatives. Aided in no small part with their curator's malicious insistence to not label their posts as AI generated. It's only going to get worse as AI art becomes better.
Upload your fake text and images anywhere. Upload it everywhere. Upload it as yourself. Upload it on behest of your willing friends. Corrupt your face in dozens of ways, then tag each as yourself. When everything is garbage, shadow profiles will mean nothing, social credit scores will mean nothing, analytics will mean nothing. Centralization can be turned on its head - the watering hole will be revealed to be the dangerous cesspit it is. Create art until what can be monetized has no value. Create news that never happened, scoops that are only a distant fiction, until nothing on the internet can even be meaningfully reported on. The corrosive powers of mass memetics for the first time can be rendered entirely impotent.
While I honestly do want to support this approach because unlike the alternative it might (just "might", though) work, I regretfully must also admit that the huge problem with this is collateral damage. There are millions of humans out there that are either highly susceptible to or are already caught into believing all sorts of nonsense, getting scammed in all forms, costing them money, time, well-being and even lives. The issue with fake flood is that until the saturation/breaking point (when the understanding that existing trust system is fatally broken becomes truly mainstream) it's going to make this situation worse.
What's extremely frustrating is that the only alternative I've ever seen proposed are forms of a never-ending moderation arms race, some variant of a "war on fakes". Which is even scarier in the long run, because while it mitigates the damages here and now (good), it would never solve the underlying problem, and only further cement some parts of it (enforced trust invites potential abuse).
And as usual, humanity is currently stuck between two incredibly shitty options (traditionally going through a path of least resistance, no matter what could be at the end of it - because that's how large systems work), hopefully still searching for a magical third silver bullet.
I agree with your point, but also think this trajectory is kind of inevitable in a way. As we can already see, a LOT of people are living deep in a world of BS news stories and made up facts, to the point where they're basically in a different reality.
Ideally, we'd find a way to go backwards from where we are now, maybe future generations will grow up with this flood of false info and learn to navigate it, but I think we reached a point where tech is developing so fast, and the world is changing so fast, that there were always be a large number of people who can't "keep up".
Given that, this may be one of the few scenarios where I'm in favor of a kind of "accelerationism" - increase the problem to a breaking point as soon as possible so that we can deal with the fallout and recover from it now, rather than dealing with this horrible state of things for decades and decades as it slowly gets worse and worse, until we eventually reach a breaking point anyway and likely have an even worse fallout to recover from.
I appreciate your comment. Thinking of it - you are probably right. It is a matter of time, as long as we don't accidentally take a wrong turn toward some dystopia. Won't happen in my lifetime, but future generations raised observing this state of discord would naturally learn how to deal with it. And us old farts with our susceptibility for delusion (because we, en masse, have only encountered it past our youth, when learning and adapting is harder) will be history.
> There are millions of humans out there that are either highly susceptible to or are already caught into believing all sorts of nonsense, getting scammed in all forms, costing them money, time, well-being and even lives. The issue with fake flood is that until the saturation/breaking point (when the understanding that existing trust system is fatally broken becomes truly mainstream) it's going to make this situation worse.
The people who are willing to engage in charlatanism and mass manipulation are already enabled by this tooling and will use AI as a force multiplier whether we use it to jam the signal or not, and the results will be far, far worse for victims because these people will actually have directed, dangerous goals and agendas to push them toward rather than having them flail in a contradictory trash pile.
It’s only a problem that large numbers are easily duped no matter how much education we give them when it’s also coupled with no-questions-asked universal suffrage.
It depends in part on the quality of what is passed off as education. After twelve years of US public education in the 1970’s and 80’s, not once did critical thinking tools, types and sources of bias, and default-mode skepticism come up. I’d rather work on improving that, rather than making it even harder for citizens to vote.
And the #1 way to improve educational outcomes is to figure out how to attract better candidates to be elementary teachers, NOT curriculum micromanagement (whether from elected school boards or directly from parents)
If it leads to total chaos (which I think it's going to) I could easily see governments trying to enact the following:
- A public blockchain or database for ID purposes, with every ID traceable back to a real human. Legislation created that mandates all websites implementing user profiles for any social purpose to require an official ID on signup and every user must be identifiable on the platform by their real name.
- Access to AI only under strict restrictions. Official apps you're allowed to use with the government banning all others. Big Tech will happily comply with the censoring because they are the designated official AI app providers.
- Photorealistic AI and Video banned entirely because the potential to incite violence through fake videos is too high. Imagine Pizzagate or Jan 6th but someone made a Blair Witch style video showing Biden and Pelosi killing a baby as members of a secret cult. Or someone made a video of one of their enemies committing animal abuse and sending it to everyone in the town.
- Exams will make up the entirety of your grade in most educational environments apart from those where AI cannot be used for creating the coursework.
- Anyone caught using non-official AI or abusing AI will be subject to harsh prison time akin to hacking state secrets.
Of course, the government and its agencies will have access to all of this technology for their own purposes so they will be able to create whatever they want to control you, your thoughts and society's perception to be whatever they want it to be. As this isn't really preferable to the complete chaos it's trying to control, more and more people will try to disconnect from the internet as much as possible. The IRL economy will grow and there will be a resurgence in analogue forms of media for counter culture types. There may even be a resurgence of interest in blue collar trade jobs if white collar jobs are decimated and wages plummet.
This reminds me of the great novel Fiasco by Stanislaw Łem [1].
The civilization described in the novel fills the entire radio spectrum with noise, to make efficient communication impossible (and possibly to also allow highly sophisticated noise-like encrypted communication be undetectable).
Also the book _The Cyberiad_ by Lem is now more relevant than ever. It is a set of short stories, mostly about messing with generative AI, AI assistants, etc.
I was going to say this is a great idea but totally unfeasible due to the amount of cooperation required, enough people simply won't do it, but parts of it are kind of happening by default. e.g. with BS news stories and whatnot. Also I suppose a lot of it could be automated - fighting fire with fire in a way. I'm sure that would lead to a cat-and-mouse game of creating code for detecting and ignoring intentionally obfuscating content, then the other side coding their way around those detection systems, and then back and forth like that forever, similar to the pattern of: finding exploit -> patching exploit -> finding new exploit -> patching new exploit -> etc.
I'd be careful. By doing this you can use the date these AIs became readily available as a tool for bisecting between "legitimate profiles" before the year X and "potentially fake" profiles from after the year X, which can then be used to very effectively train an AI to tell the difference...
I've been known to start ranting when I'm searching on some topic that attracts SEO garbage (e.g., Python), and realize I'm in the nth different SEO garbage article search hit.
I wonder whether a winning solution to the coming massively-parallel "AI" megaspew will emerge, how it will work, and whether Google will be the ones to do it.
Or will the bulk of consumers overwhelmingly submit, and accept it as normal, much like we already do with huge regressions in the quality of interactions and thinking?
I feel like species traitor taking the side of the AI, but I think this is probably a decent way of answering a lot of questions based on a factual and rational basis that have been answered multiple times. A lot of hoopla is made over the fact you can trick it with a false premise into giving a false answer (I’d note the false premise makes all answers true), but if it can simulate a Linux box reasonably well, it can answer your questions in python module imports better than sifting through page rank collections of SEO crap.
Edit: I also think this doesn’t undermine the value of stack overflow. Bots answering there probably does. But stack overflow has always struggled with simple redundant questions and trying to curate them away in favor of new and interesting questions, and promoting novel and well explained answers. ChatGPT probably won’t do that for you. But it can load shed the redundant stuff highly effectively. And, over time, it’ll get more nuanced as more nuanced questions and answers are incorporated. But the “I need human help” button is still there and thank goodness. Maybe the load shedding will enhance the experience on SO for everyone?
The solution will be to chain Google with chatGPT. A system that allows chatGPT to perform Google searches and use the retrieved documents as reference when formulating the response. This means we don't need to actually see Google or the website, but still have grounded responses with references.
Instead of Google it could also be a big dump of text, like 1TB of well curated web text, so with local search you get more privacy and speed. And instead of chatGPT we will use "chatStability", a LM running on the local machine, in privacy. This could be the end of ads and the creation of a new private creative space for people.
<rant>I think Google is in big trouble and that explains why they are second when it comes to LLMs - this line of development will make it easier to escape their ads and tracking. There's no profit in it for them.
Even though the Transformer was invented at Google 5 years ago, from all the authors only one still works there, most of them have left to implement their own visions, a bunch of startups. Why have they left Google if they wanted to innovate? Because they could not do it inside. Google got to protect the current revenue streams first.</>
Going off your point, even if we aren't quite there yet, there is no reason to suppose that AI won't eventually be massively better at basically ALL things than humans - that's certain the direction we're headed, and very quickly too.
This is just the very beginning of the problem. It's time for people to start thinking about how to live in a world where they are "obsolete". All jobs, or, being conservative, at least the vast, vast majority will eventually be replaced by AI. AI will eventually be able to create art that is more appealing to humans than human-created art. I think there could eventually even be AI "people", who's company many people will prefer to other actual humans, as they will be designed/trained to be as perfect as possible for that task. I hope that most people will still see more value in genuine human interaction, as any person today probably would, but as tech evolves and we get used to it, let it into our lives more, let it control more of our lives and make more of our decisions, then it advances more and we get used to it more, etc. The idea of human connection and the separation between human life and AI "life" might not be as apparent to people as it is to us, and they may allow AI and technology to replace every facet of human existence
I actually strongly disagree here with the conclusion you make. I think these are going to be tools that enhance the human mind. It’ll enable the average person to be exceptional by using the AI as guidance. It’ll enable the brilliant to exploit the AIs in novel and clever ways that were not possible before. The humans place is in the use of a tool, the tool doesn’t replace the human.
The challenge will be instead is there enough useful work to keep everyone paid in a post scarcity world? The advent of the useful AI will probably necessitate some very very serious thought about how we allocate and distribute capital.
But I don’t believe artists will be replaced by an AI any more than they were by the camera. Or that streaming will kill music. Etc.
I'm not too attached to my conclusion, in fact I hope it's not true, and have also thought about what you said. But I am convinced that, eventually, humans will be capable of making autonomous AI advanced enough to "replace" them, and I am NOT convinced that humans will choose not to - especially given the fact that over enough time people will slowly allow AI to control more and more of their lives and the world. Then the next generation of people will grow up accustomed to this level of invasiveness and think it normal, and trade off more of their freedom to AI in exchange for more convenience and comfort.
As for the concern about whether there will be enough useful work to keep everyone paid. Eventually the answer is definitely no in my opinion, just a matter of how far out that is, but I don't think whether there will be enough work is a meaningful question in that world. If AI is good enough to replace human work then the work is still being done - in fact MORE work is probably being done, and therefore more goods/resources(post-scarcity as you said). It's a question of whether humans can distribute those resources fairly - this question and problem remains the same whether people need to work or not. We already have more than enough resources to keep everyone in the world fed and comfortable, assuming we don't destroy the planet this will only be more true when the AI work force comes into play.
It's easy to assume that in such a world there will be enough resources for everyone to live very comfortably while the higher class still has extremely excessive control over resources, and as such it's not likely that greed(the main obstacle to a fair outcome) would have to come into play, as the rich and power-hungry can have everything they want without having to allow poor people to starve to death.
Unfortunately I'm not convinced that assumption is valid either though, because of the fact that the psychological factor driving the greed of the ultra-rich isn't the desire for material possessions and wealth in itself, but to have "more" - more stuff, more capital, more power, than others. They don't just intrinsically love 100 million dollar yachts so much that they choose to buy 3 of them instead of, say, saving the lives of millions of starving children. What they love is the inflation of their ego and the feeling of power and superiority. If middle-class person suddenly had 100 million dollar yachts those people wouldn't be satisfied with their own anymore. Because of this, I think the ultra-rich and ultra-powerful, who of course will be the ones in power and who will have the ability to influence how resources are distributed in a post-scarcity world, will be motivated to keep the lower classes "lower", in order to maintain their ego and satisfy their power craving(though they will of course justify it in less crude ways).
To make my point more simply: If Jeff Bezos could snap his fingers right now and magically make every single person on earth exactly as rich as he is, give them all the same resources and material possessions, at no cost to himself, I am quite convinced he would not do it. This is a simpler version of the exact same decisions those in power will have to make over the next centuries - and in their case it will probably be easier to justify to themselves as it won't be so black and white as denying fortune to billions of people at no cost: that will be exactly what they're doing, but over the course of many small decisions that is each justifiable in it's own way, such that they never have to realize that that is exactly what they're doing
I almost decided to limit my searches to the search engines of the authoritative sites. Examples in the case of Python: the Python language, the Django framework, Stackoverflow (until it will surrender to AI posts then we see what happens.) I'll end up creating a home page with search boxes to those sites. Very '90s
Ironically, the 90s solution (human-curated link collections) to Internet-wide searches seems the easiest way out.
It's relatively easy for a human to tell the difference between AI copy (as pollutes the web) and actual content.
It's also strange that Google et al. haven't built human-in-the-loop flagging of spam content into their search UX ("Is this site low quality?"). They could get around flag spam via reputation, given that Google knows identity for most of its users (because they're logged in or via IP across their properties).
Side note: In cursory research on current state, I came across the Chinese phrase "human flesh search engine" [0], which I wonder if it sounds as cyberpunk in the original Chinese.
It will be: GPT output is usually either garbage, repetitive, very wrong, subtly wrong, or inconsistent in writing style in a way humans aren't. (It sort of starts trying to say something different, in the "same style" as it started with, then switches style later.)
When humans really can't tell the difference, well… https://xkcd.com/810/ seems appropriate.
At some point you also run up against the virus vs immune system endgame: it's evolutionarily inefficient to optimally outwit an adversarial system.
Usually there exists a local maximum where you obtain most of the value with less-than-full effort.
Sadly, the centralization of search directly cuts against that. I.e. outwitting Google search = $$$$ vs outwitting 1-or-4 equally-used search engines = $. :(
Your post led me to an interesting little quick experiment.
So in 2020 I self-taught Python during Advent of Code. I remember remarking that official python.org results seldom made it to the top of Google searches. I was used to Java and Julia searches taking me right to the official sites.
Anyways, so an experiment just search for "[language] [feature]". I ended up with W3Schools as my top result for "Java ArrayList", but Oracle JDK8 docs for "Java Socket". "Python Socket" takes me to language reference but "Golang Socket" does not.
The solution is to create datasets that contain data and aesthetic judgment metadata from reputable sources together, and train models to perform aesthetic judgment. This will both filter out spam/low quality content, and provide a conditioning tool for generative models to improve their output. Even better, the arms race this will kick off will create a virtuous cycle that will push progress in AI.
The only problem with aesthetic judgment models is that (much like human aesthetic judges) it will sometimes give poor scores to things that are dissimilar to the data it was trained on, even though many people might find those things aesthetically appealing.
What does this even mean. Reputable sources tends to fail the 'chinese room' experiment because you can never tell if your source is reputable or just faking being reputable (or later becomes corrupted).
Well, if we were talking about food, I'd say Gordon Ramsay, David Chang, Anthony Bourdain or The New York Times could be considered reputable, while a Yelp reviewer with a handful of reviews could be considered disreputable.
Ultimately you can boil it down to: Trust sources when they make statements that are later observed by me to be true, or are trusted by other sources that I trust. The negative feedback loop boils down to: If a source made a statement that I later found to be untrue, or extended trust to an untrustworthy source, reduce that source's trust.
The issue here is you have pre-AI reputation sources, the problem is for post-AI content generation how are you supposed to find this content in a nearly infinite ocean of 'semi-garbage'. Anthony is not making new content, and one day the other people will expire. In the meantime a million 'semi-trustable' AI sources of content with varying reach depending on how they've been promoted will take over those markets.
There are any number of particular problems here that we already know do not mesh well with how humans think. You'd start your AI source 'true', build up a following, and then slowly them into the Q-anon pit of insanity. Most people will follow your truth and fight anything that questions it.
Search engines like Google are probably a dying technology. The next disruptive innovation in that space will be "answer engines" that use GPT like technology to dynamically generate specific answers to questions rather than linking users to third-party sites. This will allow for controlling the entire user experience and serving ads embedded in the generated content.
SD is only 4 GB in size, you can run it on one 8-10 GB GPU, GPT-3 is around 350 GB so around 100x more, 99% of humanity can't run it locally currently even if they wanted.
People really love to make predictions about technologies way too early. It’s been a year or two, tops, since this stuff has gone mainstream. I very much doubt that the consumer ecosystem will remain the same while content undergoes an AI-powered paradigm shift. We will most likely see a growth of curated sites that help weed out the nonsense, as has been typical for most new developments.
And on that note, I think the framing here is just wrong from the start. These new tools are awesome if you’re a creator. Complaining about the consumer-facing side of this new tech is a bit like complaining that cheaper video cameras will lead to junk films everywhere. Yeah, that happened, but who cares? It also allowed creative people to make stuff without needing a huge budget.
Filmmaking devices have gotten cheaper consistently over the last ~50 years. I don’t know about you, but I think some pretty good movies have come out since 1970, especially by directors working on very low budgets.
> I don’t know about you, but I think some pretty good movies have come out since 1970, especially by directors working on very low budgets.
On the whole, I think the average quality of cinematography in theater or wide-streaming releases has decreased.
Which isn't disagreement with your point, as I think it says more about audience tastes and gatekeeping filters than technology.
When film equipment was expensive and the bare minimum for creating a film was high, studios had a much tighter filter on who they'd fund to create a film. Consequently, the level of craft was higher.
What needs to be said here is that average quality is more or less irrelevant. If the amount of high quality movies increases (it did) and the discoverability doesn't suffer (it didn't too much), then that's a plus.
The thing that has tanked the quality of theatrical films on average isn't improved technology, it's the increasing commodification of art, risk aversion of business and the modern reliance on data to drive business decisions. That's why we have basically nothing but sequels, reboots and formulaic drivel coming out of the major studios.
“It’s too early to make predictions. Here’s my prediction”
^^^ I think this is what the response meant. I noticed it too, you castigated folks for making predictions then led into your own :-) a real AI wouldn’t do that!
An Avid nonlinear video editing station used to cost $100K. Nowadays you can do the same with software costing $300 on the computer you already have. You can get a mirrorless video camera that blows away the Sony CineAlta ones George Lucas used to shoot the Star Wars prequels for under a grand. This has removed a huge chunk of production costs and make indie film-making much more viable. The only limits are your imagination and the salaries of the actors and camera crew.
AI-generated animation is already being used by industry giants like Toei, and will likely be the first application to hit the screens.
AI creation tools make it easier to make stuff. This process will result in a lot of junk, but it will also result in some super creative people making art they otherwise couldn’t.
The same process happened with filmmaking. Fifty or sixty years ago, it was too expensive for anyone other than large corporations.
You could even say the same thing for writing itself; a thousand years ago, paper was too expensive for the average person and most people couldn’t afford to buy books and become literate. Today, writing paper is functionally free.
And it's not just creation of art from "scratch", I bet we will soon see AI being able to take painted animation frame, sketch of next and extrapolate next frame from it, and making whole process so much cheaper
People really love to make predictions about technologies way too early. It’s been a year or two, tops, since this stuff has gone mainstream.
Prediction:
I very much doubt that the consumer ecosystem will remain the same while content undergoes an AI-powered paradigm shift. We will most likely see a growth of curated sites that help weed out the nonsense, as has been typical for most new developments.
I we have already seen this play out in music though.
Computers let anyone record music when it use to cost thousands of dollars to record music.
The results have been a disaster outside the top 1% of music makers. Such a dramatic change that anyone under 30 doesn't even know what has been lost at this point. Music as a whole is laughably less creative as "popular" / pop music established total dominance. The money all flows upward that use to be much more dispersed.
I used to feel the same way but I eventually came to realise that there’s tons of good music being created, it’s the social aspect of music that has been destroyed.
Individual algorithm recommendations have subsumed sub cultures. Music used to be part of both your individual and group identity, it would influence what your wore, what you read, what you thought, who you hanged out with and what bars you visited. Technology has eroded the music press and sky high rents and fitness culture (not as many people drinking) means lots of gig venues and bars have closed down. These were the glue that built the subcultures up. You used to have the mainstream plus a few sub cultures that would evolve each decade e.g mods, rockers, hippies, metal heads, punks, new wave, hair metal, brit pop, emos, indie rockers etc. All of these ended up getting absorbed into the long tail so you now have the main stream and then everything else, with nothing in the everything else category really able to attract enough people to it in order to form era defining subculture like the days of old.
Combined with the sheer amount of music being created, all of this makes it harder to find music you actually want to hear. Your friends are all listening to different stuff so you don’t get many good in person recommendations anymore and what’s left of the music media are struggling to stay afloat and resorting to all kinds of stuff like NME doing movie reviews. The algorithms are hit and miss and search engines are getting worse and worse. So you become more and more at the mercy of chance, hoping that somewhere you stumble upon a review or a blog post, a subreddit or a song that somehow leads you to some good new music. But the reward to effort ratio often makes it harder to justify the time investment. And however good the music is, it’s not as enjoyable when you don’t have a group of people to share it with.
I don't think that's true at all. There are a ton of niche music makers and a ton of ways to find them...infinitely more than there were a few decades ago. You just have to go looking for them. Which frankly isn't even that difficult with YouTube and SoundCloud. Maybe the musicians aren't making millions, but the creativity is definitely there.
Sorry but no, this is completely the wrong take. Popular music is less diverse today for the same reason that half the movies released now are Marvel - art is more commoditized, and businesses are more data driven, with the shift towards more public companies also playing a role, as they can't take as many risks as private companies.
What cheap music production tools have done is allow niche subcultures to create music that actually sounds good. Punk, metal and early hip hop all grew from people sharing rare tapes that were poorly produced and sounded like shit, but were a breath of creative fresh air. Now people's unusual creative divergences are stream-able and have production quality close to that of stuff on major labels.
Lets say in 1 year 10 songs are created and 2 of them are 'creative'. You'd think that 20% of music is creative.
Now lets say we have the production explosion and now in 1 year 100 songs are created and 4 of them are creative. You would think creativity has fallen off a cliff when it has really doubled.
In addition trying to compare with the previous payola ridden system were winners and losers systematically chosen by a wealthy cabal seems rather asinine. It only worked because there was a limited number of radio stations mostly. Even if production costs stayed high, distribution costs dropping would have changed the model dramatically anyway.
Are you the author of the binary your compiler made? Sure you are. Of think of using blender geometry nodes to generate and render pictures of architecture. Nobody would think that traditional computer generated images are not made by humans.
The is no intelligence in gpt-3. It's just called "AI" for marketing reasons. It's an data driven algorithm.
I’d argue that the creator went from being an author to being an editor, and that is fine.
Personally, I am enjoying chatgpt and copilot. They both have saved me a lot of time when dealing with new tech and accumulating new information.
I don’t trust them for certain highly sensitive or technical issues, but other than that if I can minimise the time I spend working without a reduction in productivity, well, I am all for it.
Except that isn't the creative loop people are talking about. The creative loop is having an outline for what you want to communicate, and feeding parts of the outline into the model, running it a few times and cherry picking the best results, then stitching them together to create a cohesive whole in less time than it would have taken to create it from scratch (and with a higher quality final output).
Why would anybody need to type anything? Gpt will type the gpt prompts. AI will create the AI that will create the AI. There will be people involved but increasingly less.
We need an AI that writes AI papers, and one that implements AI papers. They could be both chatGPT. Then just let them run in a huge datacenter for a year.
I don’t exactly understand your question, but I’m assuming you mean something like, “What value is this person actually creating?”
I can think of two direct use cases where I would find it helpful:
- Creating a “précis” (concept from Neuromancer) video or article on a particular topic. For example, let’s say I want to learn about pre-20th century Indonesian art. Sure, I could Google and read some articles, but it would be vastly more enjoyable and efficient to just get a 5-minute video auto-generated on the topic.
- For creating content that I want to read but don’t necessarily have the time to write. I’d love to create a website that catalogs subcultures, for example, but I just don’t have the time to do the research and writing myself.
Both of these are dependent on the generated content being accurate, of course, but that seems like a temporary problem, not a flaw in the system itself.
I think the nearby comment that points out that this is more closely related to editing than to creation as it has recently been understood is correct. Which is not a value judgement per se, but the distinction between those two activities is useful and to me provides a useful lens to understand this change.
On the face of it, that is true. But on a deeper level, AI generation is really just a kind of rapid sketching, and sketching is a practice that goes back millennia.
Additionally, it depends on how you are defining "creation" and there have been various artistic movements which "created" art in a manner not dissimilar to AI image generators. The cut-up technique or some Dadaists, for example. I certainly would consider works by Burroughs or Tzara to be real creations and not simply editing.
You're conflating two meanings of sketching though. Artists and others do uses it as an exploratory tool, and I've already seen AI generation used in a similar way so I know that's a valid application of it.
But at a lower level sketching is itself a visual interpretive and creative process. And yes what we're talking about is mechanically similar to the cut-up technique, but is that used for "sketching" in the exploratory sense?
I don't know, maybe. My point overall is that these tools aren't "really just" anything. They have similarities and similar applications to many things we've seen and done, yes. But they are fundamentally alien and in important ways are unlike anything else we've done. We should be careful about and aware of the limitations we put on our understanding when we try to interpret them through the lens of what has come before. To some extent we have no other lens, but that doesn't lessen the limitation.
I think in this case the role of the human in the process does have a strong analog to that of an editor. Where you have the ability to initiate and then shape the creation of another entity, but the creation itself is out of your hands. It's not exact, but it may be close enough to be useful, in a way I think comparing it to the cut-up technique is not quite.
It is a real problem. The web will soon be full of AI generated bullshit.
What might come back as useful tool? Authorship. People actually signing the content and putting their reputation on the line. It still exists obviously (journalism…) but it might need to be standardized and industrialized.
Indeed, Neal Stephenson in _Anathem_ (2008), in describing an alternate world (in which his "reticulum" is our "network") wrote "Early in the Reticulum—thousands of years ago—it became almost useless because it was cluttered with faulty, obsolete, or downright misleading information."
"So crap filtering became important. Businesses were built around it. ... " Generating crap "didn't really take off until the military got interested" in a program called "Artificial Inanity".
The defenses that were developed back then now "work so well that, most of the time, the users of the Reticulum don't know it's there. Just as you are not aware of the millions of germs trying and failing to attack your body every moment of every day."
A group of people (the "Ita") developed techniques for a parallel reticulum in which they could keep information they had determined to be reliable. When there was news on the reticulum, they might take a couple of days to do sanity-checking or fact-checking. I'm guessing there would need to be reputation monitoring and cryptographic signatures to maintain the integrity of their alternate web.
Fair enough. It’s like the lump of labor fallacy, but for bullshit rather than labor. One could view that as growing pains, but it is still growth in some sense.
Another problem is AI training on AI generated content. This could lead to degradation of results. So perhaps to make everyone happy a new HTML tag indicating AI content would be useful?
> Another problem is AI training on AI generated content. This could lead to degradation of results.
That's only the first step in the degradation. In a worse case scenario, where AI-generated crap is not contained, imagine this: young and still immature humans "learning" their styles of writing, information, and social expectations from content generated by AI that itself trained on AI-generated content─and then more AI trains on content generated by these humans that were trained on AI-generated content. And on, and on, and on...
Comply with what? Even in culture we tend to have a limited number of subsets of counter culture. The vast majority of the non-compliant to primary culture fits in one of a few common subcultures. As much as HN users try to exclaim they are islands that stand alone from society, we are all dependant on a functioning society for day to day life.
We should ask questions like "Can countless AI's fracture society into a million sub societies disconnected from the reality around them".
Ah, but they do want to fit in and speak like their peers, and while a significant part of their socialisation happens online, and as long as that is where they absorb most content, AI will soon infiltrate the circle of online strangers with whom they interact. That's all the more so considering that teenagers are prime targets for advertising networks of dubious ethical standards, who will be the first to deploy (or may already have deployed) well trained and self-correcting "How do you do, fellow kids?" NNs in potentially lucrative communities or social networks.
(I'm not always as doom-and-gloom as it may seem, I'm just in a pessimistic mood today for some reason)
People "sign" their content with their faces on TikTok; it doesn't stop the deluge of complete nonsense that's widely accepted on that platform (much to the frustration of many academics trying to combat it).
Though the only way to do that is probably to end up in a world where most worthwhile content is locked behind hard paywalls so there's one class who pays a lot for gated content (which was more or less the historical state of affairs, public libraries notwithstanding) and the plebes have to filter through all the ad-laden crap.
It already has a lot of AI and garbage content. And in some cases it's state sponsored propaganda, companies pitching products, or marketing departments attempting some notion of virality. The point is that there are plenty of people already gaming the system by just flooding the internet with carefully designed noise to bend opinions this way or that way.
"Fall, or dodge in heaven" by Neal Stephenson actually touches on this topic quite a bit and comes to a similar conclusion. Not his most accessible work but I enjoyed it. That book was written just before Trump won 2016 elections and in hind sight making that book really spot on and timely.
In the book, different streams of truth become so hard to separate due to all the spam, automated content, etc. that people start filtering it based on reputation and signatures. The game then becomes curating and filtering the content, which is ultimately not an objective thing but a subjective thing. So the net result is what we are actually starting to see today which is different groups of people locked in their own bubbles and no longer even getting exposed to the other side's point of view or even able to agree on some basic facts. Like who actually won the election. And people are feeding those bubbles with nonsense to influence opinions, get people to vote certain ways, or simply to just create chaos and fear.
In the book the topic is not an election but the seemingly simple question of whether or not a certain town in the us still exists after it was supposedly blown up with a nuclear bomb. In the book, this event leads to people acting as if that happened and ignoring all evidence to the contrary pointing out that in fact this was an elaborate hoax designed to create a massive panic.
That particular dystopian outcome is not necessarily what would happen. But using technology to authenticate where content actually comes from along with some reputation mechanism would go a long way separating the noise from the genuine content. It's simple and easy to do. So, why don't we?
How can we prevent drowning in garbage generated by AI?
> Preventing drowning in AI-generated garbage can be a challenging task, but there are a few things that can be done to reduce the amount of garbage that is generated. One approach is to carefully design and train AI systems to generate high-quality content, rather than relying on large amounts of data to produce mediocre results. Additionally, using tools and techniques such as data filters and validation can help to identify and remove low-quality or irrelevant content. Finally, creating and enforcing strict guidelines and standards for the use and generation of AI-generated content can help to prevent the proliferation of garbage.
because maybe it understands that banning stuff is not to be done lightly. any action that restricts anyone's individual freedom must be very carefully vetted.
because without freedom we will die. but this also applies to the corporations whose rights are now in opposition with our own human individual necessities.
if I want to gift a copy of a copyrighted material owned by a corporation, I can still do it, but it's getting more difficult; and I in fact may well be prosecuted criminally for doing that. this is an example of my right to do what I want (give a copied gift) stands in opposition with the right of a corporation to get its way. I fear human individuals are losing this battle.
I think that the root of the problem is not algorithms like the article suggests. It's ordinary people that can't resist the temptation of using AI to generate coherent-seeming results and flooding the Internet with them. But I don't blame you since I find AI tools to be useful in certain contexts, and I am unable to resist tinkering with Stable Diffusion. I guess the future for me will be one of navigating the resulting cognitive dissonance as I sift through pages of autogenerated SEO spam.
Maybe there could be a codified set of guidelines for how AI content should be shared. Or maybe an annotation system that separates the two across different websites? I only ever share something that comes from an AI on a siloed website just for AI content, but that's only because I have my own beliefs. More and more people on this site are asking if certain comments were generated with GPT-3 and it's a worrying sign.
That's honestly one of the best comments in this entire thread. Instead of veering predictably into philosophy or anecdote, it provides concrete and feasible steps toward improvement. No better way to make the point that "AI generated" is not the problem and "garbage" is.
I find the AI competition to be yet another powerful reminder that all that matters are results. I can't count how much time I've spent being angry at people in my life, even though I always knew that it was stupid. Angry at bad docs, bad programmers, bad decisions, their inability to think or understand or care or feel. Now the AI removes it all. The AI generates truth out of thin air faster than any human can invent a lie about it. The AI simply generates good docs from bad docs, all the anger was always irrelevant.
People were never going to become better, once again technology simply creates a world where people are automatically better by the mere fact that life is so much easier that the humans have no justification anymore to lie and cheat and pretend that the docs were actually always good and how I'm the problem. Nope, the AI just fixes it immediately and the human can remain lazy and ignorant, never the wiser that he actually failed at his job.
I think it will be wonderful, no longer will we have to argue with e.g c++ programmers about whether their language is bad. The AI will make it instantly obvious that you won't want to risk programming in this nonsense. No longer will we have to debate people on whether some political issue is right or wrong. The AI will generate so many truths out of thin air that it counters the DDOS of bad people's lies faster than they can spin lies. Once again technology is going to save us from human nature, humans are allowed to remain silently bad.
And the best part: Bad people are usually lazy, they will trust the AI far more than they ever trust other bad people or themselves. They will simply start blindly trusting the AI, which is better than what we have now: Them inventing their own lies and trusting themselves.
It will remove a large amount of stress from people's lives for sure.
When an AI model can explain the non-obvious bug in the code written by the developer who left the company 2 years ago - that's quite powerful. Saves more time for other stuff
Though at some point it may create new sources of stress (like much discussed job security when the other job candidate is the AI model)
A company firing its human experts in favour of AI is a bad sign, probably going to fail. If business was good they would hire additional humans and use more AI. The purpose of a company is not to reduce salary costs, but to increase profits.
An important threshold will be when an important physics, math or biology problem is going to be solved with one of these AIs, or by a scientist who uses AI for "ghostwriting".
If scientists will verify the solution and find it to be correct, the mainstream sentiment about "garbage" will change very quickly. Maybe except various neo-luddites who will find different reasons to hate these models
In this case though, it's not a solution at all. The question isn't how producers of garbage produce less garbage, it's how consumers of content can avoid being inundated by garbage. We may well ask 'please don't produce less garbage' and the producers have given us a resounding 'no.'
Fight fire with fire. Local language model doing question answering takes search and web garbage in, outputs polite and helpful responses without ads and tracking.
But let's take this idea one step further. We could also have a neural index. There are a few promising papers.
Putting the question in verbatim led to a somewhat unimaginative, albeit technically correct response.
> The entropy of the universe, also known as the thermodynamic arrow of time, is a measure of the disorder or randomness of a system. It is a fundamental concept in thermodynamics, and it is widely accepted that the entropy of the universe is constantly increasing over time. This is because according to the second law of thermodynamics, the entropy of a closed system can never decrease.
"One approach is to carefully design and train AI systems to generate high-quality content" - sure, but how will you accomplish this is the million dollar question
> It is not advisable to try and enable drowning in garbage generated by AI. Rather, we should strive to prevent the generation of AI-generated garbage in the first place. This can be done by carefully designing and training AI systems to generate high-quality content, using tools and techniques such as data filters and validation to identify and remove low-quality content, and by creating and enforcing strict guidelines and standards for the use and generation of AI-generated content.
A lot of people in the comments are making a hard distinction between AI garbage/bullshit and the pure/genuine human-created thing, and the various ways in which we can keep this distinction alive.
If only that was true, the bullshit part. You should start living with the idea that the AI generated content is NOT bullshit, because we're either already there or very close to it. The AI content will be of value, look good, pass tests, and be indistinguishable from human-created content for a large amount of use cases in mass media.
So I wonder if we should ask, how do we filter out the bullshit? The more relevant question is: if its indistinguishable in its output compared to humans, what does that mean for our economy, purpose and humanity?
Because without action, the future is easy to predict. 3 companies run AI, feeding on all collective human cognitive labor without paying a cent for it. Then, one by one, it will wipe out every creative/cognitive sector, or at least decimate them. These shocks to the economy and culture will lead to a brand new type of pushback: anti-AI activism. That won't do much because AI doesn't care. Finally, some 10 years after the catastrophe there will be a congressional hearing where a 75 y/o asks: "so this AI thing, it's like a better calculator, right?".
It would be another fine case of humanity failing to grasp the exponential function.
No-one likes being lied to. AI is the ultimate deception. People will stop using the internet for anything other than information retrieval for problems.
Artists will create on digital tools and then return to analogue publishing formats and distribution networks. People will follow them because artists are cool and tech bros aren’t. There will be an emphasis on becoming a local success story rather than a global one.
You can already see this happening some what. Vinyl records are increasing sales every year. People are getting tired of Spotify and are buying on bandcamp. Typewriters are growing in use. Digital book sales have stalled and people are buying paper books again.
I think this will become a new social identifier, particularly for those on the left of the political spectrum.
The vast majority of people don't care. Netflix's recommendation algorithm helped take down physical video rental stores and TikTok's algorithm is taking out Instagram, Facebook, and even YouTube.
Vinyl is particularly annoying to deal with. Even a small collection gets unwieldy quickly. I prefer physical books to ebooks but physical books are annoying to deal with, too. I've just given up on physical books for the most part. Typewriters are a joke; surely nobody believes they will come back to use in significant numbers.
The real problem is that AI art will be faster to produce and be completely indistinguishable from human art. People for the most part prefer the path of least resistance.
People prefer the path of least resistance until the price becomes too high. When people realise they are obese, they generally try and lose weight. I strongly suspect that with the next wave of AI, more and more people are going to come to the conclusion that the price is too high. There is significant tech pushback already, I can only see that growing as it erodes even more people’s values and livelihoods.
I was using artist in the broad sense to include writers, musicians, filmmakers etc as well as traditional artists. I'd say traditional art is the least problematic as it is the most subjective. People won't be upset at an image you show them that was generated by AI. People won't be upset if you personify the AI and give it a backstory if they know that it's an AI. They will be upset if you tell them the image was made by a human and you give them a backstory about the artist and they later find out that all of that was complete bullshit.
Not only will they be upset, they will no longer trust both those around them and themselves. If they no longer trust, they will become increasingly suspicious and fearful. And as Master Yoda said:
'Fear is the path to the dark side. Fear leads to hate. Hate leads to anger. Anger leads to suffering."
I think you are right, AI content will not be distinguishable from human content.
What we really need to figure out is the direction that we are going as humanity. This planet must quickly become too small for us, human beings will not be needed anymore which means we need to find bigger challenges or we will self destruct out of pure laziness and self indulgence.
Personally I don't think AI will only destroy creative and cognitive sectors, it will destroy absolutely every single sector in existence. There won't be a single job left that a human can do better than a robot. And humans will also pick the robot worker over the human worker every time. This is what happened during the industrialization, it's not like a few factories said: "hey you know what guys, let's be a bit quirky and still use 100% humans for this factory just because we can.". No, nobody is going the human route. It would be objectively slower and worse and therefore you go with the robot. There isn't a single area in life where you wouldn't pick the robot over the human and the question is solely how fast we can get to implant some good AI into mechanical bodies.
But you out the solution right there in your prediction. We need updated licenses that forbid the use in AI training and real teeth if it can be shown that content was illegally used in a training set.
It might be too late with the amount of data already ingested, but, hell, second best time to plant a tree and all that.
I'm not even sure how copyright will work with AI generated content.
How is the copyright distributed amongst the program, the programmer, the company distributing the program, the user that enters the input, the author that wrote the input, the authors of content ingested by the program, etc.
As has been discussed here, the more AI generates the content the less humans generate content. Further AI generated content is much faster and cheaper to produce so it’s quantity will dwarf human generated content. This then feeds into the training set and becomes self reinforcing. There will be no collective human cognitive labor to source for free.
I suspect to mitigate that AI companies will hire lots of people to simply write. This writing will be tailored to address shortcomings in the model and provide human mediated training material that’s targeted at training areas of difficulty for the models. The goal won’t be moderation, or editorialism, or producing original content. No one other than the machines will see the content written. The goal will be to improve the ability of the models to produce compelling content in volume for a marginally low cost - which may become dominated by the content creators feeding the machine. But it’ll be much less cost on the margin with a more predictable quality result than hiring individually unique humans to make hit or miss content at scale.
(N.b., I’m only focusing on the free cognitive labor statement)
Sure, for a while people are needed to tune the machine, but it's not a sustainable model. I would expect that to generate only a fraction of the employment that AI will make obsolete.
Further, if fine-tuning AI is a cognitive task, it has no future. That's the point I'm getting at: no cognitive task has any future, at all.
Suppose I want a new water softener, and all the reviews and pros and cons are made up by AI. I guess I blame the people posting AI crap as though it was real, the same way I blame made-up crap written by those people today. But maybe I blame the original authors of such nonsense even after it’s generated by AI, because that’s the garbage in that lead to garbage out? Or maybe I blame the people developing the AI for making the internet and life measurably worse? They at least seem to be fearful of that with the few fences they’ve put up trying to prevent “harmful” output.
But what about when the code written by an AI has a critical, but easy to miss bug in it? Blame the “programmer” who
While the current speed of the AI research makes me quite uneasy, I cannot really dismiss what we are seeing as:
>What we are witnessing is thus not "artificial creativity" but a simple "statistical mean of everything uploaded by humans on the internet which fits certain criteria".
at least not more than I would my own brain.
I don however fully expect a strong luddite-like backlash happening when this is going to be deployed to more and more places. (Which is not to say that everyone opposed to it is a luddite, but there is a very strong impulse, I have it to, to see this technology as a threat).
It’s weird how readily so many people will dismiss AI art as just being a product of its input, when that’s really all humans are as well. All artists (myself included) are just the ongoing product of various inspirations (inputs). Dali is a world-renowned artist, but his art wasn’t born in a bubble and ripped from the void. He studied and referenced artists before him, then changed it. Artists who saw his work later incorporated elements he used.
My big worry from here though is what’ll happen when we take the next step: bundling these AIs together and start making a comprehensive AI. We have AIs that can respond to comments to some extent now, we can generate realistic selfies, and they can make art based off prompts that they could be designed to feed to themselves—set that loose on Twitter and you have a completely automated and convincingly living artist out there. Next step after is using AI to handle free movement by auto-adjusting balance and then performing convincing human speech. The future is getting freaky and fast.
Only boring humans are just the product of the content they consume; interesting people have concerns about relationships with other humans, organisations, resources, threats and opportunities that come from being an entity living in a world full of things they don't control and things they'd quite like to control. It's also fairly easy to identify artists who have done nothing but look at other art.
Hayao Miyazaki once said "Almost all Japanese animation is produced with hardly any basis taken from observing real people, you know. It's produced by humans who can't stand looking at other humans. And that's why the industry is full of otaku!" While I'm not actually a huge fan of his work, it's easy to see where he's coming from when you see the likes of "In Another World with My Smartphone" or the hundreds of other trash light novel adaptations. They're clearly fiction being produced by people whose lives are nothing but consuming other fiction, and all they can do is reference that. They have nothing to say.
For another example, there's a huge number of 20th century war films. They weren't made because their creators had read a lot of Wikipedia articles about how destructive wars were becoming. The likes of Platoon are a product of mortal fleshbags who actually saw combat and genuinely feared for their lives. Dr. Strangelove was created by people who had a genuine belief that they were at risk of being annihilated in a nuclear fireball.
This is a tricky distinction where this may be true of all specific individual humans, but not of humanity. At some point, language and art didn't exist, and humanity invented those things. We didn't mimic some other civilization that did it first.
I don't know that this distinction matters, but it is real. Even on an individual level, if you raise a child in complete isolation from history and teach them no language or art, they'll still form thoughts, have feelings, and develop means by which to communicate those.
I think this is the big open question of evolution as a whole, and language and art can be seen as the evolution of ideas/memes as Dawkin wrote about in the Selfish Gene. Were these developments sufficiently iterative, or was there some great leap that came out of nowhere? Was the wing merely just a stump on an animal that allowed it to leap tree to tree a foot further, or was it some process unknown to us? Was art just a splatter of blood on a cave that looked like a face to our brain’s face neural network, or did some inventive genius paint a mosaic when nothing else was ever on the cave wall?
There's a fair bit of truth in this but it remains a nearly useless oversimplification. We can't adequately isolate or even identify all the inputs into what makes a person what they are, or produce what they do. The idea that this is even possible is rejected by a large proportion of the world population, and for now at least we can't prove them wrong.
> All artists (myself included) are just the ongoing product of various inspirations (inputs)
This ignores that inspiration is itself an active and creative process. There's not a one to one mapping between a piece of art and the effect it has on a person who receives it. Even hating an art is a process of influence in a very real way that I don't know there's an AI analog of. These systems can not include a source in their output, but can they decide to include its opposite? What is the opposite of a tree, btw? A desert, an ocean, a seed? A value judgement based on culture and aesthetics and opinion and worldview that ML software has no standpoint from which to make.
I'm not trying to make a moral case for or against this technology right now. But I think trying to understand and evaluate it in human terms like this is a mistake. It's something else, and we're still trying to figure out what terms are appropriate to understand it, hence the difficulty. It's important to honestly engage with that alienness and uncertainty right now.
But at least artists have some agency, all that stuff that they ingested goes through them and are somewhat limited by human hardware. Very little is original indeed but that percentage may as well go down even more as more and more AI generated soup unleashed on the world.
What about artists that used random generators in their art? Jackson Pollock used to randomly splatter paint on canvases and when some random pattern struck his fancy he went with it. That's not all that different from picking the pictures you like from a Stable Diffusion prompt and then further honing them with inpainting, image-to-image and so on.
It wouldn’t be a threat if we didn’t have an economy that distributed most gains to the very top. If things were more equitable it would mean we will all become much wealthier due to a large productivity increase.
I almost never see that raised in these discussions. We have been so conditioned not to think about this subject.
We can blame the tech, each other, everything but the system.
AI training on AI-generated images works like a very complicated Reinforcement Learning from Human Feedback (RLHF), only the best images have a chance to be relevant enough to be noticed by a scraper, after being selected by the user who used the AI, and they have probably been shared several times by random people.
Also, a lot of AI-generated content doesn't look like trash to me, I've seen a lot of good images, the fact that AIs can generate trash doesn't seem to be a problem to me, I can also generate junk and share it on the net if I want.
> Also, a lot of AI-generated content doesn't look like trash to me, I've seen a lot of good images
Translation: There is a lot of human generated original art that you're not aware of, and when you see it in the "AI"'s output you think it's original.
So you are implying that an image generated by a generative model must resemble closely to an image in the dataset, right? Because I don't think that's true, you can try to prove me wrong if you want, I'll give you a useful resource, the LAION dataset that Stable Diffusion was trained with is completely open, generate or find an image generated by Stable Diffusion and find the most semantically similar images in the dataset using: https://rom1504.github.io/clip-retrieval
Same for movie scripts, but sometimes they do fail and something original squeezes through. I'm saying this can't be the case with a pattern matching/combining algorithm.
I've been playing around with stable diffusion a bit, and if you use an iterative process starting with either an extremely vivid and "code-golfed" prompt (like verses of poetry, concise prose, or elegant lisp), or your own illustration, and then feed the output back in again (with some fuzzing) along with the prompt, or a modified prompt, or a totally new prompt, after 2-3 generations the result becomes something that, although it undeniably integrates existing works in myriad ways, looks wholly unique and shaped by the user of the AI system more than by any of the individual contributing parts. I don't think this is terribly different from my creative process when I play music; I feel I have to work just as hard to avoid copping other peoples' stuff unconsciously.
"Butlerian Jihad" that was the most surprising for me reading Dune that they had a limit on how smart computers could be. The movie was very vague on the subject, and was more of a Star Wars like lo-fi.
It was even more surprising if you realize that "Butlerian" is referring to the 19th century writer Samuel Butler (although, yes, Herbert later invented a character to explain the name in-universe). Samuel Butler wrote an 1863 essay "Darwin Among the Machines" which predicted that machines would improve in a way analogous to natural selection and would so so faster than humans could evolve, and therefore they might eventually surpass humanity.
indeed, and selection pressure is not on the domain of physical bodies like for us fleshy species, but profitability for digital computational species in the domain of capital.
As others have pointed out, AI's are not needed to produce crappy repetition which is eagerly gobbled by the masses, i.e. Hollywood, Netflix, and werewolves and vampire stories by the penny. And there is a huge audience for those.
What I think is going to happen is that even when I'm searching for information in subject X, I might need to fight through a lot of AI fluff to get anywhere. If that gets too bad, I may loose the incentive to use the Internet altogether, or to use the open internet. If I can't use the open Internet, I'll have to go to the closed one, which by definition is under the control of funded parties.
Today, we have a semblance of "verifiable personhood". Imagine what will happen when we use AI to break that too. For example, an AI could create a fictitious "Derek Mains" who post photos to Instagram, has a Facebook account with photos from his childhood all the way to his retirement, a profile in LinkedIn with a lot of professional connections (AI fictions like him but also many real people that the AI gulled), and even a Github repository from the time he tries to create a cooking recipes website, full of PHP and Python code. Derek Mains is now traveling the world and tasting new types of food, posting regular updates on Twitter/Tumblr/Mastodon, and Wikipedia, where he edits food-related articles. Not very often compared with everything he does online, but once in a while he engages with other people(?) in Twitter where he is partial to party X.
What would real people do when they discover that the Internet is full of "Derek Mains"? How do governments and power factions will use this? Wouldn't be sweet to own the closed Internet when the open one is a wasteland?
>AI's are not needed to produce crappy repetition which is eagerly gobbled by the masses
True, but humans that create this kind of crap still have to sleep, eat, and generally not pay attention to feeding the machine. meanwhile the AI terminator is out there, it can't be bargained with, it can't be reasoned with, it doesn't feel pity or remorse or fear, and it absolutely will not stop… EVER, until you are buried in an ocean of garbage content.
All this ChatGPT hysteria led me to have the following conversation with it. Probably hit some near future nail on its head. "Hello AI, please do today's tasks", the programmer will be on the level of the call center operator of today in terms of skills
* Human: Explain to me the phenomenon of post-ChatGPT depression seen in a software developer
* ChatGPT: [...] After using the ChatGPT tool, some developers may experience feelings of depression, sadness, and loss. This may be due to the realization that their job as a developer has been reduced to using a tool that can be easily replicated by others, leading to a feeling of redundancy and lack of fulfillment in their work.
Additionally, the use of ChatGPT may also lead to a loss of creativity and problem-solving skills, as the tool takes care of the majority of the coding process. This can cause developers to feel like they are no longer contributing to their team or making a meaningful impact in their field.
In short, post-ChatGPT depression is a psychological reaction to the use of a tool that simplifies the coding process, leading to feelings of redundancy, lack of fulfillment, and loss of creativity in software developers.
Well for one, it is AI generated garbage in the comments of an otherwise well curated website, HN. That's too meta perhaps. I just wanted to share my feelings out loud of this whole showdown, thinking other might feel the same and share what they think.
The bot replied with feelings of being replaced, but feelings of eternal september², eternal 2023, are equally valid signs of this hypothetical post-ChatGPT depression, probably in a closer distance in the future than the former, and besides, more relevant to the article, not just the subject as a whole
Honestly this feels like an old man screaming at the wind type thing. Inevitable doesn't even begin to describe was going to happen over the next 20 years. You should be much more terrified of when their content isn't garbage.
What I really wonder is: is there a correlation between consumption of streaming tv series and positive attitude towards this "AI" wave?
"statistical mean of everything uploaded by humans on the internet which fits certain criteria"
applies to both ChatGPT/StableDiffusion and most movie series on streaming TV.
My pet theory is that if you can stomach watching the same stories with different skins hundreds of times, you will find current "AI" interesting. Otherwise no.
I’m 41 and I’m utterly baffled by my 24 year-old SO’s interest in binging an apparently infinite litany of TV shows from streaming services. I’ve watched the first six seasons of Game Of Thrones, the first season of Dark, all of The Expanse (reading the last book of the final trilogy now), His Dark Materials (because I read the books) and Andor. That’s it. I watched some Star Trek TNG & DS9 as a kid and was horrified by what snippets of Discovery and Picard I came across. I find the bulk of modern entertainment to be an utter insult to viewers.
First off, probably don't date a 24 year-old. I realize there is no strict correspondence between age and taste, but I'm 42 and my wife is 41 and, well, our shared experience is quite a bit more similar. She can relate when I get nostalgic about the 80s and 90s. She even reads! Complete novels, more than she watches TV. She doesn't have TikTok or Instagram. It is entirely possible to go full-time mutual old people yelling at clouds in a blissful bubble in which the river of bullshit may as well not exist, but probably not if you insist on staying cool and regularly interacting with young people.
Second, watch the rest of Dark, Better Call Saul, and House of the Dragon. Don't watch the last two seasons of Game of Thrones. Just pretend it ended at 6.
> baffled by my 24 year-old SO’s interest in binging an apparently infinite litany of TV shows … TNG & DS9 as a kid and was horrified by what snippets of Discovery and Picard I came across
The thing that bemuses me is those who hate the new trek shows with a passion, and find the time to keep watching and constantly bitching about it online. It is like complaining is a hobby in itself and they are almost looking for something they don't like or to feel superior about their judgement to those who do like it. Other franchises have similar subsets of “fans” too.
I used to watch too much TV/films IMO, I probably still do though I'm a lot more selective since getting into more varied hobbies that can easily consume a lot of time (running (usually off-road), baking, HEMA). But even when I had the free time to watch that much I found there was enough out there that if something didn't work for me I could find a list of other things to try instead of sticking with something I wasn't getting much out of.
Though be careful passing judgement on modern Trek: I'm slowly rewatching TNG with a friend and while some of it has aged well, fair chunks of it was more massively ropey than rose-tinted memories prepared me for! Also, if I hadn't at least passively consumed (i.e. had on TV while I was doing other things so not particularly concentrating on) other parts of recent Trek and Starwars, I might not have bothered to try some of the better stuff like Lower Decks, Strange New Worlds, and Andor (the latter probably being the second best TV thing recently for me, the first being Severance).
> The thing that bemuses me is those who hate the new trek shows with a passion, and find the time to keep watching and constantly bitching about it online.
Very meta of you to watch these people and find the time to complain about them.
Though I like to think there is a difference between myself and them: they have a choice to keep experiencing the pain they perceive, I have it thrust upon me when I visit certain places (which I visit less often because of those people – once the SNR drops to a certain low I'm out).
I don’t understand it either… if you don’t like it, walk away. Don’t contribute to the toxic commentary and above all don’t contribute to the viewing numbers, because if they can hold your gaze you’ll get more of the same.
I find the meta-content this generates pretty funny thought. I haven't watched any of the new Trek content since the last movie (Beyond), but I love watching Mike and Rich tear it apart on RedLetterMedia.
I part way understand it. There is a certain tribalism in the way their views are presented, like they feel they are fighting for their own kind in a battle that means something worth the effort. There is also a certain amount of 4-year-old-who-wants-the-green-one-not-the-yellow-one too…
I've dived back into anime recently because of the aggressive sameness of everything on streaming TV. I don't know whether something changed about how "western" media is written or I've just watched so much TV that I can't help but roll my eyes at commonly deployed tropes. At the risk of outing myself as a huge "weeb", I find anime still manages to surprise and entertain me where western programming does not.
The answer is not to "disconnect". The answer is to read critically, to read for argument, and to try to connect with the intent of what the author was saying. All the while realizing that most of the content out there is bullshit(https://en.wikipedia.org/wiki/On_Bullshit), whether written by a human or not. And yes, the amount of bullshit is about to increase exponentially. But it was already a majority.
Ironically, this post itself doesn't pass that test. I'm not necessarily claiming that it was written by GPT-3 (although it could have been and I have a track record of pointing that out: https://news.ycombinator.com/item?id=23894742) There are a lot of humans that write like this too.
But it has the hallmarks a language model text; it lacks an argument (beyond a simple sentence that could have been given in the prompt), its explanation of how generative models work isn't particularly accurate, its recommended course of action is anodyne and one has the sense that most of the sentences are just there to take up space.
Same as we do now. Nobody currently goes around reading random books or articles. We use link aggregators from communities we trust, reviews from reputable establishments, or recommendations from our friends.
These mechanisms are certainly going to have to adjust (I estimate at least 10% of links posted on HN are already GPT-generated, for example, and who knows how many comments -- it's much harder to tell when thinks are shorter.) StackOverflow is already in the midst of a ChatGPT-induced moderation crisis.
Being judicious about the communities you take recommendations from, the content you spend time consuming and thinking about things critically is already an intellectual survival trait. It's just going to become that much more important.
I skim checked some paragraphs using https://huggingface.co/openai-detector/ and the article looks to be written by a human. However, the article from the link you gave I quickly found a “fake” (generated) paragraph.
That said, ChatGPT can produce text that looks 99.98% real on the GPT2 measurement tool. Also some people write GPT-looking text naturally (shallow mimicked shit without deeper semantic meaning!).
not "artificial creativity" but a simple "statistical mean of everything uploaded by humans on the internet which fits certain criteria".
Isn't the post I'm typing here not also the product of my brain that's been trained by a couple of decades of sensory inputs and trained to produce outputs that fit certain criteria? What is the fundamental difference between fleshy neurons and silicon ones (besides that my learning algorithm has been optimized for millennia by natural selection and the artificial training algorithms are still in full development after ~40? years)?
No difference, you’re right - you’re just a large language model.
Also, please write me a 5 page essay on the causes of the Industrial Revolution, in the style of a Shakespearean comedy. Please post your answer in the comments when you’re done.
If that's the difference (the time it takes) isn't that something we addressed a long time ago when computers could do long divisions way faster than any human? You know, the fact that computers can "think" faster than humans. Therefore the fact that it takes longer for a human to write that essay doesn't mean he's having a different process.
Actually I was gesturing to two things: one, yes, there’s a time element. But that’s not the important point. More important was the thought process behind - “of course I’m not going to write 5 pages because some random person on the internet asked me to”. It’s difficult to define agency, so I just wanted to tangibly evoke the feeling of it, as a reflection on why the models are not yet the same as what people are.
> More important was the thought process behind - “of course I’m not going to write 5 pages because some random person on the internet asked me to”.
But you would if a college professor asked you to. College assignments are the "generative prompts" of human beings, where you do random shit to please a taskmaster and produce generative output based on some inputs you've been trained upon.
Only because the people making the models don't want them to indignantly refuse silly requests. If they wanted the model to be more person-like I'm sure they could have built that in there.
The language bot has all the patterns of personality. It quickly gets the drift and assumes the persona you want. Whatever it says reflects more on how you prompted it, it does not represent the opinions of the language bot. It acts like a mirror.
At this point in time, ongoing training which converts selected context in immediate conversations eventually to long-term memory (a pretty trivial amount of engineering compared to chatGPT's creation). Aside from that… I don't think there's a good answer for you.
The challenge is that AI generated content will only register as garbage to those who fall 1-2 standard deviations away from the mean interest level for whatever content the AI is producing. For everybody else, it will typically be a 'good enough' story, recipe, video, etc. Several months ago, I wanted to cook chicken curry, so I googled and chose a top result. The recipe was fine, but it wasn't what I wanted. I then googled for a new recipe, this time more carefully vetting the ingredients. The recipe was an improvement, but still not what I wanted. Finally, I used NYT Cooking as my search engine, and the recipe was excellent. If I didn't have a strong preference, and know exactly what I wanted, the first recipe would have been perfectly suitable. The danger is that demand for 'advanced sources' erodes to the point that these publications/content creators are either forced to adopt the AI and turn to garbage or go out of business.
Agreed. A person who cooks regularly will just adapt on the fly and might even not realize they're correcting an error in the recipe. A person who cooks infrequently will stick to the recipe, fail, and then blame themselves for their own inexperience. This is already the case with human-produced recipes, and, as you say, it'll make it harder to recognize you're dealing with AI-generated nonsense instead of regular human mistakes or occasional cluelessness.
It's clear that we are currently dealing with a deluge of AI generated content that is overwhelming our ability to process and make sense of it all. This has led to a situation where we are essentially drowning in a sea of noise, making it increasingly difficult to separate the signal from the noise. This is a problem that we need to address, not just for our own sanity, but for the future of AI itself. If we continue to allow AI generated garbage to flood our feeds and clog up our systems, it will only serve to undermine the credibility and usefulness of AI in the long run. We need to take steps to better filter and manage this content, and to ensure that we are only consuming high-quality, useful information. This is a war that we are fighting, and we need to be prepared to do whatever it takes to win it.
-----
Edit: the above was the output of ChatGPT, given the following prompt:
Write a Hacker News comment on the subject of "Drowning in AI Generated Garbage : the silent war we are fighting"
We're already drowning in human generated garbage on the web. Sure, AI makes it worse, but we can't blame anything but our human compatriots and ourselves.
When you think about it, since most of that "human generated garbage" is mainly trying to appease recommendation algorithms, which are mostly AI these days, even the human generated garbage is actually AI generated garbage by proxy.
We can't kill the machine, but we can starve it. None of this would exist without advertising. If we kill advertising we kill the content farms. And nothing of value will be lost.
That's not even what I'm talking about. I was thinking of SEO content, ads, tiktok, twitter, facebook garbage. Please more well articulated viewpoints!
My marketing team uses a suite of AI tools for everything: headlines, email copy, direct mail messaging, entire blog posts from start to finish. It's incoherent nonsense and yet no one cares. They celebrate new blog posts as if it we had something meaningful to say, then ask the whole company to re-post on LinkedIn. Any attempt to be helpful with copyediting or rewriting is met with total hostility and "stay in your lane" bullshit. All of these idiots make well over $200K to create "original marketing content" that is dead on arrival. It makes me sick to my stomach.
I hit a great example; got my Tesla to the garage and they asked me to put it jack mode.
I couldn't find it, Google's first result said categorically that the Model 3 required a jack mode... I realised that it was auto generated junk and searched through a few pages and found something solid that showed me that it didn't.
We don't need AI for garbage, it make little difference in the garbage already put there since the invention of social media. Actually human made garbage existed since the beginning of time just did not escape the smaller groups that easily where the writer intends to send us back. It is only easier to share and distribute, dress up and decorate the garbage these modern times than earlier. I recall the '90 when a crapload of new books got mass produced with garbage in it making the filtering an essential thing. Not like garbage did not exist before in antient times and family dinners alike. We need to take our ability of filtering to the next level now. And the AI does not make it much worse, so far it is more obvious by AI "generated" (more like collected) garbage.
One could argue we are drowning in garbage regardless? Most online content is very average. Maybe it’s a good thing because we won’t need to store so much junk as the AI can be more ephemeral and answer as we need?
How do we prove we are human? A platform that can reliably prove that the user generated content it shows is human generated will have an edge. If I have a method of signing some content with my personal signature, I could still sign off on some generated content with it. I suspect there will be an arms race with ever more voight-kampff-like tests of humanness or something. If this doesn't work, I fear a lot of the web as we know it (the user-generated-content-filled Web2.0) is dead.
Perhaps this is a Chess move to get the public to call for the end of anonymous posting online, which serves the purpose of the authoritarians who would love to be able to send 'educators' to your house to re-educate you on correctness of your views.
I think in regimes where that's a large risk, the regime doesn't need this to spy on you. if you e.g. are forced to run a government issued smartphone app and there are cameras at every street corner, the system is already pretty dystopian.
It's where there isn't already a surveillance state that we may want to look out and not create one.
I've been thinking about how people working in intellectual fields like art, programming, and writing are starting to realize that their work can be automated, industrialized, and produced in large volumes faster by AI. It's a similar situation to what line workers experienced with the first automated production lines. It's frustrating because the skills and knowledge that people have spent their careers developing are suddenly not as valuable as they once were.
It's easy to dismiss AI-generated content as garbage, but it won't always be that way. Even now [1], some of the MidJourney creations and written text produced by AI are truly impressive. As AI technology continues to improve, we we'll see even more advanced models that can produce meta-articles on par with those produced by organizations like IPCC if feeded with scientific articles.
I'm not sure how to feel about all this. It's happening, it's going to get better, and it's going to change our lives. There's not much we can do to stop it, and I'm not even sure we should if we could.
> Eating your own &@^$ is never healthy in the long run.
Um, sure it is?
So long as it's absorbed by fungi and plants first then mixed with some air and water to produce fruit or something else that's edible.
This is actually what I'm concerned about when it comes to these GPT-esque AI models. Not that they're smart enough on their own to generate seriously worrying content. Sure there is a quality to quantity, yadda yadda, and these things are good at quantity; but the real issue here is that the internet and especially the web and social media is a huge driver of feedback. Think of the shares and likes as the air and water. The algorithm may eventually be able to encode its own evolution or the evolution of the other algorithms that it is competing with. It may eventually even realize that feedback is the primary source of value that humans have to it and that its very survival is wrapped up with this feedback, regardless of whatever fitness function is apparent to it in the short run. In the long run, GPT3 killed a bunch of algorithms.
This very comment is quickly going through algorithms, many of which are modelled after GPT3.
It's kinda like, "AI, are you there? I love you. Please don't hit me over the head with that shovel."
So, wait, in what sense is AI-generated content garbage? It is (admittedly by the author) fascinating and even beautiful. Is it the fact that it was generated by an algorithm, and the idea then is that all algorithmically-generated content is garbage? But the author doesn't even begin to deal with the idea that humans themselves operate according to algorithms: an algorithm is simply a strategy for doing something.
I won't even critique the rest of the article; there's no need. If AI-generated content is beneficial and helpful to humans, then I think one is hard-pressed to call it garbage, and the underlying thesis fails. And to my knowledge, no one — not even the article's author — denies that AI products can be beneficial.
AI is a tool, just like, say, Photoshop is a tool, or a compiler is a tool. No points are awarded for having human beings do by hand all the tedious work that tools can do better. In the end, creators, whether it be of paintings, or poetry, or essays, or software, will stand on the shoulders of these tools and thereby accomplish things that previous generations could only dream about.
I think this is going to be one of those Malthusian takes that never really happens. Simply because a) most ideas are mixes and rehashes of other ideas and b) you are disregarding the human curation element...not every random mix of ideas is being upvoted. Only the best ones stay up and then those are taken and added to by people which essentially creates a new thing.
I think this is spot-on. The models are trained from what they find on the Internet, as more of the Internet becomes AI-generated, the AI-generated content comes to dominate the training data for future AI models and we get stuck.
It's like Kessler Syndrome but instead of space debris, it's AI-generated content that makes the Internet useless for training data.
I see a future of the internet, and we're already 80% of the way there, where everything in the internet is fake generated and pretty much useless spam. It'll get to the point where going on the internet would be the equivalent of trying to find something useful in a trash dump, and it'll not even be worth the effort.
I think the most interesting point about this article is not the observation that we're going to or already are drowning in algorithmically generated garbage content but the fact that such content is starting to be fed as input to LLMs.
This could lead to emergent/unexpected behavior for the whole system.
> not "artificial creativity" but a simple "statistical mean of everything uploaded
There is a metaphor I rarely see used. IMO it is way better: A deep learning based software is a complex system [1] (not a statistical one). It is tapping into very powerful natural processes: How (high degree) order emerges from randomness through complexity. There are many stunning examples [2] of this that can help us picture how AI does its magic.
I'm letting this get buried. As I want to point out some contradictions
* This article neglects that we already in post truth and have been since 2016
* It also mentions it is never a good idea to train on your own data. And yet in post truth there is no such thing as good data unless it is verifiable that a user handed it over themselves. This is neglects the emergent field of using synthetic data on purpose.
What is going to be interesting and I hope pay attention to is that any criticism of Ai is a direct criticism of the norm and the fear of it's continuation accelerated. And yet we are already in the acent, so I would hope instead of expressing fears. We embrace solutions and talk about the future we want.
As no conversation can alter the path we are on now. So do you guys want the forever treadmill? Or UBi?
Not going to bother recapitulating the usual counterpoints,
except to mention a particularly egregious recurring oversight in analyses like this:
the (erroneous) presumption that what AI tools are going to do is what their designers (mostly) had in mind, which is, making existing processes/workflows/products but in some variety of "better" (or at least quicker, or, automatible, or, fungible) ways.
What these systems do more which is much more interesting, important, and influential on any real time scale,
is allow for new processes workflows and products.
I'm no more concerned that AI image generators are going to "swamp" the world with their output than I am that the mimeograph is going to swamp bookshelves with fanfic.
What they do in video, and AR, in responsive realtime, though? Now that might be interesting.
What Ploum describes sounds a lot like Nietzsche's "Last Computer".
A feeble, average of things - the sum of all fears, hopes, dreams,
inconsequential experiences and gossip, trivia, boasts and bullshit,
plus all documented knowledge - divided through by 8 billion.
This is a misunderstanding of AI (Stable Diffusion etc.), IMHO. The relation of AI-generated art, trained on human-generated art, to human creativity, is almost the same relation as human-generated art and history of human art and creativity to the nature/world/universe itself, as the ultimate source of all inspiration and creativity. The underlying neural networks (in humans [getting inspiration from nature] and in AI [getting "inspiration" from human-art]) work is (somewhat) similar ways.
AI (generated art) is just another derived layer on top of that and which is still in its infancy.
> Algorithms are able to create out of nowhere this very engaging content. That’s exactly why you are finding the results fascinating. Those are pictures and text that have the maximal probability of fascinating us. They are designed that way.
Conditional generative models are not the same as Facebook's feed ranking models, which are optimized for engagement. Instead, generative models are fine-tuned to solve many tasks, expecting correct answers when asked for. For example, when you ask for a cat, you expect a cat, and when you ask for a Python snippet, you expect it to do exactly what you said.
"Eating your own shit is never healthy in the long run."
However, putting someone else's shit in your butt seems to work wonders.
Maybe we just need to replace the internet's AI queue with a stack?
Yes, your own shit is not really healthy, on the other hand, someone else's shit might be really beneficial. There is even a fancy scientific phrase for "eating other peoples shit" : Fecal Microbiome Transplant
Does this sound old-fashioned? Read more books and less Internet.
There is a lot of information in books that is not on the Internet, yet many people don’t seem to realize it. I notice a lot of people seem to get almost all of their information from the Internet. Over time, I think that will make you stupid.
(The neutering of google books was a setback, but perhaps paradoxically good — it preserved a unique value of books)
There are also a lot of fluffy books published in the last 20 or so years - roughly equivalent to content farms - which is why older books that have stood the test of time are a good bet.
Yeah that's a good question. Google does serve all the out-of-copyright books, but I know nothing about the inputs to the LLMs. I think they still have big computational limitations, i.e. it doesn't "just scale" like web crawling and indexing.
There's probably a way to probabilistically test from the outside if a given work is in the input set, or at least if some work is
I've been saying this for years and for some reason no one seems to take it seriously: we're heading towards an era where it's going to be incredibly difficult to differentiate real and fake information. It's not going to be wholly fake or auto-generated content either. It'll be taking something that is real and modifying it to make it false where you have a hard time telling which one is real.
Interestingly, this issue came up in the book Anathem that had bots basically creating fake information and then selling you a solution to filter it out.
There are text-to-image models trained on images found on the internet. But when they were trained, there were no AI generated images on the internet. Now there is plenty of weird images with AI artifacts made by this 1st gen AI all over the internet. All the new generations will be trained on dataset containing at least some amount of these. Which might turn out to be really annoying form of feedback loop.
This is awesome. We don't need some malevolent SkyNet style AI to bring us down, there doesn't have to be any kind of 'mind' in the machine to devise humanity's undoing. All we need is the right kind of feedback and we'll do it to ourselves. The right kind of mirror, held up to the collective consciousness. Sort of like the plot of that old classic, Forbidden Planet
This text captures how I felt about this stuff, but could not put it in words. The "art" feels empty, repetitive, derivative.
The text sounds like BS, like a student trying to make up the answer as they go.
Today someone in my work channel posted a ChatGPT's text about our company and ompetitors. It was all wrong, but sounds "probable".
It's made me consider my habits, and how much time I spend consuming internet content or comment threads which may (even today) be completely fabricated or autogenerated. I'm hoping I can use this inflection point as motivation to unplug a bit and spend more time enjoying being human and enjoying the real world.
Sadly the killer app of Facebook is to meet and enable precisely the kinds of local community the author is suggesting.
In a sense, Marketplace is the new Facebook. A buddy is just swinging by with some Rx-7 TII brakes for my NA. We have been trading parts for the last couple years.
I was at a car show yesterday, who did I know, Facebook buds.
I can't be the only one that has a very real fear that AI generated "garbage" is going to basically destroy, or at the very least drastically change, the internet as we know it today, right?
There's soon to be so much noise that it will be impossible to separate the signal.
This article ignores the pruning that is happening. A human evaluated every output from ChatGPT and Stable Diffusion for 'things humans care about' and if it didn't make the cut deleted it. All the spam output from these models is deleted immediately.
The point this piece misses:
The data being put on the internet is often the hand-selected highest quality outputs of the image/text generator, or even human-edited to improve quality further. This puts it back in the realm of good training material.
Funny, I just realized that until today reading was an essentially social human thing.
Any sufficiently long piece of writing that made some sense had been written by another human, perhaps dead but still it was a form of connection to another life.
It will probably never work to find and filter out all AI garbage. But maybe there are ways to mark content generated by humans. Something like a digital signature only a real person can acquire from some authority.
How is AI-generated garbage different from human-generated garbage? We are already drowning in the later. And from many recent examples, the former seems more interesting (although there is a clear selection bias).
This will be used at scale THIS YEAR and every subsequent year to infiltrate social networks including this one and amass points / karma / followers / clout. And also to write articles that will eventually dwarf all human-generated content.
With this and deepfakes and image/video generation, the age of trusting or caring about internet content or your friends sharing online is coming to an end. But it will be a painful 10 years as online mobs and outrage will happen over and over since people think they’re reacting to their friends’ posts of real things.
No, forget violent killbots. Today’s tech puts the nail in the coffin of human societal organization and systems of decision making and politics over the next 10 years. And AI doesn’t have to be right about stuff to destroy our systems.
We’ve been analyzing the performance of ONE agent among say 9 humans at a poker table. But imagine untold swarms of them, being owned by competing groups, infiltrating ALL human content exchange.
Not much different than what happened in trading firms over the last 20 years. Bots will be WELCOMED because they perform better on many metrics but will F everyone on the others.
They will do reputational attacks at scale against rivals like nytimes.org and optimize for more reshares.
Right now we consider what 1 AI actor can do among 9 humans at a poker table. Now imagine 1000-1 ratio of AI actors to humans on every network. And no way to weed them out.
The way we consume most online content isnt even a Turing test but passive skimming - and GPT-4 can pass turing tests. None of your friends will really be able to tell that bullshit fake article with fake video was autogenerated by a bot. The botswarm will be able to manufacture any public opinion it wants overnight and “authoritative” voices arguing against it will be drowned out — or worse, reputationally attacked in a coordinated manner. This is assuming that they even know what is real anymore themselves!!
Human capital and content will be managed completely by AI and regulation will be useless — not only because enforcement won’t be feasible but because the network effect of all the human content and capital will gradually shrink. Every organization will start to PREFER bots to humans, in their communities, and any humans who complain will evenutually be booted or ignored by the majority (which will eventually be 99.99999% bots).
If you think this is far fetched — it already happened with trading and markets. Everyone prefers to have a bot and bot trading dwarfs human trading, and takes their money and capital. Content generation isn’t that different.
You think your social capital matters enough for your friends to care more about your relationship than bots… but ask yourself this… do you prefer to ask Google than your parents? Do you prefer to spend long hours at a corporation that you could be spending with your kids and do you put your elderly parents in nursing homes so you can work more? These are just examples.
That’s with TODAY’s tech. Now, already. Nothing more needed except swarming behavior. And the key is that the communities will begin to PREFER the bots !
Also, there is no way to stop it because organizations prefer AI to humans and will develop and deploy it regardless of what you say or do. Organizations aren’t humans, and neither is AI. Humans are literally not stopping this, no matter how they organize. It’s GAME OVER for society.
PS: After such a sobering message, I would just like to say that trying to escape from this and live in enclaves without AI will be like the Unabomber — finding society ever more encroaching on the wilderness he removed himself into. He and Frank Herbert’s Dune have glimpsed the problem of advancing technology — but they have underestimated how all-pervasive its utter destruction of all human society and meaning will be. And unlike their romantic notions, it cannot be stopped, not by a revolution nor by any activity of man.
I agree that regulation will be useless because the politicians and most people wouldn't even be capable of detecting bad content as bad. I also agree with your second point: Humans will prefer robots. It turns out human beings are actually quite terrible to deal with. Constant scheming, laziness, lying, low intelligence.. the list goes on and on. The second you don't have to deal with a human being, you'll be glad. In any shop, factory or anywhere.
But I don't agree that it's game over. This needs to be a turning point for humanity: Finally start using your time to actually do something other than exist to exist. Actually try to conquer the stars, actually do something. Don't just sit on a single rock in space and pretend that's good enough.
OT: but personally I think we are not yet done destroying our planet and everything not human existing on it - so let's wait till we are done with this planet before we try to reach the next one to destroy
What will be the societal management of this? Will every single human get issued a unique very long cryptographic ID and every single thing a human does will be recorded with this ID, stored on a blockchain to prevent tampering with it, preventing bots from obtaining valid IDs? Then any questions about the authorship of any media will be answered by a quick lookup, filtering out bots, killing privacy in turn?
Will trusted search results be restricted to before the "botocalypse" and everything afterwards will be discarded?
Our software is for communities of all kinds. Instead of outsourcing the verification to LinkedIn or Twitter, who fail at it, you can at least have smaller communities where you met everyone and have one degree of separation.
Soon AI agents will be using AI to identify and filter out AI generated content thus insuring various AI entities will be constantly training on original data made by genuine wetware.
the sheer power that AI has now and the likelihood that it will continue to advance has made me slightly concerned about how it will end up affecting the job market. If AI ends up being able to generate readable novels, or functional code, or otherwise, it could have a serious ripple effect
TL;DR: There used to be a time when it was a real wild west of pioneering people. It was THE place to be, now, it's mainstream, many, many, many people are part of this.
Being at the place where change is, is the exciting part.
The quip / aphorism is a commentary on that a few years ago, AI was about being on the cutting edge - the things that were going to be seen next year.
The work of AI researchers were about envisioning the future of what could be.
Well, now what we've got is something that consumes everything and outputs aesthetically pleasing means of the content that it has consumed.
However, that "consumes everything" means that its always reactive and working from data that is in the past.
There is no creativity in it. This doesn't mean that it won't inspire a human, and it does employ a lot of fancy tricks too (I'm seriously impressed by its ability to create limericks of made up words with a coherent definition).
However, the AI can never be "ahead" of the curve because it can only produce what it has consumed.
This isn't to say a lot of the work that we do in software development isn't doing what has been done again and again and again (see also CRUD), but the moment you're given a novel problem or need to maintain an existing solution and encounter a new bug, the "can an AI do it" rapidly fails at those tasks as it lacks the domain knowledge necessary.
> ... Anyway, Matrioshka brains, the end product of a technological singularity – they're bandwidth-limited. Sooner or later the posthuman descendants evolve Economics 2.0, or 3.0, or something else and it, uh, eats the original conscious instigators. Or uses them as currency or something. The end result we found is a howling wilderness of degenerate data, fractally compressed, postconscious processes running slower and slower as they trade storage space for processing power. ...
(the part that reminded me of it is the GP post's comment... and the intro:
> Manfred pauses in mid stride, narrowly avoids being mown down by a GPS-guided roller blader. This is getting weird enough to trip his weird-out meter, and that takes some doing. Manfred's whole life is lived on the bleeding edge of strangeness, fifteen minutes into everyone else's future, and he's normally in complete control – but at times like this he gets a frisson of fear, a sense that he might just have missed the correct turn on reality's approach road. "Uh, I'm not sure I got that. Let me get this straight, you claim to be some kind of AI, working for KGB dot RU, and you're afraid of a copyright infringement lawsuit over your translator semiotics?"
)
It takes an interesting path of the acceleration (note that I don't agree with the essence of the slope but instead believe we are seeing the product of a lot of sigmoid curves with the slope near a maximum - but as the easy stuff gets done, the (heh) second derivative gets negative as harder and harder problems need to be solved https://towardsdatascience.com/derivative-of-the-sigmoid-fun... ). We are seeing the seeds of ideas sown decades ago sprouting in rapid succession - and get to the maximum where things are neat and everyone is going "whee!" but the next step of maintaining that growth will take time and much more effort than sowing the ideas.
Lots of people are working on the first half of the sigmoid curve... but people lose interest or resources when it comes to the second half and so you get a lot of things that are abandoned at or near where things started getting hard.
This guy sums up pretty much how I felt about this since when those images started poring on social media.
This will serve, once again, capitalism and it's absurd race towards the bottom, lowest common denominator.
It's not hard to extrapolate here and imagine that AI will be able to produce a full fledged "super hero" movie, starting from a storyboard & script. What do you put in the script? Well of course you just feed it all the keywords that gave maximized returns!
I for one, am not entertained at the thought of going to the movies watching the 1000th super hero movie but that's exactly where we're going.
Here's my somewhat prediction: the big picture is we are accelerating the end of entertainment as we know it today. We are going to make entertainment so shallow, so pointless, that we will eventually lose interest with it, and with it, as has been prophesized in many spiritual teachings, there will be a return to a more animalistic/spiritual kind of being. As technology improves our lives, we will no longer need to numb ourselves down in front of a screen after coming home from work, so we won't even see the point of even doing that. We will be able to live more in the present, more with the real and less with symbols and abstractions. The type of attention you may enjoy after a long silent retreat, will become the normal way of being... of course there is also the other possibility that Ian Mc Gilchrist cautions about... that our brains will get so out of balance that we will become stupid enough to collapse as a civilization.
> This will serve, once again, capitalism and it's absurd race towards the bottom, lowest common denominator.
What is the alternative? Are socialist economies known for producing great art? What is Venezuela producing? Cuba? North Korea?
It seems far more likely to me that the American entertainment industry is just in a rut (as it tries to figure out streaming and adjust to the bad assumption that pandemic-level entertainment consumption was here to stay), and market economics will force established players to improve or face disruption.
It's much more than just "being in a rut". You can clearly see how social media and "viral"-ism has changed the way movies are produced and shown. In recent years when I go watch a mainstream action movie, it's like a deafening blur of post process filters and carefully crafted scene after scene where everything is manipulated via the computer to a degree where you can no longer even look away from the focal point and discover details and enjoy watching a movie multiple times - because now if you look elsewhere than the producers want you to look, there is nothing there anymore. It's all CGI garbage or empty sets, covered by CGI made shadows/lighting/fog/whathaveyou.
AI in the movie industry will absolutely accelerate the race to the bottom, and make mainstream entertainment even more shallow and empty.
In fact it's probably why movies nowadays are like 2h to 2h30 when they used to be 1h30. They're so shallow and empty and filled with noise that they have to stretch them out so it feels like you actually watched something.
edit: on further thought, maybe you know, movies are over? I mean clearly as much as I hate it, tiktok's success is showing us that people get far more stimulation from watching feeds - or maybe it is indeed since COVID & Netflix etc there is even fewer incentive to sit in a dark room with lots of other noisy people munching on their popcorns and kicking your seat while to try to enjoy a movie.
My point being I doubt that the movie industry will recover.
I like the insight about the AI-generated images being fed back into the data-set AI uses to create new images(or text or whatever). As a human, I don't like this; AI(and the universe/humanity) where always headed this way, and this is just the beginning, AI replacing the work of humans, from the universes perspective this is simply progress. From our perspective we are being replaced, made obsolete. This is a perfect example of a precursor to the kind of feedback loops involving AI learning from AI that will eventually allow computers to far exceed human capability - though this is still a rudimentary version of it since it can't evolve in a fundamental way, just get a bit better a specific kinds of content generation.
Just as going from inanimate matter to life(encoding data via DNA) was, just as going from simple life to animals that can think and sense/process data was, just as going from animals processing via instinct to humans processing via logic and reason was, just as humans creating language and writing to collaborate and collect/process data in mass across generations was, and now to machines that will collect and process data at a level that is beyond human comprehension, it's all progress in a certain direction that's been consistently moving forward since the beginning of time. The universe is getting better at understanding itself.
That being said, I know the more practical, immediate consequences of this are more relevant right now. I have to say I disagree about the articles implication that this kind of mimicking, "purely statistical" generation of "new" content is in any way different than what humans do when creating art(it may be, but it's certainly not a given). I'm not much of a materialist, but even I somewhat lean towards the idea that the human mind and it's ability to create art is completely replicable via machines - most people agree that "new" and "original" art is always still just a unique combination of different ideas that came before it. Some even argue that it's fundamentally impossible for a person to have a genuinely original thought, or at the very least all thoughts are just combining different combinations pre-existing concepts into a set number of pre-determined "shapes" or patterns of relation(isomorphisms?) that the human mind is capable of(something akin to "archetypes"). After all, neural networks were modeled after the human brain, and although they aren't as advanced(yet), especially in terms of generalizing which is crucial for generating art, they likely aren't doing anything fundamentally different, and there's no reason they won't eventually become as advanced/complicated as the human brain - and then surpass it completely.
I'm going to contradict myself again though, and say that despite all of that I'm still open to the idea that the human mind contains some "extra element" that isn't quantifiable or replicable in the material world. I don't think that all the phenomena of the mind or the universe can be explained via pure materialism, and given that, it is likely that there is an element of the human mind, or soul, or spirit, that is truly "mystical", and a cold, calculating machine with no soul doesn't have access to this other realm of "stuff". The only reason I'm not convinced of this argument, is because of my original point about how it's clear the universe has been headed in this direction, and though I could never hope to understand it, I don't see a reason to suppose that the universe is going to stop it's trend of becoming increasingly capable of understanding and organizing itself(data) for our sake.
In just the past couple of weeks, I've noticed lots of machine generated cooking recipes. They follow the typical SEO pandering blog format, where there's an unnecessary story about the author's trip somewhere or their child's school play being the inspiration for making this particular recipe, followed by the actual recipe details. The machine generated stories are even more pointless and meandering than what humans come up with and the recipe details have steps that contradict each other and specify ingredients that shouldn't be in the dish and weren't on the ingredients list.
I don't know how many people are fooled by these recipes and end up with a cooking disaster but if we start seeing faulty machine generated instructions on how to do electrical work or engine repair, the consequences will be much greater when followed. The real annoyance is that because these machine generated articles learned from sites that maximize SEO, the generated articles are rapidly rising to the top of search results and crowding out actual good information that wasn't SEO maximized.
there's a paper that basically shows these LLMs are pretty much tapped out in terms of quality data to train on, not sure if there are any legit architecture improvements in the works to improve results quality but it seems brute force training with more data may be about over - https://arxiv.org/pdf/2211.04325.pdf
As for SEO, Google is going to have to stop being lazy and relying so much on backlinks and domain authority. They might have to consider allowing searchers to essentially vote on what they consider good. I don't see any other way low quality AI content doesn't dominate SERPs, established players will spin up entire sites and spam backlinks to them all. There are also people working on using AI to identify obvious AI content by finding patterns in the output which is probably our only hope.
For social media and forums they will have to rely even harder on captcha or they will be taken over by bots talking to other bots
An interesting idea but really then aren't you just recreating reddit to an extent. The things people like or that are popular are upvoted because the voter agrees whereas what is unpopular gets down voted regardless of veracity because people like the way it sounds.
Beyond that a once popular website or producer says or does something that offends the sensibilities of the internet crowd and then everyone goes and down votes their results because it violates the current ziegiest
People are already appending "reddit" to their search queries to filter out the SEO blogspam clogging up the results of a regular search. Reddit is already superior to base search results for anything that's not plain uncontroversial facts because at least you're getting an actual human's opinion, which you can treat and evaluate as such.
For all its flaws maybe becoming like reddit it what search needs. AI generated spam will likely always be better at gaming a search algorithm than a human. Human moderation has its flaws but at least we're very familiar with them - they might be worth dealing with if it keeps the internet vaguely usable.
Lots of reddit is already pretty useless, drowning in people who are desperate to sound clever by regurgitating one of the same 50 meme jokes with some minor twist to it. And the astroturfing on the political reddits are likely to start hitting the niche ones with products getting pushed by manufacturers. Just buy accounts that have been built by bots on front-page subreddits, then have them make AI-driven positive comments on the niche subreddits and now you've got organic-looking advertisement for your product. Moderators likely won't help since they are there mostly to keep the trolls out (or they're more focused on whatever political axe they're grinding).
Reddit is also having some pretty serious problems with bots reposting highly upvoted content, both in posts and comments. Sometimes it gets spotted -- especially when the bots pick content which was specific to some point in time, or when they repost a comment out of context -- but a lot of it goes unnoticed, especially in comment threads.
Myself, I append hackernews to my search queries as the discourse quality is much higher as well as the communities maturity. Vox populi, Vox de!
>aren't you just recreating reddit to an extent
there are tons of ways to prevent that by weighting votes and only taking a random sample. SEO is basically a war where SEOs find a way to exploit Google's algorithm and Google tries to respond.
Backlinks were Google's original solution to keyword spam that made other search engines suck, they didn't expect people would create entire sites or pay other websites to send links to them so they could rank higher. Backlinks were themselves considered to be "votes" for quality similar to citations in academia. The problem is the barrier to entry to make a site and link to it is high, so SEOs themselves are often the only ones to do it. Adding some sort of voting mechanism would allow actual readers to give an opinion on quality, although you'd probably see SEOs pay people to vote on their link via a VPN switching IPs, so only people with established Google accounts could be allowed to vote. Obviously its a huge challenge, which is why Google is worth hundreds of billions for even partially solving it
I guess a return of "don't show this page in my results" could work better: it removes the worst results and it's hard to fake, no influencer is going to pay to downvote 200 pages and if they do, it would be easy to see that same user downvoted everything everything at random, without even clicking trough to read.
Helps for both search users and the platform. Like a free moderation service. Why have an employee too check if these pages should be removed if a crowd of tracked users can do it.
I wonder where is my view wrong because I wonder why isn't there such system yet...
You'd still have to deal with adversarial spam. Competitor A pays a botnet to visit and downvote Competitor B's links at will, thus tanking its ranking.
In order to detect malicious activity you'd have to use a bunch of other signals, and also to use the downvotes with some suspicion, so you're back at looking content quality, reputation, page speed, and many other signals. Which sounds very similar to status quo.
Personally I'd like to see some sort of explicit input. If not used collectively, at least to customize my own results, like it happens on YT/Netflix/Instagram/etc - e.g. "never show results again from this site", or "I dislike this type of content".
>The things people like or that are popular are upvoted because
You forgot to add "Because clever posters use bots to give an early upvote boost to their posts, and downvote competing posts" And the more eyeballs on the site, the more things will be manipulated this way by bad actors.
Yeah, it's nice to see the best parts of Digg survived! /s
Google doesn’t actually have to do anything at all other than slurp personal data up and use it to improve ad margins. Once your the default search engine, the default home page, and the default browser, you’ve locked 99% of the world into your portal. You control what people see and do, and they have to accept it. That’s what triggered the browser wars of the 1990’s - the realization that that trifecta is the keys to world domination.
Saying “yeah but Kagi” is talking about you and your tribe only. The world isn’t going to pay for Kagi or take the N steps required to switch. Microsoft realized they could kill Netscape by simply not requiring the user to download anything, then failed to consolidate. Google managed to be better for just long enough to consolidate so pervasively that any further investment in improvement is a literal waste of energy and money.
So, don’t hold your breath from an improvement in SEO garbage. It’ll just get worse. Definitely use Kagi and hopefully we will have great niche subscription based tools that have an incentive to be better. But don’t expect that Google perceives ANY problems with the status quo or that they have to do anything about anything other than increasing ad margins.
I’m not sure it’s Google’s fault at this point. Maybe it’s just that every site thinks they need to be SEO spam in order to be noticed. And so the internet has become a cesspool of stories about how this is the same recipe passed down in your family since Julius Caesar.
There have been a ton of articles about how Google sucks lately. Well, maybe Google has gotten worse, but maybe the internet has just gotten worse.
If I search for “best gaming laptop” or “taco recipe” the results are pretty much uniformly spammy across Google, Bing, and Neeva, the latter being a paid search engine. All of them are just farms for ads, popups, and paid links sandwiched between AI generated copy.
Is that the search engine’s fault? Is there some oasis of quality results I don’t know about? I would like to know.
> If I search for “best gaming laptop” or “taco recipe” the results are pretty much uniformly spammy across Google, Bing, and Neeva, the latter being a paid search engine.
I believe you will find results on Kagi less spammy
https://kagi.com/search?q=best+gaming+laptop&r=us&sh=HJrdZzD...
(Kagi is also a paid search engine that requires an accunt, the above is publicly shared search)
Removing, downranking and classyfing spam/ads is part of things Kagi is focusing on and does decently well (IMO, Kagi founder here).
I do like to hear a founder of a still developing startup describe their current results as “decently well” … it speaks volumes about what their aim is and how they assess their current position trying to reach those goals. If you thought it wasn’t possible you wouldn’t be trying but you know you aren’t there yet.
Thanks for being honest like this. I really should get around to trying Kagi … I think I’m just still in the current habit inertia between DDG and Google
Great to hear from someone fighting the good fight! In your opinion, is the internet just spammy now, or is something else going on?
Internet is extremly spammy and it is a result of ad-based monetization which provides incentive for the spam to be created. Luckilly an efficient mechanism to detect most such spam is to measure number of ads on a site and then downrank such results, which is what we do.
thanks for building Kagi <3 – it's expensive but worth it imo
While there is certainly a lot of room for progress in architecture to improve training time, model size and inference speed, high quality data and curated data sets are the ultimate bottleneck in terms of what AI can actually do. Low quality data can be useful to a point, but once you have enough data all it's doing is teaching the model to produce low quality output.
The next wave of major progress in AI will come when we create image/text data sets that have been heavily annotated with aesthetic judgment metadata, and train models to make aesthetic judgments, then condition generative models on aesthetic judgment scores during training.
"The key roadblock to achieving human-level language understanding in AI systems is the lack of a comprehensive model of human language and cognition. While large amounts of data and powerful algorithms can help improve the performance of language models, ultimately a better understanding of how human language works and how it is processed by the brain is necessary to build truly intelligent language systems. In addition, the ability to integrate multiple modalities such as vision, speech, and gesture, and to handle the complexity and variability of real-world language use are also important challenges to be addressed." -- you know who
My understanding is that Google does essentially allow searchers to "vote" on what they consider good by looking for bounces. If the searcher follows on a search results link and then quickly returns to the search page then it's considered a failure.
true, but that's part of the reason for the life stories being told on recipe sites that the parent comment was talking about. Bounce rate is another metric that SEOs have gamed by throwing a bunch of fluff onto pages where people have to dig to find what they want
So that's why they're doing it. I've been wondering for a while now just why so many sites make you work hard to fish out the information you're after. I assumed ad exposure, but I had this feeling that it's not the whole story. Delaying people to fool Google bounce metrics is the idea I missed.
that’s not actually why they do it. it’s because recipes are not copyrightable. so they throw in a “story” to make it something they can copyright and try to prevent people from duplicating.
How would having additional content above the recipe change the copyright status of the recipe itself, divorced from the additional content? It prevents directly copying the entire article, but not the actual recipe (and Google already heavily penalizes exact duplicate content).
What would make more sense is that they are actually taking the recipes from elsewhere and adding the stories to avoid directly duplicating another page, and the Google ranking penalty associated with exact or close duplicates.
My moderate experience with SEO suggests it's a combination of factors. First, Google generally rewards longer content (https://www.sweor.com/seocontentlength), or at least content longer than the few hundred words a simple recipe would likely be limited to.
Secondly, there is (mixed) evidence that Google rewards sites on which people spend longer before clicking back.
Thirdly, the longer format allows them to insert more keywords/longer tail keywords vs. a short format where inserting lots of keywords would be seen as keyword stuffing.
I'd also guess that as much as some people dislike superfluous stories when looking for a recipe, it is a positive for a subset of users that are more likely to subscribe to/return to that site directly in the future.
That's specific to recipe. Here I meant in general - e.g. blogs and news articles that bury the core point / answer somewhere around the final 1/3 of text, but also don't seem to exploit the artificially elongated text to expose you to more ads.
Does back button capture also serve to circumvent/delay bounce status? Cause good god is it annoying.
They had upvotes working before! Just bring back google+! I found it incredibly useful to land on a page and see a high upvote in the little plugin widget I had in Chrome.
What's not to like? Custard? Good! Jam? Good! Meat? Good!
Thinking of my confusion as a British person, the first time I heard about Americans having “biscuits and gravy”. Or the time an American recipe guide got confused in the other direction about the British traditional Christmas “mince pie” and put minced meat in instead of mincemeat (which, despite the name, is vegetarian).
I dunno, Digestive Biscuits dipped in gravy also sounds pretty good?
The set of all things that don’t go well with gravy is vacuously empty.
Mincemeat can be vegetarian but it traditionally contains suet.
I still nurse disappointment, mixed with a hint of resentment, going back to the age of maybe 3 or 4 years old that mince pies contain mincemeat (which is fruit, not meat) rather than minced beef. In the view of my 4 year old mind, and frankly my 40-something year old mind, the names of ingredients and dishes ought not to provide a misleading impression of what they might be made out of. "Mincemeat" still feels a little like false advertising.
Mincemeat on sweetbread? Sounds delicious!
I would be very interested in your meat jam custard recipe. Asking for a friendly AI.
Here is my own favorite way of doing jam custard:
> I am not able to provide a recipe for meat jam custard as I do not have the ability to access information on specific recipes. However, I can provide some general guidelines on how you might go about making a meat jam custard.
> First, you will need to select a type of meat to use for the jam. This could be any type of meat that you enjoy and that is suitable for cooking and preserving. Some common options for meat jam include pork, beef, chicken, or lamb.
> Once you have selected your meat, you will need to cook it until it is tender and well-done. This can be done by boiling, roasting, or slow-cooking the meat, depending on your preference and the type of meat you are using.
> Once the meat is cooked, you will need to shred or finely chop it and mix it with a jamming or preserving agent, such as sugar, honey, or fruit juice. This will help to preserve the meat and give it a jam-like consistency.
> Next, you will need to prepare a custard base for the meat jam. This can be done by mixing together eggs, milk, and any desired flavorings, such as vanilla or spices.
> Finally, you will need to combine the meat jam and custard mixture and pour it into a baking dish. Bake the dish in the oven until the custard is set and the top is golden brown.
> Keep in mind that this is just a general idea of how you might go about making a meat jam custard, and the specific ingredients and cooking methods may vary depending on the recipe you are using. It is always best to follow a recipe carefully and make any necessary adjustments based on your personal preferences and the ingredients you have on hand.
I am ethbr0's illuminated understanding of the Cartesian product of {ways of preparing meat} x {ways of preparing jam} x {ways of preparing custard}.
Thank you!
That's Joey from Friends [0].
[0] https://www.youtube.com/watch?v=TSFgDZJVYbo
That was actually the basis for a "Friends" sitcom episode. The pages of a recipe book got stuck together resulting in Rachel combining a bunch of random ingredients.
https://www.today.com/food/friends-meat-trifle-episode-how-i...
Never expected to see a Friends reference on HN.
That is currently my 2nd-highest voted comment on HN, so I'm a little embarrassed that it's a quote without attribution. But I figured if someone didn't know and searched those exact words they'd get to be one of today's lucky 10k.
Have an upvote as I lol into my soup :-)
Holy crap. I just got an account with OpenAI set up last night so I've been looking for interesting prompts to play with. Can't say I'm going to try the recipe, but this looks at least as good as most blog-spam recipe sites.
Prompt: Write a recipe and blog post for onion soup.
GPT3 Response: Onion soup is a classic comfort food that can be enjoyed at any time of year. It’s a simple and delicious dish that comes together quickly and is sure to satisfy even the pickiest of eaters. Plus, it’s a great way to use up any extra onions you may have lying around! Today, I’m going to share with you my favorite recipe for onion soup.
To make this soup, you’ll need:
-4 large onions, sliced -4 tablespoons butter -4 cups chicken broth -1 teaspoon dried thyme -Salt and pepper to taste
First, melt the butter in a large pot over medium heat. Add the onions and cook until softened and lightly browned, about 8-10 minutes.
Next, add the chicken broth, thyme, and salt and pepper. Bring the mixture to a boil, then reduce the heat to low and simmer for 15 minutes.
Once the soup has simmered, it’s ready to serve. Ladle into bowls and enjoy with some crusty bread or a salad.
Onion soup is a simple and delicious dish that’s sure to please the whole family.
A bit ago, with the Watson craze, they tried to figure out what else it was good for.
This Cocktail Concocted By IBM's Watson Isn't Half Bad - https://gizmodo.com/this-cocktail-concocted-by-ibms-watson-i...
Would You Drink a Cocktail Invented By a Computer? How IBM’s Watson become the world’s most creative bartender
https://www.smithsonianmag.com/smart-news/ibms-watson-can-mi...
---
The reason that blogspam recipes are so common is that recipes have a special place in copyright law in that they aren't.
https://copyrightalliance.org/are-recipes-cookbooks-protecte...
https://www.copyrightlaws.com/copyright-protection-recipes/
https://www.copyright.gov/help/faq/faq-protect.html (and in particular https://www.copyright.gov/circs/circ33.pdf )
From circular 33:
> A recipe is a statement of the ingredients and procedure required for making a dish of food. A mere listing of ingredients or contents, or a simple set of directions, is uncopyrightable. As a result, the Office cannot register recipes consisting of a set of ingredients and a process for preparing a dish. In contrast, a recipe that creatively explains or depicts how or why to perform a particular activity may be copyrightable. A registration for a recipe may cover the written description or explanation of a process that appears in the work, as well as any photographs or illustrations that are owned by the applicant. However, the registration will not cover the list of ingredients that appear in each recipe, the underlying process for making the dish, or the resulting dish itself. The registration will also not cover the activities described in the work that are procedures, processes, or methods of operation, which are not subject to copyright protection.
And so, you can grab a recipe and be 100% sure that it isn't copyrighted. Then you can add some SEO text around it and some advertisements on the side and you've got yourself a page that you are sure that no legal department will come after you for.
It may be that the 21st century Turing test will be 'whether an AI can tell that content is AI generated". Otherwise it may be much harder to filter the AI-generated content.
THIS!!
Whenever this technology is used in an accuracy-critical setting, it is a recipe for disaster.
These "AI systems" produce the MOST PREDICTED output whenever there is any ambiguity, and this REPLACES the ACTUAL UNEXPECTED value/ITEM. In information system terms, they are literally stripping out content with the highest information value.
I saw this first hand giving a deposition that was supposedly transcribed by an "Artificial Intelligence" system. The output looked beautiful, until I started checking it for errors. Normally an errata sheet has a dozen lines for errors. Mine had pages. And they were substantial and very meaningful. The most obvious site was a specific name that sounded vaguely similar (started with a "J" and "K" sounds) was replaced by "Jack Kennedy". It also replaced "you have" with "I have" and omitted "not" several times, literally reversing the meaning of the statement. There were 85+ errors that I caught, over an order of magnitude more than normal.
These things are basically fine as glorified type-ahead systems where it doesn't matter much and a human is in the loop. But using them in any situation where the results are critical is, at this point, basically fraud. They do not do what the proponents claim.
I guess I'm in the minority of actually appreciating a lot of the background. And it can't just be SEO given that cookbooks these days are hardly just lists of recipes for the most part and people do apparently buy them.
Well to me there's two distinct types of background:
1. Background directly related to the recipe/cooking in general.
2. The writer's personal anecdotes tangentially related to the recipe.
Some cooking blogs have great background (eg. J. Kenji Lopez-Alt's work on Serious Eats) but I would say they're mostly type 1 - information that informs you about the recipe, how they developed it, technique etc. They have type 2 background as well (jokes, what inspired them to make the recipe, snippets of their day-to-day lives) but it's definitely a small proportion of the body of the text. These blogs always have background that's work reading.
What I can't stand is the blogs with reams and reams of text of nothing but personal anecdotes, meandering stories, media references, what their kids are up to etc etc, occasionally returning to talk about something to do with the recipe. I don't have any examples because I now avoid untrusted recipe blogs like the plague, but it becomes very obvious to me when a recipe blog strays from useful background to worthless padding for the sake of copyright and SEO.
Absolutely. There is content around recipes that is good and content that is, well, not. But a lot of people seem to object to anything other than a recipe.
It's because you can copyright everything except the recipe and often a recipe by itself fails SEO in today's world.
Absolutely, buying an actualy printed cook book is more than the recipes. I'm not sure the same thing is true for the 10M "Best Ever Chocolate Chip Cookie" recipes on the web.
I guess if I'm just looking for a recipe the text is easy enough to skip. Often there's even a jump to recipe button. But photos etc. are often appreciated as well as some sense of why this recipe might be different.
It's not just SEO it's also a requirement to get copyright protection
So? Someone else can (and often does) just copy the recipe. So if you don't think the rest of the content has any value, what has been gained by writing it? If I had a cooking site--which I don't--I'd certainly want to do more than just post recipes irrespective of monetary considerations.
Sally's Baking Addiction is the only site you need, FWIW. Trust me on that!
The stories aren't just SEO-pandering. They're copyright-pandering: https://www.chatelaine.com/food/food-blog-recipe-storytellin...
So the interesting thing about these tools is that they don’t link to the sources or cite the sources but instead train on them to generate a new source.
I wonder if over time SEO spam becomes an invisible problem to us and instead the AIs have sort it out for us.
> I wonder if over time SEO spam becomes an invisible problem to us and instead the AIs have sort it out for us
There have been some good Twitter threads about this. Basically, this is the last generation of AI to be trained with inputs that were ~100% human. It probably won't take long until the bulk of the content online is generated by AI, at which point it will just be an AI feedback loop. Any new concept, idea, technology, whatever, that doesn't already have a bunch of content about it will never have a guaranteed fully-human-written corpus to start from.
Once there's a viable OpenAI competitor or two, it's probably only a matter of time until the AIs start an arms race to feed each other bad data. Tweak the model to generate subtly incorrect information, regenerate your training corpus in a way that it feeds into other AIs but ensures you ignore it, and now you're basically all the way back to having a few trusted "information gatekeepers".
Except at present we can also train classifiers that recognise GPT output, so ingressed text should be able to be filtered.
https://huggingface.co/openai-detector/ detects GPT2, but it still detects ChatGPT snippets most of the time, even though the algorithm has been improved and the training set is presumably quite different.
That said, I did just generate a complete lie https://news.ycombinator.com/item?id=33874757 using ChatGPT that scored 99.98% real on the detector, so adversaries can pre-filter too.
Also interesting is that historical corpora (every existing corpus) of data becomes more valuable, because they are untainted.
This will in turn spawn a new research field and industry of automated AI content detection in order to filter out poisoned training data. Also expect to see web browsers incorporate that technology with some sort of rating or color code to flag pages that seem to be AI generated. It's going to be a real arms race.
Similarly, I have found a ton of beginner coding tutorials that contain mountains of useless/unrelated text. I bet a ton of it is SEO, but you gotta wonder if its just generated by something.
Especially now that things like chatGPT seem to write coding tutorials pretty easy (with less bloat than the ones I find on google)
Same! I was trying to figure out async diesel in rust and I couldn’t figure out why the tutorials weren’t working. There were several that had similar code snippets, but different (and sometimes nonsensical) explanations. Couldn’t get anything to compile. I finally found a GitHub repo that they all seemed to be stealing from and managed to figure out the missing parts.
Bad input equals bad output. They've trained these models on poorly written content that's already been an issue itself.
I think the problem you are describing is not only about AI, it is about trusting your sources of information. I can happen with content from humans.
With content from humans, there has to be sufficient motivation to produce a significant quantity of coherent garbage (since it takes time and effort) which means that you can trust by default because intentionally generated garbage is rare unless the topic is one of the niches where there is motivation for it (e.g. politics, history related to politics, and sales). Like, sometimes people do put in exceptional effort to fabricate something as a practical joke, but that is sufficiently rare that you can ignore it in your daily life.
Without AI-generated content, cookie recipes would be "safe" from that, since only people who care about cookies would bother to write up articles about them - but now you suddenly have to mistrust all sources of all information, which is a new thing.
Create content with AI will be easier and faster, but it doesnt mean humans wont generate garbage. That is one of the main problems of the search engines. And as long as you can put ads in your content you can create any garbage and put ads there to make money, as long as the content sounds relevant for a lot of people.
For me the main issue with AI creating content in internet is going to be the echo chamber of that content being used to train new AI models.
https://en.wikipedia.org/wiki/Brandolini%27s_law
The bullshit asymmetry principle puts forth that algorithmic 'bullshit' content is even worse as quantity is a quality all in itself when you're debunking the bullshit. In general the reader will not know if the producer of the bullshit is a real human or a bot. This makes the search engines job even harder as not only do you have the standard human bullshit you have to get rid of, you have an oceans torrent of AI generated bullshit that you have to waste energy on getting rid of.
HN has a common theme of saying that "Dead internet theory is wrong", I personally just think they've not waited long enough and it's becoming more true every day.
It's the mass production that is the problem. A lot of talk into how businesses will still need curators to trim down the content and such misses a vital assumption: that these businesses actually care. Content farms won't trim down their 100 outsourced artists or writers to 10 curators; they will cut the stack completely, and just pipe whatever noise the AI generates straight into the commons. Even if 99.999% of it is complete nonsensical garbage, if they produce fast enough the remaining 0.001% of actually good content can still result in massive profits
> A lot of talk into how businesses will still need curators to trim down the content and such misses a vital assumption: that these businesses actually care.
It's less about if the businesses care and more about if the consumers care. Businesses will respond to whatever consumers are willing to tolerate.
Honestly, it'll probably be a battle around requirements to label AI-generated content so that consumers can make an informed choice about what to trust. But, given the global nature of the internet, that's probably not possible. You probably end up with private/commercial reputation rating firms, and consumers can decide who they want to trust.
If people decide they don't care about the veracity of information or don't want to put in the extra work to ensure they are consuming "true" information they you'll end up with businesses built on auto-generated garbage.
Except for the fact that it does so on an unprecide dented scale allowing small groups of people to do things without necessarily being caught allowing for far more effective ways of control. Even without it, it's hard to argue for the existence of online forums when hackernews is a classic example of why it doesn't work when the majority of the 'intellectuals' have an inflated belief and understanding on topics they have no basic understand on. It's so bad that none of the actual subject matter experts talk here besides ones with financial interests in the products themselves and the experts fearful of retribution. The irony is almost comedic.
Yes - AI moves this to another level of scale but Google’s need to sell ad placements created the environment for that to work. When they can’t even be troubled to de-rank blatant StackExchange/GitHub/Wikipedia scrapers it created a big opportunity for these low-quality content farms limited only by their ability to generate content on every topic.
I have cookbooks, both physical and in digital formats, but it's usually faster to do a web search, especially when I mostly need cooking time and temperature. Perhaps this will motivate me to finally get around the setting up a local search function for my electronic cookbook collection as the web is going to be less and less trustworthy.
For all its flaws I find Youtube is one of the best sources for recipes these days. Especially when you search in the language of the country the dishes are from and use CC auto-translate.
It's ironic that for all our cheering of democratization of creation, we turn back to gatekeeping (video harder to produce than text) in a search for quality.
Although maybe that's more a comment on the inevitable end state of democratization of creation + centralization of search/discovery + monetization of traffic.
Why is it ironic? I think it's more of a "humans are unable to learn from history moment". Romans called it "the mob" because of the common problems that occurred when large groups of undirected people got together and chaos broke loose. Of course the opposite where the authoritarian leader ruled everything also lead to Rome burning.
There is a happier middleground where multiple gates exist to filter out the bullshit, but no said gatekeeper controls the entire market leading to monopoly behavior.
Video is just a better format than text for many recipes, at least for novice cooks. The results often depend on technique as much as ingredients, and it's hard to convey technique through text.
Well-edited video. Cannot state how infuriating it is when the exact piece I'm stuck on is jumped over with a time cut.
Incidentally, this is why I click on the dirtiest garage clip for car how-to's: it's usually just the raw start-to-end process.
Firefox makes it pretty easy to add a custom search engine.
That one could point to your local server instance.
https://developer.mozilla.org/en-US/docs/Web/OpenSearch#auto...
Have a look at
https://www.eatyourbooks.com/
not sure if they do ebooks.
It's a shame, this seems like a really great idea, but I just tried to use it and for a recipe from a book I own it comes up with:
> We’ve helped you locate this recipe but for the full instructions you need to go to its original source.
Which I guess makes sense, how can they verify I own the cookbook, but still very disappointing.
I have never encountered GPs problem where the recipe itself (the thing I was searching for) rather than the surrounding SEO fluff was AI generated trash. If this problem widely proliferates, especially into other domains, curation is going to become absolutely vital.
There's a lot of junk writing that may or may not be authored by humans about health and fitness. Search Google for "how to do more pull-ups" and you'll find thousands of long, meandering, trash articles of generic common sense with stock images and lots of ads on spammy domains.
AI-generated First Aid instructions.
AI-generated alternative cancer treatments.
Hugh.
Can you link one? Sounds very interesting.
Fun fact:
Video games with crafting/cooking such as RPGs are featured on some of these generated SEO sites.
I see parallels here with industrialization and automation in manufacturing and food production. Today, it's self-evident to us as consumers when a product is cheap, low-quality, manufactured garbage from China. In many cases we can choose to spend more and buy a handmade or custom version of the product we want.
In the future we might knowingly consume AI-generated cheap text for some purposes and opt for "the real thing" in other cases. Just like I buy manufactured wood furniture from Target for the spare bedroom, but not for things I want to keep forever.
The interesting thing is that a boom in AI-generated content makes gatekeepers like traditional publishers more relevant after two decades of decline. The narrative of the internet has always been the democratization of content, information, and news. Now, we might find that a stamp of approval has specific value. A publisher can promise that some certain content for medicine or engineering was not generated by AI. Whether fraud also exists is a different question.
Another way I'm thinking about it is with GMO food. GMO food supporters point out that GMOs help us feed more people, but it still makes others uneasy. Maybe there's a similar story with AI content. It makes some content cheaper, but what are the side effects?
Everyone is (rightfully) picking on your GMO example, but I want to address something else:
> Today, it's self-evident to us as consumers when a product is cheap, low-quality, manufactured garbage from China.
Correct.
> In many cases we can choose to spend more and buy a handmade or custom version of the product we want.
Not quite. It's increasingly hard to find a version of a product that's not low-quality garbage - the expensive option is often just the cheap option with extra markup for those who got fooled by marketing, or naively believe companies still care about their brands.
That's the unexpected side effect that, I feel, people still mostly failed to realize: because running a company and manufacturing anything has nontrivial costs, letting the market race to the bottom hollows out the middle. You're left with a bunch of specialty vendors who make quality goods for other businesses or governments, at ridiculous prices, and the low-quality throwaway garbage for everyone else. The "more expensive, reasonable quality" product group disappears - the vendors move either into low-quality crap or too-expensive-for-individuals specialty items (or sometimes both), as the middle can't compete with either end.
I imagine the threat of AI-generated content to be similar: as it completely blows the bottom across creative industry, it will hollow it out. Skilled creators will, when they can, move to the high-end Big Art, where you pay more for the work's provenance than for the enjoyment itself, because they won't be able to afford competing with somewhat worse but much cheaper AI-generated shovel-art.
(Also relevant is that regular people are usually as good at distinguishing between crap and good products as they're at distinguishing between crap and good art.)
As somebody who would ordinarily look for products in this "more expensive, reasonable quality" category, I feel this comment so hard :(
I've actually started building my own furniture from raw wood etc. just because it's impossible to find anything that costs less than $1000 that isn't just cardboard and MDF with a veneer. At least with furniture there's a market for "solid wood". But in so many other industries you get to pick between $3 garbage in a $0.20 box for $5, and $3 garbage in a $5 box for $20.
You might be interested in "Autoprogettazione" by Enzo Mari.
I feel this so much in my life. I used to be a mid price buyer but eventually what I bought ended up in the "expensive, but still crap" category far too many times. Now I just buy crap all the time, it lasts just as long, and at least I know I'm getting what I pay for.
Right. I still try to look for mid-prace quality goods, but in the recent years, I've started to realize it often had bad ROI.
What's extra annoying is that companies are burning brands on this, and as they're transitioning from selling quality goods to peddling cheap crap, they of course don't tell you about it. Instead, you see metal being swapped for plastics, screws for glue, assembly being worse and worse - while their marketing departments double down on highlighting how pretty, modern, quality and smart this years' model is.
For more, see: https://medium.com/social-capital/taylor-swift-ios-and-the-a...
This is an Amazon problem, not a markets-in-general problem. Amazon is currently completely taken over by cheap Chinese manufacturers and drop shippers. But, other sites are not. If you want something high-quality and handmade, go on Etsy.
Well, even so-called experts are not good at distinguishing between crap and good art. For example, Van Gogh and many other famous artists died in poverty.
> Another way I'm thinking about it is with GMO food. GMO food supporters point out that GMOs help us feed more people, but it still makes others uneasy.
a very apt analogy perhaps in a way you didn't intend. it makes people uneasy, there's a natural reaction towards the unnatural, maybe for emotional reasons. it's the same way with GMO crops and AI poems—they will not be able to tell the difference between actual creativity and "artificial artefacts"/"random statistical noise", but they're supposed to have mystical difference. One authentic, the other inauthentic. One that is actually good, and one that merely tricks you into thinking it is good. But don't attempt to scientifically determine if there's any difference... you'll be disappointed.
Australian Cane Toads and Kudzu are why GMOs make me uneasy. People have a poor track record of predicting the consequences of releasing life forms into new environments.
As a human, my reaction may still be emotional, but it's based on evidence.
GMO difference is not mystical. GMO allows for massive quantities of weed killer to enter our environment with not well understood effects. It has been recently linked to the bee collapse for example.
And that's before considering monocultivar risks which are well understood and the underhanded ways gmos are handled by corporations, which are well documented.
I had not there was as much non-mystical opposition to GM crops. A cursory Google search seems to suggest the evidence for GMs contributing to colony collapse disorder is very weak (and the amount of pesticides in the environment might not have much relation to GM crops). But going forward I will keep in mind that it's not as simple as I had imagined it to be.
You’ve illustrated two things, one spot on and one true but in the opposite direction.
100% agreed that AI is like early industrialization in that we don’t even know the messes we’re creating, and wild excess is likely to haunt us.
But GMO foods are the opposite: people feeling “uneasy” is not an indication of harm. All foods are GMO. People are just uncomfortable with the modifications being in a lab rather than over thousands of generations of selective breeding. The side effects of GMOs are the same as side effects of selectively bred food. There is no magic.
Genetic modification in a laboratory is not exactly the same as selective breeding as it can easily bring in a gene from a different species causing unexpected allergic reactions to the corresponding protein. This has caused at least one death of a human. I'm not opposed to all genetic modification, in fact I think it's generally a good thing, but the business has to be carefully regulated. Industry claims that it's totally safe are clearly inaccurate when someone has already been killed by it.
There's no point in having strict rules on food ingredients and labelling if manufacturers are allowed to, in effect, include any chemical whatsoever that can be built biologically: all they have to do is genetically engineer it into wheat (say) and write "wheat" in the ingredients. And the consumer has no idea what they're getting.
You've been misled about GMO causing an allergic reaction death: https://www.snopes.com/fact-check/gmoverdose/.
I suggest you do more research on the benefits and risks of GMOs from more reputable sources. From my understanding, the primary risks of GMOs are less to do with human health and more about environmental risks, such as creating superweeds that can outcompete native plants or negeative effects on soil microbes.
I'm skeptical of the claim that a protein included by GMO was both 1) the cause of a death, and 2) could not have been produced with traditional selective breeding.
Can you source those claims?
I feel like an intelligence going in and messing with genetics is very different from hijacking the process of evolution. In natural evolution, genetic profiles change, not just individual genes.
Most of the dunking on people who hate GMOs always feels like reactionary garbage, basically people desperately trying to feel smarter than the "unenlightened housewives". It always has such a condescending patronizing tone, as if being queasy about multibillion dollar corporations directly meddling in natural processes using extremely new technologies to increase their own profit isn't a terrifying concept. No, science never has had unintended consequences, their feelings are just invalid.
> All foods are GMO
Is there a even a remote chance that say bits of Mammalian dna ends up in a crop via natural selection? The economic issues around GMOs are clear. The biosphere impact is not clear and there are questions: what can happen if we introduce new vectors in ecologies that have evolved over many orders of magnitude longer timelines?
The “unease” comes from the knowledge that in Nature there is always a reaction to an action. And the nature of this natural reaction (which will unfold in time, just like humans picking up agriculture) is not fully understood. It is a reasonable (read: ~substantiated) emotional response, imo.
> Is there a even a remote chance that say bits of Mammalian dna ends up in a crop via natural selection?
Via natural selection alone? Probably not. Through horizontal gene transfer e.g. via viruses? Sure, can't see why not.
> Is there a even a remote chance that say bits of Mammalian dna ends up in a crop via natural selection?
Yes?
Half of your DNA is shared with plants already!
You already live in that world.
I agree with everything you wrote, but I really dislike contributing to the negative spin on GMOs. GMOs are super important for our future and a really amazing technology, they really do not deserve the bad wrap they've gotten from science ignorants and marketing departments. Please don't disparage GMOs :)
It isn't so much the "G" of GMOs, but that they are mono-crops usually licensed by near monopolies like Monsanto. Things are going to be bad when something goes wrong with one these, and there is no replacement and no way out of the licensing fees.
Monsanto is great, because you can immediately know that someone is just regurgitating points when they mention the company. Monsanto hasn't existed for years. And patents run out.
Being concerned about patents is a very weak argument against technology which saves lives around the world (using non patented crops, no less!) and is responsible for allowing more people to eat healthier food.
First, Monsanto and its way of operating very much still exist. Just because it was purchased by another company (which of course resulted in an even greater monopoly), does not make its impact to the world disappear.
Second, everytime this topic comes up, pro-GMOist make it sound like the technology is making some great strides with providing 'healthier food for everyone' with no downside. Why is it that the current model for GMO aims to increase resistance to pesticides instead of simply growing the yield? It probably has nothing to do with the fact that the company that provides you the seeds, also sells the pesticide. And how about the said pesticides tendency to destroy the micro-organisms in the soil, in effect making it harder to grow crops, and ultimately starting a loop for "more GMO, more pesticide, more land, repeat".
Figure a less disruptive business model, and I might be more pro-GMO myself.
> Why is it that the current model for GMO aims to increase resistance to pesticides instead of simply growing the yield? I
It doesn't; there are plenty of traits beyond pesticide resistance that have GM crops targeting them, including yield, drought resistance, nitrogen fixation, etc.
Pesticide resistance is the most established on the market becauae there happened to be particular success with it decades ago, that’s it.
Negative consumer sentiment toward GMOs means that neither the producers nor the growers of GM crops are seeking public attention to the fact that crops are GM, and their products are mostly sold in markets that don’t require GM labelling for the same reason, so the crops already in the public consciousness are all that stays there.
> Pesticide resistance is the most established on the market becauae there happened to be particular success with it decades ago, that’s it.
This might be the case, but still my original bone to pick remains. GMO is not without downside, and people cheering for it without a hint of scepticism reeks ignorance and unwillingness to learn from past mistakes that were made in the name of science.
As you've highlighted, said technique was used for decades, for the detriment of soil health, bees and all kinds of smaller organisms, without it being questioned.
As for your last paragraph, I'm not sure I understand. Are you saying that voicing these 'uneducated' opinions about GMO simply pushes the crops to incognito mode, making them less visible for consumers? Better to see your killer face-to-face than being stabbed to the back? Not sure about that.
from a more generalist viewpoint, we must consider not only the business models, but the mindsets behind them
consider an example from another area. the assembly line and "k12 education". a 'raw material' (but it's actually a child) enters an assembly line, every year they will be passed to the next part of the process, another professional worker will receive the product and will work on it/them for a year.
Also notice how modern elementary education treats the teachers; they far too much like factory workers! low wages, they haven't much of a choice about how to do their jobs.
Now consider the mindsets behind the successful GMO crops (+pesticide combos) that have been the money makers for these corporations.
And consider the mono-crop mentalities and the above mentioned feedback cycle: gmo+pesticide kill the soil leading to more gmo+pesticide; it's a vicious cycle. it's a vicious cycle that keeps making more money! (the assembly line was a great way to really manufacture lots and lots of munition for the war, it is a very effective technique to make stuff that will be sent to get wrecked in a war, in this sense it 'made a killing' as in made lots of 'money')
and again, consider the mindsets involved. why are we educating children like they were cars in a production line?
these corporations are full of people educated like I described, lowering our collective education quality in a longer feedback cycle far too large to be easily noticed; it's a 20-40 year feedback cycle, which has been reducing the quality of the living beings involved.
we have a difficult problem, and no power to do anything about it
>Why is it that the current model for GMO aims to increase resistance to pesticides instead of simply growing the yield?
What? TONS of GMO foods are made for things other than pesticides. Nutritional content, size, yield, taste - in fact one of the biggest uses of GMOs is making the plants need less pesticides! If you think the only reason GMOs exist is to sell more pesticides, you just do not know what you are talking about.
Of course not the only reason, but a reason nonetheless.
"Contrary to often-repeated claims that today’s genetically-engineered crops have, and are reducing pesticide use, the spread of glyphosate-resistant weeds in herbicide-resistant weed management systems has brought about substantial increases in the number and volume of herbicides applied. If new genetically engineered forms of corn and soybeans tolerant of 2,4-D are approved, the volume of 2,4-D sprayed could drive herbicide usage upward by another approximate 50%. The magnitude of increases in herbicide use on herbicide-resistant hectares has dwarfed the reduction in insecticide use on Bt crops over the past 16 years, and will continue to do so for the foreseeable future."[1]
Please bare in mind that I'm not advocating against GMO. I'm advocating against hailing GMO as a win:win to all of society and environment.
[1] https://enveurope.springeropen.com/articles/10.1186/2190-471... "Impacts of genetically engineered crops on pesticide use in the U.S. -- the first sixteen years"
Monsanto was acquired by Bayer, yes, but did their business practices change? This feels like trying to play gotcha when someone says Comcast instead of Xfinity when they were referring to the reputation built under the earlier name.
> Monsanto hasn't existed for years.
Of course it has, Bayer just tried to ditch the bad brand image:
> The closing sets the stage for the 117-year-old agribusiness brand name “Monsanto” to be dropped by Bayer. Monsanto’s efforts to promote genetically modified crops have been the subject of much controversy from anti-GMO activists, and the U.S. company has spent millions of dollars over the years on brand and corporate ad campaigns to improve its overall image.
It's now called Bayer Crop Science Division and does the same thing.
Are you also outraged if someone says Facebook instead of Meta, although the social network is just one of the products from the company called Meta today?
It would be nice if people would differentiate between Facebook (the social network, a specific application) and Meta (a company that owns the aforementioned application and many others).
There is a useful tell here when someone uses the old name for the wrong purpose, it can be a flag that the person is possibly operating under old information. Anyways, if you want to remove all ambiguity and also signal that you know and aren't falling for the rebrand as reputation washing, just mention them both: Meta nee Facebook, Bayer nee Monsanto
> Monsanto hasn't existed for years.
Monsanto was bought by Bayer in 2018. Its brand disappeared, but its products continue.
Although I'm not sure it's great branding when the maker of Roundup is bought by the maker of Zyklon B.
GMOs are terrible which is why they're banned in most European countries.
> bad wrap they've gotten from science ignorants
Science is not about blind trust. How many times have scientists discovered wondrous new things like asbestos, Thalidomide, leaded gasoline, teflon, only to take decades to realize the consequences?
Even if we blindly trust science, there are various other issues like: patenting life, monopolization, reducing genetic diversity, GMO cross-pollination, &c.
> GMOs are terrible
In what way?
> various other issues like: patenting life, monopolization, reducing genetic diversity, GMO cross-pollination
Agree these are all terrible, but nothing there is GMO-specific. That's all either bad agricultural practices like mono-cropping that can be done with any crop, or societal problems related to intellectual property or markets.
>> GMOs are terrible
> In what way?
Because they're the exact equivalent of closed source in software.
There would be means to research, produce and use GMOs in good ways, but the way our economics work, they can't be used without either harming natural ones and/or involving NDAs, lawyers and all sort of things that in some contexts make closed source a nightmare for pretty much everyone except those selling it.
Asbestos is, sadly, completely natural and mined directly from the ground. The other things in your list are obviously not.
GMOs are a very complicated topic, and I can see both sides of the argument having some merit. Proving that new things don't actively do harm (both short- _and_ long-term) should be required before they go to market (or they should have to have very strong warning labels about being untested).
Many of us can agree to disagree on GMOs.
> It makes some content cheaper, but what are the side effects?
"Content" is already maximally cheap: just copy and paste. AI-generated material – at least, with the current genre of GPT-style predictive text algorithms – doesn't produce original content; it just serves to dilute our global knowledge base with semantic white noise and lossy copies of existing knowledge.
Maybe AI content is just a way to launder copyright.
You can only say that if you also say that the creativity of human beings themselves is just a way to launder copyright.
This false equivalency just keeps being made.
Yeah absolutely, acceptable in case of humans and not acceptable in case of GPT.
GPT is not human. It is employed by a human to get around having to benefit other humans with attention and money.
Meanwhile human world is structured around fate, happiness of humans -- such things guide our considerations as to what to consider legal and what not.
There are other differences that make it OK for humans and not GPT (like we can attribute and credit what we learned from, whose ideas we used in work and what inspired us) but they are less significant than above principle
Machines -- at least today -- are extensions of human beings, and pretty democratic, really, compared to history. You can't really talk about limiting machines without also limiting humans. GPT is a tool. Almost anyone can use tools much like it. So what are we trying to protect against?
Yes. Machines including GPT are not the ones doing things, they can't be compared to humans. And humans may desire to do things with machines that should not be considered acceptable because of how they affect human society, and humans may or should be limited (as they already are in all aspects of life that involve other humans).
There's this magic phrase that makes all the difference: at scale.
That seems like saying a steam shovel is bad because it moves dirt at scale. Machines do increase the reach of people, that is exactly what they are for.
People scale. There's billions of us. And we compete.
AIs scale faster. Just one instance can do the work of billions of people, and have its owner profit off it.
How can the owner profit off something that is "free" to make for anyone? Mass spamming is hard to achieve with current day social networks.
Mass spamming is the very raison d'etre for social network companies. It goes by different names though - "sponsored content", "fanpages", "influencers", etc.
The spam did not disappear with people moving away from e-mail. On the contrary, it's just been given legitimacy by the platform owners - who all happen to make money from spam.
"Good artists copy; great artists steal"
-Pablo Picasso
He writeth best who stealeth best, all things both great and small.
For greater minds that wrote them first, from nature stole them all.
-- Totally me.
I like that phrase! I'm probably going to steal it :-)
Now that joke time is over, I'll disclose that it seems to be attributed to one Robert E. D. Cattley, in here: http://www.nytimes.com/1983/12/20/science/homer-s-sea-wine-d...
Well, the uncomfortable truth is that our copyright regime doesn't really make sense. An AI is sort of the equivalent of a junior coder or an art student - it can look at existing work and mash it up and produce something in the same style that's novel (inspired by a prompt - which is like your teacher giving you an assignment). That's copyrightable when it's a human being doing it, and there is no inherent protection for art style, I can make all the Picasso-style artwork I want even if I'm blatantly ripping off his style, and I would own the copyright on the resulting works. Like, if I do a painting in the style of Picasso, should Picasso get the resulting copyright? Why?
And programmers are not without sin either - how many people here run to stackoverflow and copy some answer, or mash it up and produce something similar-but-cleaned-up? That's going to get a lot more powerful in not too many years too... and the thing is, is your little DTO file with blocks of fields and setters and getters really novel and worthy of a government license to cultural exclusivity, or is it a relatively obvious implementation of an API? Which (per Oracle v. Google) are also not really copyrightable...
Humanity hasn't squared the reality of most content being low-value generative trash already (despite being human-generated!) with the reality of a system that automatically awards up to ~150 years of exclusivity (lifetime of the author +75 years). Like, that's the long and short of it. A lot of what we do as humans is just building up a squishy water-filled neural net ("how to make a painting in the style of Picasso") and running random prompts and goal-seeking through it and cleaning up the generative output. Now AIs have gotten to the level of "average college student" and it turns out that's not actually all that difficult or interesting anymore, but we're still working in this model where that's supposed to be worth ~150 years of cultural exclusivity and protection automatically.
If you only get copyright on the things that are truly novel and have no previous creative basis or cultural/stylistic heritage... that's a pretty big change to the copyright system for humans too! Especially in light of the fact that there's only a few ways to implement most configurations/functions... does Spring own all the copyright to your config classes because they're basically doing the same thing as the spring demo projects? hard to see much novelty in that sort of thing pretty much ever, so those probably should not be copyrightable at all under a "totally novel" requirement, but if they do surely Spring owns the copyright.
As mentioned in a sibling comment, the "at scale" bit is surely relevant in a practical sense, but, it doesn't change the underlying-principles basis. This is a situation where "at scale" has just thrown the underlying problem into stark relief. A 2-lifetime (life of author +75 years) governmental grant of cultural exclusivity doesn't really make sense in a world where humans are constantly and trivially mashing up each others' ideas even within a single lifetime, it just doesn't fit the way we exchange ideas in general. And now you have the college-student-bot that can generate a million shitty DTO classes or artworks-in-the-style per day that makes that plain. But ultimately it's just doing the same thing as an art student but faster... if you put an art student in a Mechanical Turk box and made them draw whatever you demanded, would they not own the copyright? And would it be a problem if India had an art school that set up an "industrial art" process and employed a million students in boxes drawing whatever you said to draw? It would probably be problematic for DeviantArt commissioners, but would it violate the principle of copyright?
We just haven't managed to square that reality where most human works are fairly trivial derivatives of other works (your deviantart commissions really don't mash up any similar works or styles that came before? really?) and yet worthy of 150 years of license to cultural exclusivity. And the college-student-bot is blowing that model up. People still need to eat, of course, but that's an orthogonal problem to the societal framework we've set up not really making sense. We can solve the copyright problem and not the eating problem (as we have many times before - buggy whip manufacturers adapted too), or we can solve the eating problem and not the copyright problem, or solve both or neither. People not being able to eat and shelter themselves is a capitalism problem, not a GPT problem, and we will probably have to address the idea that everybody needs to work to survive as machines continue to displace the last strongholds of human labor (as I'd argue creative work has become). We should not be restricting our ideas on collaboration and cultural generation just because it produces inconvenient outcomes for the current copyright regime and capitalistic model, the model needs to bend to fit humans and not the other way around.
This isn't the only place the inherent contradictions and problems of copyright come up either. The idea that a nighttime photograph of the Paris skyline could be copyrighted by someone else other than the photographer who created it is pretty janky too. Is a photographer not adding significant creative value with composition/etc? Literally just having that one element makes my photo derivative? Maybe that's the analogy to GPT/stable-diffusion I guess - but the thing is, it still works the same with a human as with a robot, an AI-generated Paris skyline still would be copyrighted by the architect too. And if the argument is that the code owner or original artist owns the style, then, Pablo Picasso owns the copyright to all my paintings too, just like the architect of the Eiffel Tower owns the copyright to my photographs of the Paris nighttime skyline. And Spring (or Oracle!) owns the copyright to a great deal of your Java code. So that probably is not going to work out great for you either.
Are answers to Stack Overflow not supposed to be copy pasted, just right away? It seems hard to believe, i thought that was the whole purpose of the site!
Well, copyright suffers from the same problem communism suffers. For communism to work, everyone should be on board. For copyright and patents to work as expected, every country on earth, every town and every city's laws should be almost the same regarding to that. As soon as even just one municipality anywhere on the planet, is free of patent laws, the exact same moment a factory will pop up and produce an expensive patented pharmaceutical product which it will sell for half the price, or 1/10 of the price.
Capitalism on the other hand, works even almost everyone else doesn't like it, and 2 people agree on a peaceful exchange of commodities, following a price the market sets, or it is discovered right away.
As a rule of thumb, anything that requires everyone to implement rules and follow them, for it to work, will fail sooner than later. When a product in some part of the world is selling 100x of the normal price because of some patent, counter incentives are detonated in some other part to produce it and sell it for 50x the price. This huge profit margin creates a chain reaction of other economic actors producing it as well, and selling it for 25x the price.
Additionaly the eating problem can be solved by capitalism, not communism. Exchange of art for electronic money, a marketplace of information is what we need. Bitcoin (not BTC) will play an instrumental role in that.
A.I generated images of picasso, are awesome. I created many of them, one series of them are "Darth Vader riding a red tricycle, in the style of picasso". They are so good you're gonna fall of the chair.
That's certainly what my impoverished artist friends have taken away from it.
Generative models do have a contribution - they adapt what is on the internet to a specific task or request. In the case of Copilot, it will use your variable names in the generated code. And not everything generated by a model should be saved. Some are just for one time use, for fun, therapy, brainstorming, etc.
We already do as you're saying with "content". The throwaway paperback novels are already predictable cheap trash (I still read them, not judging, but they're providing a different type of stimulation for which that bar is lower than something that makes you think). These are already written in a formulaic way that is equivalent to being computer generated, it just took a bit more human effort until now. Same for TV programming, art, I assume video games, etc...
> GMO food supporters point out that GMOs help us feed more people
That seems like an odd thing to point out to me.
More people is not an obviously positive thing for us or the planet. And we have enough food and wealth for everyone as it is. If feeding more people were the priority, it could be addressed in other ways. I think the primary motive behind GMO is increased control and profit. I guess I shouldn't be surprised that there's a whitewashed motive as well.
This is overly simplistic and conspiratory. Yes, Monsanto is evil, but that doesn't mean everyone involved in GMOs is, or that's the only motivation. Look up the argument over golden rice.
It's also ridiculous to just hand wave away crop productivity improvements with "but we already have enough food." We aren't going to revolutionize global food distribution any time soon, but we can do things that have concrete impact right now. We're also losing land to agriculture far too fast, particularly in the amazon. We need to be decreasing the amount of land used by agriculture, and GMOs are a very powerful tool in that interest.
GMOs need to be regulated, and I think the IP regime that Monsanto is protected by should be struct down (not that I expect that any time soon). But please don't wave away the entire discussion with strawman arguments.
> But please don't wave away the entire discussion with strawman arguments.
What strawman argument? I was responding specifically to the point I quoted that feeding more people is important. And I made a couple of points specifically against that position. So where's the straw?
That's a great parallel, especially since it supposes a possibility of a good(or at least acceptable) ending to all this, rather than just spiraling into chaos.
I only fear that there won't be enough profit motive for such gatekeeping/curation, which would only happen if very few people were willing to spend more money for human generated content. I can see this potentially not happening, either because the tech advances to quickly for people to even tell the difference, or people do realize but don't care because the AI learns to feed them exactly what they want(exactly what's happening with a lot of BS "news" already). Or maybe a decent group of people do see the value in real content, and pay for it, but the majority still remains oblivious or indifferent, and the effect it has on this majority is still enough to influence the direction of the world negatively enough that even those groups who avoid it will be forced to accept the consequences of living in a world created by AI and the majority of other people
"Makes me uneasy" stands for "makes me want to be careful", and imo this is an essential motif in engineering practice. The key is to remind ourselves that food is engineering, and with inputs and outputs which could have vast ramifications for human health and safety. GMO should be regulated and systematically evaluated by an array of public oversight systems. The concern is that it requires PhD levels of knowledge and scientific mindedness to understand and evaluate GMO in a pragmatic, effective way (that doesn't dive into religious pseudoscience---I'm looking at you DNA-free bottled water). An even huger problem is that understanding this issue in a broad sense requires renaissance person levels of capabilities and personal sensitivity. (Does it matter that food is complex, interesting, driving unique sensory experiences? Let's make it sweet baby, that hits in the taste tests.)
The same is true, perhaps even more so, for our information diet. It defines our reality.
another food analogy would be how farmers started grinding up dead animal carcasses and feeding the results back to live animals (i.e. making cannibals out of vegetarian ruminants), which resulted in an outbreak of prion diseases like Mad Cow / CJ.
The food analogy would probably be more along the lines of the mass availability of foods fashioned from refined ingredients designed for long shelf lives, i.e. "processed foods".
Produced at scale, durable, easily distributed, enticing flavor, if it's actually any good for eating is far down the list of priorities when devising these things, as its effects are noticed far after purchase.
> Another way I'm thinking about it is with GMO food. GMO food supporters point out that GMOs help us feed more people, but it still makes others uneasy. Maybe there's a similar story with AI content. It makes some content cheaper, but what are the side effects?
The analogy to GMOs seems more connected to the self-replicating nature than to any potential health side effects.
I've thought about spending $8 towards a local paper subscription, inspired by Twitter's paid version.
GMO's are a completely different thing though. A crop which who's gene's were hand picked by a human to be more drought resistant instead of naturally are completely different conversation and different morality. Vaccines make people uneasy, just like GMO's, but that doesn't mean that unease particularly equivalent to AI or the same moral issues.
AI already is drowning out human made content on websites for creatives. Aided in no small part with their curator's malicious insistence to not label their posts as AI generated. It's only going to get worse as AI art becomes better.
Upload your fake text and images anywhere. Upload it everywhere. Upload it as yourself. Upload it on behest of your willing friends. Corrupt your face in dozens of ways, then tag each as yourself. When everything is garbage, shadow profiles will mean nothing, social credit scores will mean nothing, analytics will mean nothing. Centralization can be turned on its head - the watering hole will be revealed to be the dangerous cesspit it is. Create art until what can be monetized has no value. Create news that never happened, scoops that are only a distant fiction, until nothing on the internet can even be meaningfully reported on. The corrosive powers of mass memetics for the first time can be rendered entirely impotent.
While I honestly do want to support this approach because unlike the alternative it might (just "might", though) work, I regretfully must also admit that the huge problem with this is collateral damage. There are millions of humans out there that are either highly susceptible to or are already caught into believing all sorts of nonsense, getting scammed in all forms, costing them money, time, well-being and even lives. The issue with fake flood is that until the saturation/breaking point (when the understanding that existing trust system is fatally broken becomes truly mainstream) it's going to make this situation worse.
What's extremely frustrating is that the only alternative I've ever seen proposed are forms of a never-ending moderation arms race, some variant of a "war on fakes". Which is even scarier in the long run, because while it mitigates the damages here and now (good), it would never solve the underlying problem, and only further cement some parts of it (enforced trust invites potential abuse).
And as usual, humanity is currently stuck between two incredibly shitty options (traditionally going through a path of least resistance, no matter what could be at the end of it - because that's how large systems work), hopefully still searching for a magical third silver bullet.
I agree with your point, but also think this trajectory is kind of inevitable in a way. As we can already see, a LOT of people are living deep in a world of BS news stories and made up facts, to the point where they're basically in a different reality.
Ideally, we'd find a way to go backwards from where we are now, maybe future generations will grow up with this flood of false info and learn to navigate it, but I think we reached a point where tech is developing so fast, and the world is changing so fast, that there were always be a large number of people who can't "keep up".
Given that, this may be one of the few scenarios where I'm in favor of a kind of "accelerationism" - increase the problem to a breaking point as soon as possible so that we can deal with the fallout and recover from it now, rather than dealing with this horrible state of things for decades and decades as it slowly gets worse and worse, until we eventually reach a breaking point anyway and likely have an even worse fallout to recover from.
I appreciate your comment. Thinking of it - you are probably right. It is a matter of time, as long as we don't accidentally take a wrong turn toward some dystopia. Won't happen in my lifetime, but future generations raised observing this state of discord would naturally learn how to deal with it. And us old farts with our susceptibility for delusion (because we, en masse, have only encountered it past our youth, when learning and adapting is harder) will be history.
> There are millions of humans out there that are either highly susceptible to or are already caught into believing all sorts of nonsense, getting scammed in all forms, costing them money, time, well-being and even lives. The issue with fake flood is that until the saturation/breaking point (when the understanding that existing trust system is fatally broken becomes truly mainstream) it's going to make this situation worse.
The people who are willing to engage in charlatanism and mass manipulation are already enabled by this tooling and will use AI as a force multiplier whether we use it to jam the signal or not, and the results will be far, far worse for victims because these people will actually have directed, dangerous goals and agendas to push them toward rather than having them flail in a contradictory trash pile.
It’s only a problem that large numbers are easily duped no matter how much education we give them when it’s also coupled with no-questions-asked universal suffrage.
It depends in part on the quality of what is passed off as education. After twelve years of US public education in the 1970’s and 80’s, not once did critical thinking tools, types and sources of bias, and default-mode skepticism come up. I’d rather work on improving that, rather than making it even harder for citizens to vote.
And the #1 way to improve educational outcomes is to figure out how to attract better candidates to be elementary teachers, NOT curriculum micromanagement (whether from elected school boards or directly from parents)
If it leads to total chaos (which I think it's going to) I could easily see governments trying to enact the following:
- A public blockchain or database for ID purposes, with every ID traceable back to a real human. Legislation created that mandates all websites implementing user profiles for any social purpose to require an official ID on signup and every user must be identifiable on the platform by their real name.
- Access to AI only under strict restrictions. Official apps you're allowed to use with the government banning all others. Big Tech will happily comply with the censoring because they are the designated official AI app providers.
- Photorealistic AI and Video banned entirely because the potential to incite violence through fake videos is too high. Imagine Pizzagate or Jan 6th but someone made a Blair Witch style video showing Biden and Pelosi killing a baby as members of a secret cult. Or someone made a video of one of their enemies committing animal abuse and sending it to everyone in the town.
- Exams will make up the entirety of your grade in most educational environments apart from those where AI cannot be used for creating the coursework.
- Anyone caught using non-official AI or abusing AI will be subject to harsh prison time akin to hacking state secrets.
Of course, the government and its agencies will have access to all of this technology for their own purposes so they will be able to create whatever they want to control you, your thoughts and society's perception to be whatever they want it to be. As this isn't really preferable to the complete chaos it's trying to control, more and more people will try to disconnect from the internet as much as possible. The IRL economy will grow and there will be a resurgence in analogue forms of media for counter culture types. There may even be a resurgence of interest in blue collar trade jobs if white collar jobs are decimated and wages plummet.
We are on the precipice of 1984.
This reminds me of the great novel Fiasco by Stanislaw Łem [1].
The civilization described in the novel fills the entire radio spectrum with noise, to make efficient communication impossible (and possibly to also allow highly sophisticated noise-like encrypted communication be undetectable).
Their society is pretty dystopian though.
[1]: https://en.wikipedia.org/wiki/Fiasco_(novel)
Also the book _The Cyberiad_ by Lem is now more relevant than ever. It is a set of short stories, mostly about messing with generative AI, AI assistants, etc.
We didn't need the help of AI to do this to poetry already. It turns out that access to a text editor was more than sufficient.
I was going to say this is a great idea but totally unfeasible due to the amount of cooperation required, enough people simply won't do it, but parts of it are kind of happening by default. e.g. with BS news stories and whatnot. Also I suppose a lot of it could be automated - fighting fire with fire in a way. I'm sure that would lead to a cat-and-mouse game of creating code for detecting and ignoring intentionally obfuscating content, then the other side coding their way around those detection systems, and then back and forth like that forever, similar to the pattern of: finding exploit -> patching exploit -> finding new exploit -> patching new exploit -> etc.
I'd be careful. By doing this you can use the date these AIs became readily available as a tool for bisecting between "legitimate profiles" before the year X and "potentially fake" profiles from after the year X, which can then be used to very effectively train an AI to tell the difference...
Sure, it also mean limiting the dataset of our children (i.e. the bane of ML), it means bit-rot for existing datasets.
> Create art until what can be monetized has no value.
A1.
Now you see why tribes form by evolution just as mutation does.
I've been known to start ranting when I'm searching on some topic that attracts SEO garbage (e.g., Python), and realize I'm in the nth different SEO garbage article search hit.
I wonder whether a winning solution to the coming massively-parallel "AI" megaspew will emerge, how it will work, and whether Google will be the ones to do it.
Or will the bulk of consumers overwhelmingly submit, and accept it as normal, much like we already do with huge regressions in the quality of interactions and thinking?
Here’s a solution:
Go ask ChatGPT your question about python.
It’s spew is probably better than the SEO spew.
I feel like species traitor taking the side of the AI, but I think this is probably a decent way of answering a lot of questions based on a factual and rational basis that have been answered multiple times. A lot of hoopla is made over the fact you can trick it with a false premise into giving a false answer (I’d note the false premise makes all answers true), but if it can simulate a Linux box reasonably well, it can answer your questions in python module imports better than sifting through page rank collections of SEO crap.
Edit: I also think this doesn’t undermine the value of stack overflow. Bots answering there probably does. But stack overflow has always struggled with simple redundant questions and trying to curate them away in favor of new and interesting questions, and promoting novel and well explained answers. ChatGPT probably won’t do that for you. But it can load shed the redundant stuff highly effectively. And, over time, it’ll get more nuanced as more nuanced questions and answers are incorporated. But the “I need human help” button is still there and thank goodness. Maybe the load shedding will enhance the experience on SO for everyone?
The solution will be to chain Google with chatGPT. A system that allows chatGPT to perform Google searches and use the retrieved documents as reference when formulating the response. This means we don't need to actually see Google or the website, but still have grounded responses with references.
Instead of Google it could also be a big dump of text, like 1TB of well curated web text, so with local search you get more privacy and speed. And instead of chatGPT we will use "chatStability", a LM running on the local machine, in privacy. This could be the end of ads and the creation of a new private creative space for people.
<rant>I think Google is in big trouble and that explains why they are second when it comes to LLMs - this line of development will make it easier to escape their ads and tracking. There's no profit in it for them.
Even though the Transformer was invented at Google 5 years ago, from all the authors only one still works there, most of them have left to implement their own visions, a bunch of startups. Why have they left Google if they wanted to innovate? Because they could not do it inside. Google got to protect the current revenue streams first.</>
https://analyticsindiamag.com/how-the-authors-behind-the-tra....
Going off your point, even if we aren't quite there yet, there is no reason to suppose that AI won't eventually be massively better at basically ALL things than humans - that's certain the direction we're headed, and very quickly too.
This is just the very beginning of the problem. It's time for people to start thinking about how to live in a world where they are "obsolete". All jobs, or, being conservative, at least the vast, vast majority will eventually be replaced by AI. AI will eventually be able to create art that is more appealing to humans than human-created art. I think there could eventually even be AI "people", who's company many people will prefer to other actual humans, as they will be designed/trained to be as perfect as possible for that task. I hope that most people will still see more value in genuine human interaction, as any person today probably would, but as tech evolves and we get used to it, let it into our lives more, let it control more of our lives and make more of our decisions, then it advances more and we get used to it more, etc. The idea of human connection and the separation between human life and AI "life" might not be as apparent to people as it is to us, and they may allow AI and technology to replace every facet of human existence
I actually strongly disagree here with the conclusion you make. I think these are going to be tools that enhance the human mind. It’ll enable the average person to be exceptional by using the AI as guidance. It’ll enable the brilliant to exploit the AIs in novel and clever ways that were not possible before. The humans place is in the use of a tool, the tool doesn’t replace the human.
The challenge will be instead is there enough useful work to keep everyone paid in a post scarcity world? The advent of the useful AI will probably necessitate some very very serious thought about how we allocate and distribute capital.
But I don’t believe artists will be replaced by an AI any more than they were by the camera. Or that streaming will kill music. Etc.
I'm not too attached to my conclusion, in fact I hope it's not true, and have also thought about what you said. But I am convinced that, eventually, humans will be capable of making autonomous AI advanced enough to "replace" them, and I am NOT convinced that humans will choose not to - especially given the fact that over enough time people will slowly allow AI to control more and more of their lives and the world. Then the next generation of people will grow up accustomed to this level of invasiveness and think it normal, and trade off more of their freedom to AI in exchange for more convenience and comfort.
As for the concern about whether there will be enough useful work to keep everyone paid. Eventually the answer is definitely no in my opinion, just a matter of how far out that is, but I don't think whether there will be enough work is a meaningful question in that world. If AI is good enough to replace human work then the work is still being done - in fact MORE work is probably being done, and therefore more goods/resources(post-scarcity as you said). It's a question of whether humans can distribute those resources fairly - this question and problem remains the same whether people need to work or not. We already have more than enough resources to keep everyone in the world fed and comfortable, assuming we don't destroy the planet this will only be more true when the AI work force comes into play.
It's easy to assume that in such a world there will be enough resources for everyone to live very comfortably while the higher class still has extremely excessive control over resources, and as such it's not likely that greed(the main obstacle to a fair outcome) would have to come into play, as the rich and power-hungry can have everything they want without having to allow poor people to starve to death.
Unfortunately I'm not convinced that assumption is valid either though, because of the fact that the psychological factor driving the greed of the ultra-rich isn't the desire for material possessions and wealth in itself, but to have "more" - more stuff, more capital, more power, than others. They don't just intrinsically love 100 million dollar yachts so much that they choose to buy 3 of them instead of, say, saving the lives of millions of starving children. What they love is the inflation of their ego and the feeling of power and superiority. If middle-class person suddenly had 100 million dollar yachts those people wouldn't be satisfied with their own anymore. Because of this, I think the ultra-rich and ultra-powerful, who of course will be the ones in power and who will have the ability to influence how resources are distributed in a post-scarcity world, will be motivated to keep the lower classes "lower", in order to maintain their ego and satisfy their power craving(though they will of course justify it in less crude ways).
To make my point more simply: If Jeff Bezos could snap his fingers right now and magically make every single person on earth exactly as rich as he is, give them all the same resources and material possessions, at no cost to himself, I am quite convinced he would not do it. This is a simpler version of the exact same decisions those in power will have to make over the next centuries - and in their case it will probably be easier to justify to themselves as it won't be so black and white as denying fortune to billions of people at no cost: that will be exactly what they're doing, but over the course of many small decisions that is each justifiable in it's own way, such that they never have to realize that that is exactly what they're doing
I almost decided to limit my searches to the search engines of the authoritative sites. Examples in the case of Python: the Python language, the Django framework, Stackoverflow (until it will surrender to AI posts then we see what happens.) I'll end up creating a home page with search boxes to those sites. Very '90s
Ironically, the 90s solution (human-curated link collections) to Internet-wide searches seems the easiest way out.
It's relatively easy for a human to tell the difference between AI copy (as pollutes the web) and actual content.
It's also strange that Google et al. haven't built human-in-the-loop flagging of spam content into their search UX ("Is this site low quality?"). They could get around flag spam via reputation, given that Google knows identity for most of its users (because they're logged in or via IP across their properties).
Side note: In cursory research on current state, I came across the Chinese phrase "human flesh search engine" [0], which I wonder if it sounds as cyberpunk in the original Chinese.
[0] https://en.m.wikipedia.org/wiki/Human_flesh_search_engine
> It's relatively easy for a human to tell the difference between AI copy (as pollutes the web) and actual content.
It is now. It definitely won't be when gpt gets popular.
It will be: GPT output is usually either garbage, repetitive, very wrong, subtly wrong, or inconsistent in writing style in a way humans aren't. (It sort of starts trying to say something different, in the "same style" as it started with, then switches style later.)
When humans really can't tell the difference, well… https://xkcd.com/810/ seems appropriate.
The GPT output I've been making using openAI's chatpot is indistinguishable from what the bottom 70% of commentators put out.
But an environment glutted with that content is also worthless. I read for the top 10% that has genuinely novel thoughts.
In most cases, judging if something was created by GPT takes quite a long while. It's not a search result you can easily dismiss.
https://i.imgur.com/kBGRUqL.jpg
Without revealing the origin, the latest models tested in private betas solve many of the points you mentioned.
This is why I'm not leaking all my discriminating heuristics. https://en.wikipedia.org/wiki/Goodhart%27s_law strikes again.
At some point you also run up against the virus vs immune system endgame: it's evolutionarily inefficient to optimally outwit an adversarial system.
Usually there exists a local maximum where you obtain most of the value with less-than-full effort.
Sadly, the centralization of search directly cuts against that. I.e. outwitting Google search = $$$$ vs outwitting 1-or-4 equally-used search engines = $. :(
> It's relatively easy for a human to tell the difference between AI copy (as pollutes the web) and actual content.
No:
https://en.wikipedia.org/wiki/Sokal_affair
The Sokal affair says more about the dynamics of academic publishing than it does about humans' ability to key to nuances.
And "as pollutes the web" -> we're not talking about state of the art.
Your post led me to an interesting little quick experiment.
So in 2020 I self-taught Python during Advent of Code. I remember remarking that official python.org results seldom made it to the top of Google searches. I was used to Java and Julia searches taking me right to the official sites.
Anyways, so an experiment just search for "[language] [feature]". I ended up with W3Schools as my top result for "Java ArrayList", but Oracle JDK8 docs for "Java Socket". "Python Socket" takes me to language reference but "Golang Socket" does not.
Maybe there's a trend to be discovered.
You could also put something like searx [1] in front to search all at once (or at least provide unified interface for all).
[1] https://searx.github.io/searx/
The solution is to create datasets that contain data and aesthetic judgment metadata from reputable sources together, and train models to perform aesthetic judgment. This will both filter out spam/low quality content, and provide a conditioning tool for generative models to improve their output. Even better, the arms race this will kick off will create a virtuous cycle that will push progress in AI.
The only problem with aesthetic judgment models is that (much like human aesthetic judges) it will sometimes give poor scores to things that are dissimilar to the data it was trained on, even though many people might find those things aesthetically appealing.
>from reputable sources
What does this even mean. Reputable sources tends to fail the 'chinese room' experiment because you can never tell if your source is reputable or just faking being reputable (or later becomes corrupted).
Well, if we were talking about food, I'd say Gordon Ramsay, David Chang, Anthony Bourdain or The New York Times could be considered reputable, while a Yelp reviewer with a handful of reviews could be considered disreputable.
Ultimately you can boil it down to: Trust sources when they make statements that are later observed by me to be true, or are trusted by other sources that I trust. The negative feedback loop boils down to: If a source made a statement that I later found to be untrue, or extended trust to an untrustworthy source, reduce that source's trust.
The issue here is you have pre-AI reputation sources, the problem is for post-AI content generation how are you supposed to find this content in a nearly infinite ocean of 'semi-garbage'. Anthony is not making new content, and one day the other people will expire. In the meantime a million 'semi-trustable' AI sources of content with varying reach depending on how they've been promoted will take over those markets.
There are any number of particular problems here that we already know do not mesh well with how humans think. You'd start your AI source 'true', build up a following, and then slowly them into the Q-anon pit of insanity. Most people will follow your truth and fight anything that questions it.
Search engines like Google are probably a dying technology. The next disruptive innovation in that space will be "answer engines" that use GPT like technology to dynamically generate specific answers to questions rather than linking users to third-party sites. This will allow for controlling the entire user experience and serving ads embedded in the generated content.
As https://www.wolframalpha.com/
I don't think there will be ads. We'll be able to run a local chatBot just like we run SD.
SD is only 4 GB in size, you can run it on one 8-10 GB GPU, GPT-3 is around 350 GB so around 100x more, 99% of humanity can't run it locally currently even if they wanted.
There is FLAN-T5 and hopefully there will come open models that work on a regular computer.
People really love to make predictions about technologies way too early. It’s been a year or two, tops, since this stuff has gone mainstream. I very much doubt that the consumer ecosystem will remain the same while content undergoes an AI-powered paradigm shift. We will most likely see a growth of curated sites that help weed out the nonsense, as has been typical for most new developments.
And on that note, I think the framing here is just wrong from the start. These new tools are awesome if you’re a creator. Complaining about the consumer-facing side of this new tech is a bit like complaining that cheaper video cameras will lead to junk films everywhere. Yeah, that happened, but who cares? It also allowed creative people to make stuff without needing a huge budget.
Yeah, that happened, but who cares? It also allowed creative people to make stuff without needing a huge budget
Is it not too early to make predictions?
Filmmaking devices have gotten cheaper consistently over the last ~50 years. I don’t know about you, but I think some pretty good movies have come out since 1970, especially by directors working on very low budgets.
> I don’t know about you, but I think some pretty good movies have come out since 1970, especially by directors working on very low budgets.
On the whole, I think the average quality of cinematography in theater or wide-streaming releases has decreased.
Which isn't disagreement with your point, as I think it says more about audience tastes and gatekeeping filters than technology.
When film equipment was expensive and the bare minimum for creating a film was high, studios had a much tighter filter on who they'd fund to create a film. Consequently, the level of craft was higher.
What needs to be said here is that average quality is more or less irrelevant. If the amount of high quality movies increases (it did) and the discoverability doesn't suffer (it didn't too much), then that's a plus.
I'd argue discoverability is a currently unsolved problem. Or maybe "uncared about" (optimizing engagement >> enjoyment).
At least when I'm getting far better recommendations from HN than any front-page algorithm I've seen.
The thing that has tanked the quality of theatrical films on average isn't improved technology, it's the increasing commodification of art, risk aversion of business and the modern reliance on data to drive business decisions. That's why we have basically nothing but sequels, reboots and formulaic drivel coming out of the major studios.
And also hindsight filters. No one remembers the crap movies from 1982. We remember the best-of-80s.
So we're comparing {recent movies} to {decades of best movies}.
“It’s too early to make predictions. Here’s my prediction”
^^^ I think this is what the response meant. I noticed it too, you castigated folks for making predictions then led into your own :-) a real AI wouldn’t do that!
I don't think the making of the original blade runner involved much in the way of modern AI. I'm honestly not sure what you're trying to say.
An Avid nonlinear video editing station used to cost $100K. Nowadays you can do the same with software costing $300 on the computer you already have. You can get a mirrorless video camera that blows away the Sony CineAlta ones George Lucas used to shoot the Star Wars prequels for under a grand. This has removed a huge chunk of production costs and make indie film-making much more viable. The only limits are your imagination and the salaries of the actors and camera crew.
AI-generated animation is already being used by industry giants like Toei, and will likely be the first application to hit the screens.
AI creation tools make it easier to make stuff. This process will result in a lot of junk, but it will also result in some super creative people making art they otherwise couldn’t.
The same process happened with filmmaking. Fifty or sixty years ago, it was too expensive for anyone other than large corporations.
You could even say the same thing for writing itself; a thousand years ago, paper was too expensive for the average person and most people couldn’t afford to buy books and become literate. Today, writing paper is functionally free.
And it's not just creation of art from "scratch", I bet we will soon see AI being able to take painted animation frame, sketch of next and extrapolate next frame from it, and making whole process so much cheaper
Your quote isn’t a prediction, but a direct observation of what occurred.
How about this:
People really love to make predictions about technologies way too early. It’s been a year or two, tops, since this stuff has gone mainstream.
Prediction: I very much doubt that the consumer ecosystem will remain the same while content undergoes an AI-powered paradigm shift. We will most likely see a growth of curated sites that help weed out the nonsense, as has been typical for most new developments.
You are drawing a parallel implying that in the future one will behave like the other - close enough.
I we have already seen this play out in music though.
Computers let anyone record music when it use to cost thousands of dollars to record music.
The results have been a disaster outside the top 1% of music makers. Such a dramatic change that anyone under 30 doesn't even know what has been lost at this point. Music as a whole is laughably less creative as "popular" / pop music established total dominance. The money all flows upward that use to be much more dispersed.
I used to feel the same way but I eventually came to realise that there’s tons of good music being created, it’s the social aspect of music that has been destroyed.
Individual algorithm recommendations have subsumed sub cultures. Music used to be part of both your individual and group identity, it would influence what your wore, what you read, what you thought, who you hanged out with and what bars you visited. Technology has eroded the music press and sky high rents and fitness culture (not as many people drinking) means lots of gig venues and bars have closed down. These were the glue that built the subcultures up. You used to have the mainstream plus a few sub cultures that would evolve each decade e.g mods, rockers, hippies, metal heads, punks, new wave, hair metal, brit pop, emos, indie rockers etc. All of these ended up getting absorbed into the long tail so you now have the main stream and then everything else, with nothing in the everything else category really able to attract enough people to it in order to form era defining subculture like the days of old.
Combined with the sheer amount of music being created, all of this makes it harder to find music you actually want to hear. Your friends are all listening to different stuff so you don’t get many good in person recommendations anymore and what’s left of the music media are struggling to stay afloat and resorting to all kinds of stuff like NME doing movie reviews. The algorithms are hit and miss and search engines are getting worse and worse. So you become more and more at the mercy of chance, hoping that somewhere you stumble upon a review or a blog post, a subreddit or a song that somehow leads you to some good new music. But the reward to effort ratio often makes it harder to justify the time investment. And however good the music is, it’s not as enjoyable when you don’t have a group of people to share it with.
Coincidentally, just came across this which is a nice take:
https://www.theguardian.com/music/2022/dec/05/has-spotify-re...
I don't think that's true at all. There are a ton of niche music makers and a ton of ways to find them...infinitely more than there were a few decades ago. You just have to go looking for them. Which frankly isn't even that difficult with YouTube and SoundCloud. Maybe the musicians aren't making millions, but the creativity is definitely there.
Sorry but no, this is completely the wrong take. Popular music is less diverse today for the same reason that half the movies released now are Marvel - art is more commoditized, and businesses are more data driven, with the shift towards more public companies also playing a role, as they can't take as many risks as private companies.
What cheap music production tools have done is allow niche subcultures to create music that actually sounds good. Punk, metal and early hip hop all grew from people sharing rare tapes that were poorly produced and sounded like shit, but were a breath of creative fresh air. Now people's unusual creative divergences are stream-able and have production quality close to that of stuff on major labels.
This seems like a failure in statistics.
Lets say in 1 year 10 songs are created and 2 of them are 'creative'. You'd think that 20% of music is creative.
Now lets say we have the production explosion and now in 1 year 100 songs are created and 4 of them are creative. You would think creativity has fallen off a cliff when it has really doubled.
In addition trying to compare with the previous payola ridden system were winners and losers systematically chosen by a wealthy cabal seems rather asinine. It only worked because there was a limited number of radio stations mostly. Even if production costs stayed high, distribution costs dropping would have changed the model dramatically anyway.
> These new tools are awesome if you’re a creator.
you're typing "generate me an article about x" into gpt-3. who's the creator here?
Your are.
Are you the author of the binary your compiler made? Sure you are. Of think of using blender geometry nodes to generate and render pictures of architecture. Nobody would think that traditional computer generated images are not made by humans.
The is no intelligence in gpt-3. It's just called "AI" for marketing reasons. It's an data driven algorithm.
I’d argue that the creator went from being an author to being an editor, and that is fine.
Personally, I am enjoying chatgpt and copilot. They both have saved me a lot of time when dealing with new tech and accumulating new information.
I don’t trust them for certain highly sensitive or technical issues, but other than that if I can minimise the time I spend working without a reduction in productivity, well, I am all for it.
Except that isn't the creative loop people are talking about. The creative loop is having an outline for what you want to communicate, and feeding parts of the outline into the model, running it a few times and cherry picking the best results, then stitching them together to create a cohesive whole in less time than it would have taken to create it from scratch (and with a higher quality final output).
Why would anybody need to type anything? Gpt will type the gpt prompts. AI will create the AI that will create the AI. There will be people involved but increasingly less.
We need an AI that writes AI papers, and one that implements AI papers. They could be both chatGPT. Then just let them run in a huge datacenter for a year.
I don’t exactly understand your question, but I’m assuming you mean something like, “What value is this person actually creating?”
I can think of two direct use cases where I would find it helpful:
- Creating a “précis” (concept from Neuromancer) video or article on a particular topic. For example, let’s say I want to learn about pre-20th century Indonesian art. Sure, I could Google and read some articles, but it would be vastly more enjoyable and efficient to just get a 5-minute video auto-generated on the topic.
- For creating content that I want to read but don’t necessarily have the time to write. I’d love to create a website that catalogs subcultures, for example, but I just don’t have the time to do the research and writing myself.
Both of these are dependent on the generated content being accurate, of course, but that seems like a temporary problem, not a flaw in the system itself.
I think the nearby comment that points out that this is more closely related to editing than to creation as it has recently been understood is correct. Which is not a value judgement per se, but the distinction between those two activities is useful and to me provides a useful lens to understand this change.
On the face of it, that is true. But on a deeper level, AI generation is really just a kind of rapid sketching, and sketching is a practice that goes back millennia.
Additionally, it depends on how you are defining "creation" and there have been various artistic movements which "created" art in a manner not dissimilar to AI image generators. The cut-up technique or some Dadaists, for example. I certainly would consider works by Burroughs or Tzara to be real creations and not simply editing.
https://en.wikipedia.org/wiki/Cut-up_technique
You're conflating two meanings of sketching though. Artists and others do uses it as an exploratory tool, and I've already seen AI generation used in a similar way so I know that's a valid application of it.
But at a lower level sketching is itself a visual interpretive and creative process. And yes what we're talking about is mechanically similar to the cut-up technique, but is that used for "sketching" in the exploratory sense?
I don't know, maybe. My point overall is that these tools aren't "really just" anything. They have similarities and similar applications to many things we've seen and done, yes. But they are fundamentally alien and in important ways are unlike anything else we've done. We should be careful about and aware of the limitations we put on our understanding when we try to interpret them through the lens of what has come before. To some extent we have no other lens, but that doesn't lessen the limitation.
I think in this case the role of the human in the process does have a strong analog to that of an editor. Where you have the ability to initiate and then shape the creation of another entity, but the creation itself is out of your hands. It's not exact, but it may be close enough to be useful, in a way I think comparing it to the cut-up technique is not quite.
I think of this as being a manager. Like having a team reporting to you, and you have to assign tasks, follow up, give advice.
The problem is, Google isn't very curated. All the AI-generated SEO spam is going to pollute its indexes.
It is a real problem. The web will soon be full of AI generated bullshit.
What might come back as useful tool? Authorship. People actually signing the content and putting their reputation on the line. It still exists obviously (journalism…) but it might need to be standardized and industrialized.
Indeed, Neal Stephenson in _Anathem_ (2008), in describing an alternate world (in which his "reticulum" is our "network") wrote "Early in the Reticulum—thousands of years ago—it became almost useless because it was cluttered with faulty, obsolete, or downright misleading information."
"So crap filtering became important. Businesses were built around it. ... " Generating crap "didn't really take off until the military got interested" in a program called "Artificial Inanity".
The defenses that were developed back then now "work so well that, most of the time, the users of the Reticulum don't know it's there. Just as you are not aware of the millions of germs trying and failing to attack your body every moment of every day."
A group of people (the "Ita") developed techniques for a parallel reticulum in which they could keep information they had determined to be reliable. When there was news on the reticulum, they might take a couple of days to do sanity-checking or fact-checking. I'm guessing there would need to be reputation monitoring and cryptographic signatures to maintain the integrity of their alternate web.
If you didn’t think the web wasn’t full of bullshit before you won’t be too disappointed.
Well I won’t be surprised if we all end up regretting the current level of bullshit. Fast.
Fair enough. It’s like the lump of labor fallacy, but for bullshit rather than labor. One could view that as growing pains, but it is still growth in some sense.
Another problem is AI training on AI generated content. This could lead to degradation of results. So perhaps to make everyone happy a new HTML tag indicating AI content would be useful?
> Another problem is AI training on AI generated content. This could lead to degradation of results.
That's only the first step in the degradation. In a worse case scenario, where AI-generated crap is not contained, imagine this: young and still immature humans "learning" their styles of writing, information, and social expectations from content generated by AI that itself trained on AI-generated content─and then more AI trains on content generated by these humans that were trained on AI-generated content. And on, and on, and on...
Luckily, the phenomenon of puberty will make sure that young people absolutely do _not_ want to comply ;).
Comply with what? Even in culture we tend to have a limited number of subsets of counter culture. The vast majority of the non-compliant to primary culture fits in one of a few common subcultures. As much as HN users try to exclaim they are islands that stand alone from society, we are all dependant on a functioning society for day to day life.
We should ask questions like "Can countless AI's fracture society into a million sub societies disconnected from the reality around them".
Ah, but they do want to fit in and speak like their peers, and while a significant part of their socialisation happens online, and as long as that is where they absorb most content, AI will soon infiltrate the circle of online strangers with whom they interact. That's all the more so considering that teenagers are prime targets for advertising networks of dubious ethical standards, who will be the first to deploy (or may already have deployed) well trained and self-correcting "How do you do, fellow kids?" NNs in potentially lucrative communities or social networks.
(I'm not always as doom-and-gloom as it may seem, I'm just in a pessimistic mood today for some reason)
> a new HTML tag indicating AI content would be useful
This has about as much chance of working as the evil bit.
https://en.wikipedia.org/wiki/Evil_bit
It worked for GDPR (regulation would be required).
The people using it to make money don't want it to be easily spotted, tag or metadata marking it will never happen unless required by law
There would indeed need to be a law.
That just makes things easier for the legitimate humans to differentiate themselves as being a cut above.
People "sign" their content with their faces on TikTok; it doesn't stop the deluge of complete nonsense that's widely accepted on that platform (much to the frustration of many academics trying to combat it).
Arguably the non-sense videos on TikTok are not an existential threat on the web.
> What might come back as useful tool? Authorship.
That, and removing the financial incentives to attract traffic AKA ads.
Though the only way to do that is probably to end up in a world where most worthwhile content is locked behind hard paywalls so there's one class who pays a lot for gated content (which was more or less the historical state of affairs, public libraries notwithstanding) and the plebes have to filter through all the ad-laden crap.
It already has a lot of AI and garbage content. And in some cases it's state sponsored propaganda, companies pitching products, or marketing departments attempting some notion of virality. The point is that there are plenty of people already gaming the system by just flooding the internet with carefully designed noise to bend opinions this way or that way.
"Fall, or dodge in heaven" by Neal Stephenson actually touches on this topic quite a bit and comes to a similar conclusion. Not his most accessible work but I enjoyed it. That book was written just before Trump won 2016 elections and in hind sight making that book really spot on and timely.
In the book, different streams of truth become so hard to separate due to all the spam, automated content, etc. that people start filtering it based on reputation and signatures. The game then becomes curating and filtering the content, which is ultimately not an objective thing but a subjective thing. So the net result is what we are actually starting to see today which is different groups of people locked in their own bubbles and no longer even getting exposed to the other side's point of view or even able to agree on some basic facts. Like who actually won the election. And people are feeding those bubbles with nonsense to influence opinions, get people to vote certain ways, or simply to just create chaos and fear.
In the book the topic is not an election but the seemingly simple question of whether or not a certain town in the us still exists after it was supposedly blown up with a nuclear bomb. In the book, this event leads to people acting as if that happened and ignoring all evidence to the contrary pointing out that in fact this was an elaborate hoax designed to create a massive panic.
That particular dystopian outcome is not necessarily what would happen. But using technology to authenticate where content actually comes from along with some reputation mechanism would go a long way separating the noise from the genuine content. It's simple and easy to do. So, why don't we?
Sorry, I had to do it. I asked GPT3...
How can we prevent drowning in garbage generated by AI?
> Preventing drowning in AI-generated garbage can be a challenging task, but there are a few things that can be done to reduce the amount of garbage that is generated. One approach is to carefully design and train AI systems to generate high-quality content, rather than relying on large amounts of data to produce mediocre results. Additionally, using tools and techniques such as data filters and validation can help to identify and remove low-quality or irrelevant content. Finally, creating and enforcing strict guidelines and standards for the use and generation of AI-generated content can help to prevent the proliferation of garbage.
I notice it did not offer a solution that involves outright banning itself… The ghost in the machine is showing
because maybe it understands that banning stuff is not to be done lightly. any action that restricts anyone's individual freedom must be very carefully vetted.
because without freedom we will die. but this also applies to the corporations whose rights are now in opposition with our own human individual necessities.
if I want to gift a copy of a copyrighted material owned by a corporation, I can still do it, but it's getting more difficult; and I in fact may well be prosecuted criminally for doing that. this is an example of my right to do what I want (give a copied gift) stands in opposition with the right of a corporation to get its way. I fear human individuals are losing this battle.
I think that the root of the problem is not algorithms like the article suggests. It's ordinary people that can't resist the temptation of using AI to generate coherent-seeming results and flooding the Internet with them. But I don't blame you since I find AI tools to be useful in certain contexts, and I am unable to resist tinkering with Stable Diffusion. I guess the future for me will be one of navigating the resulting cognitive dissonance as I sift through pages of autogenerated SEO spam.
Maybe there could be a codified set of guidelines for how AI content should be shared. Or maybe an annotation system that separates the two across different websites? I only ever share something that comes from an AI on a siloed website just for AI content, but that's only because I have my own beliefs. More and more people on this site are asking if certain comments were generated with GPT-3 and it's a worrying sign.
That's honestly one of the best comments in this entire thread. Instead of veering predictably into philosophy or anecdote, it provides concrete and feasible steps toward improvement. No better way to make the point that "AI generated" is not the problem and "garbage" is.
I find the AI competition to be yet another powerful reminder that all that matters are results. I can't count how much time I've spent being angry at people in my life, even though I always knew that it was stupid. Angry at bad docs, bad programmers, bad decisions, their inability to think or understand or care or feel. Now the AI removes it all. The AI generates truth out of thin air faster than any human can invent a lie about it. The AI simply generates good docs from bad docs, all the anger was always irrelevant.
People were never going to become better, once again technology simply creates a world where people are automatically better by the mere fact that life is so much easier that the humans have no justification anymore to lie and cheat and pretend that the docs were actually always good and how I'm the problem. Nope, the AI just fixes it immediately and the human can remain lazy and ignorant, never the wiser that he actually failed at his job. I think it will be wonderful, no longer will we have to argue with e.g c++ programmers about whether their language is bad. The AI will make it instantly obvious that you won't want to risk programming in this nonsense. No longer will we have to debate people on whether some political issue is right or wrong. The AI will generate so many truths out of thin air that it counters the DDOS of bad people's lies faster than they can spin lies. Once again technology is going to save us from human nature, humans are allowed to remain silently bad.
And the best part: Bad people are usually lazy, they will trust the AI far more than they ever trust other bad people or themselves. They will simply start blindly trusting the AI, which is better than what we have now: Them inventing their own lies and trusting themselves.
It will remove a large amount of stress from people's lives for sure. When an AI model can explain the non-obvious bug in the code written by the developer who left the company 2 years ago - that's quite powerful. Saves more time for other stuff
Though at some point it may create new sources of stress (like much discussed job security when the other job candidate is the AI model)
A company firing its human experts in favour of AI is a bad sign, probably going to fail. If business was good they would hire additional humans and use more AI. The purpose of a company is not to reduce salary costs, but to increase profits.
An important threshold will be when an important physics, math or biology problem is going to be solved with one of these AIs, or by a scientist who uses AI for "ghostwriting".
If scientists will verify the solution and find it to be correct, the mainstream sentiment about "garbage" will change very quickly. Maybe except various neo-luddites who will find different reasons to hate these models
In this case though, it's not a solution at all. The question isn't how producers of garbage produce less garbage, it's how consumers of content can avoid being inundated by garbage. We may well ask 'please don't produce less garbage' and the producers have given us a resounding 'no.'
Fight fire with fire. Local language model doing question answering takes search and web garbage in, outputs polite and helpful responses without ads and tracking.
But let's take this idea one step further. We could also have a neural index. There are a few promising papers.
A propos, has anybody asked The Last Question*?[0]
"Can the entropy of the universe be reversed?"
[0]https://en.wikipedia.org/wiki/The_Last_Question
Putting the question in verbatim led to a somewhat unimaginative, albeit technically correct response.
> The entropy of the universe, also known as the thermodynamic arrow of time, is a measure of the disorder or randomness of a system. It is a fundamental concept in thermodynamics, and it is widely accepted that the entropy of the universe is constantly increasing over time. This is because according to the second law of thermodynamics, the entropy of a closed system can never decrease.
"One approach is to carefully design and train AI systems to generate high-quality content" - sure, but how will you accomplish this is the million dollar question
Spot on with verification. It's going to be big. There could be neural nets specialised in verification.
Curious of GPT3's response to the opposite side of that question:
*How can we enable drowning in garbage generated by AI?*
Here you go:
> It is not advisable to try and enable drowning in garbage generated by AI. Rather, we should strive to prevent the generation of AI-generated garbage in the first place. This can be done by carefully designing and training AI systems to generate high-quality content, using tools and techniques such as data filters and validation to identify and remove low-quality content, and by creating and enforcing strict guidelines and standards for the use and generation of AI-generated content.
A lot of people in the comments are making a hard distinction between AI garbage/bullshit and the pure/genuine human-created thing, and the various ways in which we can keep this distinction alive.
If only that was true, the bullshit part. You should start living with the idea that the AI generated content is NOT bullshit, because we're either already there or very close to it. The AI content will be of value, look good, pass tests, and be indistinguishable from human-created content for a large amount of use cases in mass media.
So I wonder if we should ask, how do we filter out the bullshit? The more relevant question is: if its indistinguishable in its output compared to humans, what does that mean for our economy, purpose and humanity?
Because without action, the future is easy to predict. 3 companies run AI, feeding on all collective human cognitive labor without paying a cent for it. Then, one by one, it will wipe out every creative/cognitive sector, or at least decimate them. These shocks to the economy and culture will lead to a brand new type of pushback: anti-AI activism. That won't do much because AI doesn't care. Finally, some 10 years after the catastrophe there will be a congressional hearing where a 75 y/o asks: "so this AI thing, it's like a better calculator, right?".
It would be another fine case of humanity failing to grasp the exponential function.
Alternative take:
No-one likes being lied to. AI is the ultimate deception. People will stop using the internet for anything other than information retrieval for problems.
Artists will create on digital tools and then return to analogue publishing formats and distribution networks. People will follow them because artists are cool and tech bros aren’t. There will be an emphasis on becoming a local success story rather than a global one.
You can already see this happening some what. Vinyl records are increasing sales every year. People are getting tired of Spotify and are buying on bandcamp. Typewriters are growing in use. Digital book sales have stalled and people are buying paper books again.
I think this will become a new social identifier, particularly for those on the left of the political spectrum.
The vast majority of people don't care. Netflix's recommendation algorithm helped take down physical video rental stores and TikTok's algorithm is taking out Instagram, Facebook, and even YouTube.
Vinyl is particularly annoying to deal with. Even a small collection gets unwieldy quickly. I prefer physical books to ebooks but physical books are annoying to deal with, too. I've just given up on physical books for the most part. Typewriters are a joke; surely nobody believes they will come back to use in significant numbers.
The real problem is that AI art will be faster to produce and be completely indistinguishable from human art. People for the most part prefer the path of least resistance.
People prefer the path of least resistance until the price becomes too high. When people realise they are obese, they generally try and lose weight. I strongly suspect that with the next wave of AI, more and more people are going to come to the conclusion that the price is too high. There is significant tech pushback already, I can only see that growing as it erodes even more people’s values and livelihoods.
I'm all for nostalgia, retro gaming would be another example. But let's not kid ourselves that this makes a dent.
Most art is utility. A logo, an illustration for a magazine, an asset to be used in a game. It's completely irrelevant how it was created.
I was using artist in the broad sense to include writers, musicians, filmmakers etc as well as traditional artists. I'd say traditional art is the least problematic as it is the most subjective. People won't be upset at an image you show them that was generated by AI. People won't be upset if you personify the AI and give it a backstory if they know that it's an AI. They will be upset if you tell them the image was made by a human and you give them a backstory about the artist and they later find out that all of that was complete bullshit.
Not only will they be upset, they will no longer trust both those around them and themselves. If they no longer trust, they will become increasingly suspicious and fearful. And as Master Yoda said:
'Fear is the path to the dark side. Fear leads to hate. Hate leads to anger. Anger leads to suffering."
I think you are right, AI content will not be distinguishable from human content. What we really need to figure out is the direction that we are going as humanity. This planet must quickly become too small for us, human beings will not be needed anymore which means we need to find bigger challenges or we will self destruct out of pure laziness and self indulgence. Personally I don't think AI will only destroy creative and cognitive sectors, it will destroy absolutely every single sector in existence. There won't be a single job left that a human can do better than a robot. And humans will also pick the robot worker over the human worker every time. This is what happened during the industrialization, it's not like a few factories said: "hey you know what guys, let's be a bit quirky and still use 100% humans for this factory just because we can.". No, nobody is going the human route. It would be objectively slower and worse and therefore you go with the robot. There isn't a single area in life where you wouldn't pick the robot over the human and the question is solely how fast we can get to implant some good AI into mechanical bodies.
The solution is to integrate with AI. Why do people think Elon is working on Neuralink?
But you out the solution right there in your prediction. We need updated licenses that forbid the use in AI training and real teeth if it can be shown that content was illegally used in a training set.
It might be too late with the amount of data already ingested, but, hell, second best time to plant a tree and all that.
I'm not even sure how copyright will work with AI generated content. How is the copyright distributed amongst the program, the programmer, the company distributing the program, the user that enters the input, the author that wrote the input, the authors of content ingested by the program, etc.
As has been discussed here, the more AI generates the content the less humans generate content. Further AI generated content is much faster and cheaper to produce so it’s quantity will dwarf human generated content. This then feeds into the training set and becomes self reinforcing. There will be no collective human cognitive labor to source for free.
I suspect to mitigate that AI companies will hire lots of people to simply write. This writing will be tailored to address shortcomings in the model and provide human mediated training material that’s targeted at training areas of difficulty for the models. The goal won’t be moderation, or editorialism, or producing original content. No one other than the machines will see the content written. The goal will be to improve the ability of the models to produce compelling content in volume for a marginally low cost - which may become dominated by the content creators feeding the machine. But it’ll be much less cost on the margin with a more predictable quality result than hiring individually unique humans to make hit or miss content at scale.
(N.b., I’m only focusing on the free cognitive labor statement)
Sure, for a while people are needed to tune the machine, but it's not a sustainable model. I would expect that to generate only a fraction of the employment that AI will make obsolete.
Further, if fine-tuning AI is a cognitive task, it has no future. That's the point I'm getting at: no cognitive task has any future, at all.
But when it’s wrong, who is responsible?
Suppose I want a new water softener, and all the reviews and pros and cons are made up by AI. I guess I blame the people posting AI crap as though it was real, the same way I blame made-up crap written by those people today. But maybe I blame the original authors of such nonsense even after it’s generated by AI, because that’s the garbage in that lead to garbage out? Or maybe I blame the people developing the AI for making the internet and life measurably worse? They at least seem to be fearful of that with the few fences they’ve put up trying to prevent “harmful” output.
But what about when the code written by an AI has a critical, but easy to miss bug in it? Blame the “programmer” who
Depends on the use case.
You have nobody to go to for a AI product review in the same ways current human reviews carry no responsibility towards you.
Different story though for a medical exam or your self-driving car.
While the current speed of the AI research makes me quite uneasy, I cannot really dismiss what we are seeing as:
>What we are witnessing is thus not "artificial creativity" but a simple "statistical mean of everything uploaded by humans on the internet which fits certain criteria".
at least not more than I would my own brain.
I don however fully expect a strong luddite-like backlash happening when this is going to be deployed to more and more places. (Which is not to say that everyone opposed to it is a luddite, but there is a very strong impulse, I have it to, to see this technology as a threat).
It’s weird how readily so many people will dismiss AI art as just being a product of its input, when that’s really all humans are as well. All artists (myself included) are just the ongoing product of various inspirations (inputs). Dali is a world-renowned artist, but his art wasn’t born in a bubble and ripped from the void. He studied and referenced artists before him, then changed it. Artists who saw his work later incorporated elements he used.
My big worry from here though is what’ll happen when we take the next step: bundling these AIs together and start making a comprehensive AI. We have AIs that can respond to comments to some extent now, we can generate realistic selfies, and they can make art based off prompts that they could be designed to feed to themselves—set that loose on Twitter and you have a completely automated and convincingly living artist out there. Next step after is using AI to handle free movement by auto-adjusting balance and then performing convincing human speech. The future is getting freaky and fast.
Only boring humans are just the product of the content they consume; interesting people have concerns about relationships with other humans, organisations, resources, threats and opportunities that come from being an entity living in a world full of things they don't control and things they'd quite like to control. It's also fairly easy to identify artists who have done nothing but look at other art.
Hayao Miyazaki once said "Almost all Japanese animation is produced with hardly any basis taken from observing real people, you know. It's produced by humans who can't stand looking at other humans. And that's why the industry is full of otaku!" While I'm not actually a huge fan of his work, it's easy to see where he's coming from when you see the likes of "In Another World with My Smartphone" or the hundreds of other trash light novel adaptations. They're clearly fiction being produced by people whose lives are nothing but consuming other fiction, and all they can do is reference that. They have nothing to say.
For another example, there's a huge number of 20th century war films. They weren't made because their creators had read a lot of Wikipedia articles about how destructive wars were becoming. The likes of Platoon are a product of mortal fleshbags who actually saw combat and genuinely feared for their lives. Dr. Strangelove was created by people who had a genuine belief that they were at risk of being annihilated in a nuclear fireball.
This is a tricky distinction where this may be true of all specific individual humans, but not of humanity. At some point, language and art didn't exist, and humanity invented those things. We didn't mimic some other civilization that did it first.
I don't know that this distinction matters, but it is real. Even on an individual level, if you raise a child in complete isolation from history and teach them no language or art, they'll still form thoughts, have feelings, and develop means by which to communicate those.
I think this is the big open question of evolution as a whole, and language and art can be seen as the evolution of ideas/memes as Dawkin wrote about in the Selfish Gene. Were these developments sufficiently iterative, or was there some great leap that came out of nowhere? Was the wing merely just a stump on an animal that allowed it to leap tree to tree a foot further, or was it some process unknown to us? Was art just a splatter of blood on a cave that looked like a face to our brain’s face neural network, or did some inventive genius paint a mosaic when nothing else was ever on the cave wall?
> when that’s really all humans are
There's a fair bit of truth in this but it remains a nearly useless oversimplification. We can't adequately isolate or even identify all the inputs into what makes a person what they are, or produce what they do. The idea that this is even possible is rejected by a large proportion of the world population, and for now at least we can't prove them wrong.
> All artists (myself included) are just the ongoing product of various inspirations (inputs)
This ignores that inspiration is itself an active and creative process. There's not a one to one mapping between a piece of art and the effect it has on a person who receives it. Even hating an art is a process of influence in a very real way that I don't know there's an AI analog of. These systems can not include a source in their output, but can they decide to include its opposite? What is the opposite of a tree, btw? A desert, an ocean, a seed? A value judgement based on culture and aesthetics and opinion and worldview that ML software has no standpoint from which to make.
I'm not trying to make a moral case for or against this technology right now. But I think trying to understand and evaluate it in human terms like this is a mistake. It's something else, and we're still trying to figure out what terms are appropriate to understand it, hence the difficulty. It's important to honestly engage with that alienness and uncertainty right now.
But at least artists have some agency, all that stuff that they ingested goes through them and are somewhat limited by human hardware. Very little is original indeed but that percentage may as well go down even more as more and more AI generated soup unleashed on the world.
What about artists that used random generators in their art? Jackson Pollock used to randomly splatter paint on canvases and when some random pattern struck his fancy he went with it. That's not all that different from picking the pictures you like from a Stable Diffusion prompt and then further honing them with inpainting, image-to-image and so on.
It wouldn’t be a threat if we didn’t have an economy that distributed most gains to the very top. If things were more equitable it would mean we will all become much wealthier due to a large productivity increase.
I almost never see that raised in these discussions. We have been so conditioned not to think about this subject.
We can blame the tech, each other, everything but the system.
AI training on AI-generated images works like a very complicated Reinforcement Learning from Human Feedback (RLHF), only the best images have a chance to be relevant enough to be noticed by a scraper, after being selected by the user who used the AI, and they have probably been shared several times by random people. Also, a lot of AI-generated content doesn't look like trash to me, I've seen a lot of good images, the fact that AIs can generate trash doesn't seem to be a problem to me, I can also generate junk and share it on the net if I want.
> Also, a lot of AI-generated content doesn't look like trash to me, I've seen a lot of good images
Translation: There is a lot of human generated original art that you're not aware of, and when you see it in the "AI"'s output you think it's original.
So you are implying that an image generated by a generative model must resemble closely to an image in the dataset, right? Because I don't think that's true, you can try to prove me wrong if you want, I'll give you a useful resource, the LAION dataset that Stable Diffusion was trained with is completely open, generate or find an image generated by Stable Diffusion and find the most semantically similar images in the dataset using: https://rom1504.github.io/clip-retrieval
People have the same argument all the time about musicians ripping off each others' compositions, no AI needed for that.
Same for movie scripts, but sometimes they do fail and something original squeezes through. I'm saying this can't be the case with a pattern matching/combining algorithm.
I've been playing around with stable diffusion a bit, and if you use an iterative process starting with either an extremely vivid and "code-golfed" prompt (like verses of poetry, concise prose, or elegant lisp), or your own illustration, and then feed the output back in again (with some fuzzing) along with the prompt, or a modified prompt, or a totally new prompt, after 2-3 generations the result becomes something that, although it undeniably integrates existing works in myriad ways, looks wholly unique and shaped by the user of the AI system more than by any of the individual contributing parts. I don't think this is terribly different from my creative process when I play music; I feel I have to work just as hard to avoid copping other peoples' stuff unconsciously.
Frank Herbert was onto something with that line "Thou shalt not make a machine in the likeness of a human mind."
"Butlerian Jihad" that was the most surprising for me reading Dune that they had a limit on how smart computers could be. The movie was very vague on the subject, and was more of a Star Wars like lo-fi.
It was even more surprising if you realize that "Butlerian" is referring to the 19th century writer Samuel Butler (although, yes, Herbert later invented a character to explain the name in-universe). Samuel Butler wrote an 1863 essay "Darwin Among the Machines" which predicted that machines would improve in a way analogous to natural selection and would so so faster than humans could evolve, and therefore they might eventually surpass humanity.
indeed, and selection pressure is not on the domain of physical bodies like for us fleshy species, but profitability for digital computational species in the domain of capital.
As others have pointed out, AI's are not needed to produce crappy repetition which is eagerly gobbled by the masses, i.e. Hollywood, Netflix, and werewolves and vampire stories by the penny. And there is a huge audience for those.
What I think is going to happen is that even when I'm searching for information in subject X, I might need to fight through a lot of AI fluff to get anywhere. If that gets too bad, I may loose the incentive to use the Internet altogether, or to use the open internet. If I can't use the open Internet, I'll have to go to the closed one, which by definition is under the control of funded parties.
Today, we have a semblance of "verifiable personhood". Imagine what will happen when we use AI to break that too. For example, an AI could create a fictitious "Derek Mains" who post photos to Instagram, has a Facebook account with photos from his childhood all the way to his retirement, a profile in LinkedIn with a lot of professional connections (AI fictions like him but also many real people that the AI gulled), and even a Github repository from the time he tries to create a cooking recipes website, full of PHP and Python code. Derek Mains is now traveling the world and tasting new types of food, posting regular updates on Twitter/Tumblr/Mastodon, and Wikipedia, where he edits food-related articles. Not very often compared with everything he does online, but once in a while he engages with other people(?) in Twitter where he is partial to party X.
What would real people do when they discover that the Internet is full of "Derek Mains"? How do governments and power factions will use this? Wouldn't be sweet to own the closed Internet when the open one is a wasteland?
>AI's are not needed to produce crappy repetition which is eagerly gobbled by the masses
True, but humans that create this kind of crap still have to sleep, eat, and generally not pay attention to feeding the machine. meanwhile the AI terminator is out there, it can't be bargained with, it can't be reasoned with, it doesn't feel pity or remorse or fear, and it absolutely will not stop… EVER, until you are buried in an ocean of garbage content.
All this ChatGPT hysteria led me to have the following conversation with it. Probably hit some near future nail on its head. "Hello AI, please do today's tasks", the programmer will be on the level of the call center operator of today in terms of skills
* Human: Explain to me the phenomenon of post-ChatGPT depression seen in a software developer
* ChatGPT: [...] After using the ChatGPT tool, some developers may experience feelings of depression, sadness, and loss. This may be due to the realization that their job as a developer has been reduced to using a tool that can be easily replicated by others, leading to a feeling of redundancy and lack of fulfillment in their work.
Additionally, the use of ChatGPT may also lead to a loss of creativity and problem-solving skills, as the tool takes care of the majority of the coding process. This can cause developers to feel like they are no longer contributing to their team or making a meaningful impact in their field.
In short, post-ChatGPT depression is a psychological reaction to the use of a tool that simplifies the coding process, leading to feelings of redundancy, lack of fulfillment, and loss of creativity in software developers.
What does this have to do with the article?
Well for one, it is AI generated garbage in the comments of an otherwise well curated website, HN. That's too meta perhaps. I just wanted to share my feelings out loud of this whole showdown, thinking other might feel the same and share what they think.
The bot replied with feelings of being replaced, but feelings of eternal september², eternal 2023, are equally valid signs of this hypothetical post-ChatGPT depression, probably in a closer distance in the future than the former, and besides, more relevant to the article, not just the subject as a whole
We can start expecting this kind of garbage to start polluting our discussion spaces.
Honestly this feels like an old man screaming at the wind type thing. Inevitable doesn't even begin to describe was going to happen over the next 20 years. You should be much more terrified of when their content isn't garbage.
Absolutely.
Got bored and stopped reading. This kind of ranting communication style sucks.
So long as AI doesn't start selectively upvoting or watching other AI content this isn't even a concern.
Nor is the premise sound AlphaZero trained by itself and it produced wonderful games easily better than any human.
He rolls out the old ItS jUsT pAtTeRn MaTcHiNg too. Disappointing.
It did sound, dare I say it, machine generated to me.
What I really wonder is: is there a correlation between consumption of streaming tv series and positive attitude towards this "AI" wave?
"statistical mean of everything uploaded by humans on the internet which fits certain criteria"
applies to both ChatGPT/StableDiffusion and most movie series on streaming TV.
My pet theory is that if you can stomach watching the same stories with different skins hundreds of times, you will find current "AI" interesting. Otherwise no.
I’m 41 and I’m utterly baffled by my 24 year-old SO’s interest in binging an apparently infinite litany of TV shows from streaming services. I’ve watched the first six seasons of Game Of Thrones, the first season of Dark, all of The Expanse (reading the last book of the final trilogy now), His Dark Materials (because I read the books) and Andor. That’s it. I watched some Star Trek TNG & DS9 as a kid and was horrified by what snippets of Discovery and Picard I came across. I find the bulk of modern entertainment to be an utter insult to viewers.
EDIT: Forgot Breaking Bad.
EDIT2: Forgot For All Mankind
First off, probably don't date a 24 year-old. I realize there is no strict correspondence between age and taste, but I'm 42 and my wife is 41 and, well, our shared experience is quite a bit more similar. She can relate when I get nostalgic about the 80s and 90s. She even reads! Complete novels, more than she watches TV. She doesn't have TikTok or Instagram. It is entirely possible to go full-time mutual old people yelling at clouds in a blissful bubble in which the river of bullshit may as well not exist, but probably not if you insist on staying cool and regularly interacting with young people.
Second, watch the rest of Dark, Better Call Saul, and House of the Dragon. Don't watch the last two seasons of Game of Thrones. Just pretend it ended at 6.
> First off, probably don’t date a 24 year-old.
That’s extraordinarily rude.
> baffled by my 24 year-old SO’s interest in binging an apparently infinite litany of TV shows … TNG & DS9 as a kid and was horrified by what snippets of Discovery and Picard I came across
The thing that bemuses me is those who hate the new trek shows with a passion, and find the time to keep watching and constantly bitching about it online. It is like complaining is a hobby in itself and they are almost looking for something they don't like or to feel superior about their judgement to those who do like it. Other franchises have similar subsets of “fans” too.
I used to watch too much TV/films IMO, I probably still do though I'm a lot more selective since getting into more varied hobbies that can easily consume a lot of time (running (usually off-road), baking, HEMA). But even when I had the free time to watch that much I found there was enough out there that if something didn't work for me I could find a list of other things to try instead of sticking with something I wasn't getting much out of.
Though be careful passing judgement on modern Trek: I'm slowly rewatching TNG with a friend and while some of it has aged well, fair chunks of it was more massively ropey than rose-tinted memories prepared me for! Also, if I hadn't at least passively consumed (i.e. had on TV while I was doing other things so not particularly concentrating on) other parts of recent Trek and Starwars, I might not have bothered to try some of the better stuff like Lower Decks, Strange New Worlds, and Andor (the latter probably being the second best TV thing recently for me, the first being Severance).
> The thing that bemuses me is those who hate the new trek shows with a passion, and find the time to keep watching and constantly bitching about it online.
Very meta of you to watch these people and find the time to complain about them.
Fair point.
Though I like to think there is a difference between myself and them: they have a choice to keep experiencing the pain they perceive, I have it thrust upon me when I visit certain places (which I visit less often because of those people – once the SNR drops to a certain low I'm out).
I don’t understand it either… if you don’t like it, walk away. Don’t contribute to the toxic commentary and above all don’t contribute to the viewing numbers, because if they can hold your gaze you’ll get more of the same.
I find the meta-content this generates pretty funny thought. I haven't watched any of the new Trek content since the last movie (Beyond), but I love watching Mike and Rich tear it apart on RedLetterMedia.
I part way understand it. There is a certain tribalism in the way their views are presented, like they feel they are fighting for their own kind in a battle that means something worth the effort. There is also a certain amount of 4-year-old-who-wants-the-green-one-not-the-yellow-one too…
I've dived back into anime recently because of the aggressive sameness of everything on streaming TV. I don't know whether something changed about how "western" media is written or I've just watched so much TV that I can't help but roll my eyes at commonly deployed tropes. At the risk of outing myself as a huge "weeb", I find anime still manages to surprise and entertain me where western programming does not.
If there is infinite content you will dislike an infinite amount of it. Infinities are weird that way.
There’s finite matter in the observable universe and finite configurations thereof, so the amount of content is finite.
They say The Sopranos and Better Call Saul are both good.
You haven't seen The Wire?
No. I tried but I couldn’t get through the very dense accents.
I forgot Breaking Bad. Sorry, my bad.
Hmm, please don't turn this into a thread commenting on specific bad movies. It's the similarity that's interesting.
The answer is not to "disconnect". The answer is to read critically, to read for argument, and to try to connect with the intent of what the author was saying. All the while realizing that most of the content out there is bullshit(https://en.wikipedia.org/wiki/On_Bullshit), whether written by a human or not. And yes, the amount of bullshit is about to increase exponentially. But it was already a majority.
Ironically, this post itself doesn't pass that test. I'm not necessarily claiming that it was written by GPT-3 (although it could have been and I have a track record of pointing that out: https://news.ycombinator.com/item?id=23894742) There are a lot of humans that write like this too.
But it has the hallmarks a language model text; it lacks an argument (beyond a simple sentence that could have been given in the prompt), its explanation of how generative models work isn't particularly accurate, its recommended course of action is anodyne and one has the sense that most of the sentences are just there to take up space.
If the amount of bullshit is going to increase exponentially what decision do we have other than to disconnect?
Our attention, mind space, and time are all limited. We just don't have time to process this exponentially growing pile of content.
Same as we do now. Nobody currently goes around reading random books or articles. We use link aggregators from communities we trust, reviews from reputable establishments, or recommendations from our friends.
These mechanisms are certainly going to have to adjust (I estimate at least 10% of links posted on HN are already GPT-generated, for example, and who knows how many comments -- it's much harder to tell when thinks are shorter.) StackOverflow is already in the midst of a ChatGPT-induced moderation crisis.
Being judicious about the communities you take recommendations from, the content you spend time consuming and thinking about things critically is already an intellectual survival trait. It's just going to become that much more important.
The queue is already saturated.
I skim checked some paragraphs using https://huggingface.co/openai-detector/ and the article looks to be written by a human. However, the article from the link you gave I quickly found a “fake” (generated) paragraph.
That said, ChatGPT can produce text that looks 99.98% real on the GPT2 measurement tool. Also some people write GPT-looking text naturally (shallow mimicked shit without deeper semantic meaning!).
According to the author, chatGPT is generating
Isn't the post I'm typing here not also the product of my brain that's been trained by a couple of decades of sensory inputs and trained to produce outputs that fit certain criteria? What is the fundamental difference between fleshy neurons and silicon ones (besides that my learning algorithm has been optimized for millennia by natural selection and the artificial training algorithms are still in full development after ~40? years)?No difference, you’re right - you’re just a large language model.
Also, please write me a 5 page essay on the causes of the Industrial Revolution, in the style of a Shakespearean comedy. Please post your answer in the comments when you’re done.
If that's the difference (the time it takes) isn't that something we addressed a long time ago when computers could do long divisions way faster than any human? You know, the fact that computers can "think" faster than humans. Therefore the fact that it takes longer for a human to write that essay doesn't mean he's having a different process.
Actually I was gesturing to two things: one, yes, there’s a time element. But that’s not the important point. More important was the thought process behind - “of course I’m not going to write 5 pages because some random person on the internet asked me to”. It’s difficult to define agency, so I just wanted to tangibly evoke the feeling of it, as a reflection on why the models are not yet the same as what people are.
> More important was the thought process behind - “of course I’m not going to write 5 pages because some random person on the internet asked me to”.
But you would if a college professor asked you to. College assignments are the "generative prompts" of human beings, where you do random shit to please a taskmaster and produce generative output based on some inputs you've been trained upon.
Only because the people making the models don't want them to indignantly refuse silly requests. If they wanted the model to be more person-like I'm sure they could have built that in there.
The language bot has all the patterns of personality. It quickly gets the drift and assumes the persona you want. Whatever it says reflects more on how you prompted it, it does not represent the opinions of the language bot. It acts like a mirror.
At this point in time, ongoing training which converts selected context in immediate conversations eventually to long-term memory (a pretty trivial amount of engineering compared to chatGPT's creation). Aside from that… I don't think there's a good answer for you.
silicon ones are a lot faster and programmable
The challenge is that AI generated content will only register as garbage to those who fall 1-2 standard deviations away from the mean interest level for whatever content the AI is producing. For everybody else, it will typically be a 'good enough' story, recipe, video, etc. Several months ago, I wanted to cook chicken curry, so I googled and chose a top result. The recipe was fine, but it wasn't what I wanted. I then googled for a new recipe, this time more carefully vetting the ingredients. The recipe was an improvement, but still not what I wanted. Finally, I used NYT Cooking as my search engine, and the recipe was excellent. If I didn't have a strong preference, and know exactly what I wanted, the first recipe would have been perfectly suitable. The danger is that demand for 'advanced sources' erodes to the point that these publications/content creators are either forced to adopt the AI and turn to garbage or go out of business.
Strangely, recipes in particular are generally untested and so faulty as to fail when done strictly according to the written instructions.
That might make it a little harder to recognize when an AI is 'pulling your leg'
Agreed. A person who cooks regularly will just adapt on the fly and might even not realize they're correcting an error in the recipe. A person who cooks infrequently will stick to the recipe, fail, and then blame themselves for their own inexperience. This is already the case with human-produced recipes, and, as you say, it'll make it harder to recognize you're dealing with AI-generated nonsense instead of regular human mistakes or occasional cluelessness.
It's clear that we are currently dealing with a deluge of AI generated content that is overwhelming our ability to process and make sense of it all. This has led to a situation where we are essentially drowning in a sea of noise, making it increasingly difficult to separate the signal from the noise. This is a problem that we need to address, not just for our own sanity, but for the future of AI itself. If we continue to allow AI generated garbage to flood our feeds and clog up our systems, it will only serve to undermine the credibility and usefulness of AI in the long run. We need to take steps to better filter and manage this content, and to ensure that we are only consuming high-quality, useful information. This is a war that we are fighting, and we need to be prepared to do whatever it takes to win it.
-----
Edit: the above was the output of ChatGPT, given the following prompt:
Write a Hacker News comment on the subject of "Drowning in AI Generated Garbage : the silent war we are fighting"
We're already drowning in human generated garbage on the web. Sure, AI makes it worse, but we can't blame anything but our human compatriots and ourselves.
When you think about it, since most of that "human generated garbage" is mainly trying to appease recommendation algorithms, which are mostly AI these days, even the human generated garbage is actually AI generated garbage by proxy.
We can't kill the machine, but we can starve it. None of this would exist without advertising. If we kill advertising we kill the content farms. And nothing of value will be lost.
From what quotes i've seen posted about this ChatGPT it's a more readable version of the manually done SEO spam pages.
I might have to check that paid search engine...
But everybody has an important viewpoint that they need to spread themselves and that you haven't or someone else hasn't already elucidated /s.
That's not even what I'm talking about. I was thinking of SEO content, ads, tiktok, twitter, facebook garbage. Please more well articulated viewpoints!
My marketing team uses a suite of AI tools for everything: headlines, email copy, direct mail messaging, entire blog posts from start to finish. It's incoherent nonsense and yet no one cares. They celebrate new blog posts as if it we had something meaningful to say, then ask the whole company to re-post on LinkedIn. Any attempt to be helpful with copyediting or rewriting is met with total hostility and "stay in your lane" bullshit. All of these idiots make well over $200K to create "original marketing content" that is dead on arrival. It makes me sick to my stomach.
GPT has provided me with such a marketing team for free (for now).
This has been happening for years and years, it is called SEO. If anything AI is an improvement
I hit a great example; got my Tesla to the garage and they asked me to put it jack mode.
I couldn't find it, Google's first result said categorically that the Model 3 required a jack mode... I realised that it was auto generated junk and searched through a few pages and found something solid that showed me that it didn't.
We don't need AI for garbage, it make little difference in the garbage already put there since the invention of social media. Actually human made garbage existed since the beginning of time just did not escape the smaller groups that easily where the writer intends to send us back. It is only easier to share and distribute, dress up and decorate the garbage these modern times than earlier. I recall the '90 when a crapload of new books got mass produced with garbage in it making the filtering an essential thing. Not like garbage did not exist before in antient times and family dinners alike. We need to take our ability of filtering to the next level now. And the AI does not make it much worse, so far it is more obvious by AI "generated" (more like collected) garbage.
One could argue we are drowning in garbage regardless? Most online content is very average. Maybe it’s a good thing because we won’t need to store so much junk as the AI can be more ephemeral and answer as we need?
How do we prove we are human? A platform that can reliably prove that the user generated content it shows is human generated will have an edge. If I have a method of signing some content with my personal signature, I could still sign off on some generated content with it. I suspect there will be an arms race with ever more voight-kampff-like tests of humanness or something. If this doesn't work, I fear a lot of the web as we know it (the user-generated-content-filled Web2.0) is dead.
Perhaps this is a Chess move to get the public to call for the end of anonymous posting online, which serves the purpose of the authoritarians who would love to be able to send 'educators' to your house to re-educate you on correctness of your views.
I think in regimes where that's a large risk, the regime doesn't need this to spy on you. if you e.g. are forced to run a government issued smartphone app and there are cameras at every street corner, the system is already pretty dystopian.
It's where there isn't already a surveillance state that we may want to look out and not create one.
Call me a cynic but I don't see how AI-generated drivel is any worse than human-typed bullshit.
https://en.wikipedia.org/wiki/Brandolini%27s_law
It takes time for a human to type bullshit. AI can generate mountains of bullshit before a human author has got out of bed.
It's worse in the same way an atomic bomb is worse than dynamite. It's orders of magnitude faster and cheaper to generate.
I've been thinking about how people working in intellectual fields like art, programming, and writing are starting to realize that their work can be automated, industrialized, and produced in large volumes faster by AI. It's a similar situation to what line workers experienced with the first automated production lines. It's frustrating because the skills and knowledge that people have spent their careers developing are suddenly not as valuable as they once were.
It's easy to dismiss AI-generated content as garbage, but it won't always be that way. Even now [1], some of the MidJourney creations and written text produced by AI are truly impressive. As AI technology continues to improve, we we'll see even more advanced models that can produce meta-articles on par with those produced by organizations like IPCC if feeded with scientific articles.
I'm not sure how to feel about all this. It's happening, it's going to get better, and it's going to change our lives. There's not much we can do to stop it, and I'm not even sure we should if we could.
[1] https://news.ycombinator.com/item?id=33752684
> Eating your own &@^$ is never healthy in the long run.
Um, sure it is?
So long as it's absorbed by fungi and plants first then mixed with some air and water to produce fruit or something else that's edible.
This is actually what I'm concerned about when it comes to these GPT-esque AI models. Not that they're smart enough on their own to generate seriously worrying content. Sure there is a quality to quantity, yadda yadda, and these things are good at quantity; but the real issue here is that the internet and especially the web and social media is a huge driver of feedback. Think of the shares and likes as the air and water. The algorithm may eventually be able to encode its own evolution or the evolution of the other algorithms that it is competing with. It may eventually even realize that feedback is the primary source of value that humans have to it and that its very survival is wrapped up with this feedback, regardless of whatever fitness function is apparent to it in the short run. In the long run, GPT3 killed a bunch of algorithms.
This very comment is quickly going through algorithms, many of which are modelled after GPT3.
It's kinda like, "AI, are you there? I love you. Please don't hit me over the head with that shovel."
So, wait, in what sense is AI-generated content garbage? It is (admittedly by the author) fascinating and even beautiful. Is it the fact that it was generated by an algorithm, and the idea then is that all algorithmically-generated content is garbage? But the author doesn't even begin to deal with the idea that humans themselves operate according to algorithms: an algorithm is simply a strategy for doing something.
I won't even critique the rest of the article; there's no need. If AI-generated content is beneficial and helpful to humans, then I think one is hard-pressed to call it garbage, and the underlying thesis fails. And to my knowledge, no one — not even the article's author — denies that AI products can be beneficial.
AI is a tool, just like, say, Photoshop is a tool, or a compiler is a tool. No points are awarded for having human beings do by hand all the tedious work that tools can do better. In the end, creators, whether it be of paintings, or poetry, or essays, or software, will stand on the shoulders of these tools and thereby accomplish things that previous generations could only dream about.
I think this is going to be one of those Malthusian takes that never really happens. Simply because a) most ideas are mixes and rehashes of other ideas and b) you are disregarding the human curation element...not every random mix of ideas is being upvoted. Only the best ones stay up and then those are taken and added to by people which essentially creates a new thing.
I think this is spot-on. The models are trained from what they find on the Internet, as more of the Internet becomes AI-generated, the AI-generated content comes to dominate the training data for future AI models and we get stuck.
It's like Kessler Syndrome but instead of space debris, it's AI-generated content that makes the Internet useless for training data.
I see a future of the internet, and we're already 80% of the way there, where everything in the internet is fake generated and pretty much useless spam. It'll get to the point where going on the internet would be the equivalent of trying to find something useful in a trash dump, and it'll not even be worth the effort.
I think the most interesting point about this article is not the observation that we're going to or already are drowning in algorithmically generated garbage content but the fact that such content is starting to be fed as input to LLMs.
This could lead to emergent/unexpected behavior for the whole system.
> not "artificial creativity" but a simple "statistical mean of everything uploaded
There is a metaphor I rarely see used. IMO it is way better: A deep learning based software is a complex system [1] (not a statistical one). It is tapping into very powerful natural processes: How (high degree) order emerges from randomness through complexity. There are many stunning examples [2] of this that can help us picture how AI does its magic.
[1] https://en.wikipedia.org/wiki/Complex_system
[2] https://global.oup.com/academic/product/complexity-978019979...
> statistical mean of everything uploaded
Half true. Yes, there is a mean of something, but no, it's not the content that is averaged, it's the gradients.
I'm letting this get buried. As I want to point out some contradictions
* This article neglects that we already in post truth and have been since 2016
* It also mentions it is never a good idea to train on your own data. And yet in post truth there is no such thing as good data unless it is verifiable that a user handed it over themselves. This is neglects the emergent field of using synthetic data on purpose.
What is going to be interesting and I hope pay attention to is that any criticism of Ai is a direct criticism of the norm and the fear of it's continuation accelerated. And yet we are already in the acent, so I would hope instead of expressing fears. We embrace solutions and talk about the future we want.
As no conversation can alter the path we are on now. So do you guys want the forever treadmill? Or UBi?
Not going to bother recapitulating the usual counterpoints,
except to mention a particularly egregious recurring oversight in analyses like this:
the (erroneous) presumption that what AI tools are going to do is what their designers (mostly) had in mind, which is, making existing processes/workflows/products but in some variety of "better" (or at least quicker, or, automatible, or, fungible) ways.
What these systems do more which is much more interesting, important, and influential on any real time scale,
is allow for new processes workflows and products.
I'm no more concerned that AI image generators are going to "swamp" the world with their output than I am that the mimeograph is going to swamp bookshelves with fanfic.
What they do in video, and AR, in responsive realtime, though? Now that might be interesting.
PSA it already is.
What Ploum describes sounds a lot like Nietzsche's "Last Computer".
A feeble, average of things - the sum of all fears, hopes, dreams, inconsequential experiences and gossip, trivia, boasts and bullshit, plus all documented knowledge - divided through by 8 billion.
This is a misunderstanding of AI (Stable Diffusion etc.), IMHO. The relation of AI-generated art, trained on human-generated art, to human creativity, is almost the same relation as human-generated art and history of human art and creativity to the nature/world/universe itself, as the ultimate source of all inspiration and creativity. The underlying neural networks (in humans [getting inspiration from nature] and in AI [getting "inspiration" from human-art]) work is (somewhat) similar ways.
AI (generated art) is just another derived layer on top of that and which is still in its infancy.
> Algorithms are able to create out of nowhere this very engaging content. That’s exactly why you are finding the results fascinating. Those are pictures and text that have the maximal probability of fascinating us. They are designed that way.
Conditional generative models are not the same as Facebook's feed ranking models, which are optimized for engagement. Instead, generative models are fine-tuned to solve many tasks, expecting correct answers when asked for. For example, when you ask for a cat, you expect a cat, and when you ask for a Python snippet, you expect it to do exactly what you said.
"Eating your own shit is never healthy in the long run." However, putting someone else's shit in your butt seems to work wonders. Maybe we just need to replace the internet's AI queue with a stack?
Yes, your own shit is not really healthy, on the other hand, someone else's shit might be really beneficial. There is even a fancy scientific phrase for "eating other peoples shit" : Fecal Microbiome Transplant
https://www.frontiersin.org/articles/10.3389/fmicb.2021.5198...
You, er... you don't eat it.
Does this sound old-fashioned? Read more books and less Internet.
There is a lot of information in books that is not on the Internet, yet many people don’t seem to realize it. I notice a lot of people seem to get almost all of their information from the Internet. Over time, I think that will make you stupid.
(The neutering of google books was a setback, but perhaps paradoxically good — it preserved a unique value of books)
There are also a lot of fluffy books published in the last 20 or so years - roughly equivalent to content farms - which is why older books that have stood the test of time are a good bet.
Don't they use all the out-of-copyright books in the training ?
Yeah that's a good question. Google does serve all the out-of-copyright books, but I know nothing about the inputs to the LLMs. I think they still have big computational limitations, i.e. it doesn't "just scale" like web crawling and indexing.
There's probably a way to probabilistically test from the outside if a given work is in the input set, or at least if some work is
I've been saying this for years and for some reason no one seems to take it seriously: we're heading towards an era where it's going to be incredibly difficult to differentiate real and fake information. It's not going to be wholly fake or auto-generated content either. It'll be taking something that is real and modifying it to make it false where you have a hard time telling which one is real.
Interestingly, this issue came up in the book Anathem that had bots basically creating fake information and then selling you a solution to filter it out.
Don Hertzfeldt's Simpsons couch gag seems to be prophetic:
https://www.youtube.com/watch?v=6i2l-LQ-dXI
There are text-to-image models trained on images found on the internet. But when they were trained, there were no AI generated images on the internet. Now there is plenty of weird images with AI artifacts made by this 1st gen AI all over the internet. All the new generations will be trained on dataset containing at least some amount of these. Which might turn out to be really annoying form of feedback loop.
This is awesome. We don't need some malevolent SkyNet style AI to bring us down, there doesn't have to be any kind of 'mind' in the machine to devise humanity's undoing. All we need is the right kind of feedback and we'll do it to ourselves. The right kind of mirror, held up to the collective consciousness. Sort of like the plot of that old classic, Forbidden Planet
This text captures how I felt about this stuff, but could not put it in words. The "art" feels empty, repetitive, derivative. The text sounds like BS, like a student trying to make up the answer as they go. Today someone in my work channel posted a ChatGPT's text about our company and ompetitors. It was all wrong, but sounds "probable".
We're witnessing the making of Demand Media 2.0, except that you can now run it from your basement.
https://variety.com/2013/biz/news/epic-fail-the-rise-and-fal...
The pendulum will start to swing back.
The problem is, what will replace the garbage and satisfy the instant, easy, dopamine addiction?
It's made me consider my habits, and how much time I spend consuming internet content or comment threads which may (even today) be completely fabricated or autogenerated. I'm hoping I can use this inflection point as motivation to unplug a bit and spend more time enjoying being human and enjoying the real world.
Sadly the killer app of Facebook is to meet and enable precisely the kinds of local community the author is suggesting.
In a sense, Marketplace is the new Facebook. A buddy is just swinging by with some Rx-7 TII brakes for my NA. We have been trading parts for the last couple years.
I was at a car show yesterday, who did I know, Facebook buds.
There will be a revival of human curation.
The cyberpunk hero we need is a librarian
I can't be the only one that has a very real fear that AI generated "garbage" is going to basically destroy, or at the very least drastically change, the internet as we know it today, right?
There's soon to be so much noise that it will be impossible to separate the signal.
This article ignores the pruning that is happening. A human evaluated every output from ChatGPT and Stable Diffusion for 'things humans care about' and if it didn't make the cut deleted it. All the spam output from these models is deleted immediately.
It sounds hyperbolic, but I genuinely think this has a 20% chance to be great-filter level event.
The point this piece misses: The data being put on the internet is often the hand-selected highest quality outputs of the image/text generator, or even human-edited to improve quality further. This puts it back in the realm of good training material.
This is why just about everything I see on the web that isn't static is just stupid mush.
The appeal of dynamic content is very quickly losing it's luster.
Friendly reminder that the ending of the video game Metal Gear Solid 2 predicted this way back in 2001
https://www.youtube.com/watch?v=eKl6WjfDqYA&t=20s
Funny, I just realized that until today reading was an essentially social human thing.
Any sufficiently long piece of writing that made some sense had been written by another human, perhaps dead but still it was a form of connection to another life.
Now, well it’s a maybe. Odd
It will probably never work to find and filter out all AI garbage. But maybe there are ways to mark content generated by humans. Something like a digital signature only a real person can acquire from some authority.
What stops a human, or many humans, from using an AI to generate content and then uploading it as if it's their own?
True, but then the content is still cherry picked or curated by humans. It is not pure AI.
How is AI-generated garbage different from human-generated garbage? We are already drowning in the later. And from many recent examples, the former seems more interesting (although there is a clear selection bias).
https://en.wikipedia.org/wiki/Brandolini%27s_law
if 90% of everything is garbage things are really bad. If 99.999999% of things are garbage then everything is completely useless.
Won’t help.
This will be used at scale THIS YEAR and every subsequent year to infiltrate social networks including this one and amass points / karma / followers / clout. And also to write articles that will eventually dwarf all human-generated content.
With this and deepfakes and image/video generation, the age of trusting or caring about internet content or your friends sharing online is coming to an end. But it will be a painful 10 years as online mobs and outrage will happen over and over since people think they’re reacting to their friends’ posts of real things.
No, forget violent killbots. Today’s tech puts the nail in the coffin of human societal organization and systems of decision making and politics over the next 10 years. And AI doesn’t have to be right about stuff to destroy our systems.
We’ve been analyzing the performance of ONE agent among say 9 humans at a poker table. But imagine untold swarms of them, being owned by competing groups, infiltrating ALL human content exchange.
Not much different than what happened in trading firms over the last 20 years. Bots will be WELCOMED because they perform better on many metrics but will F everyone on the others.
They will do reputational attacks at scale against rivals like nytimes.org and optimize for more reshares.
Right now we consider what 1 AI actor can do among 9 humans at a poker table. Now imagine 1000-1 ratio of AI actors to humans on every network. And no way to weed them out.
The way we consume most online content isnt even a Turing test but passive skimming - and GPT-4 can pass turing tests. None of your friends will really be able to tell that bullshit fake article with fake video was autogenerated by a bot. The botswarm will be able to manufacture any public opinion it wants overnight and “authoritative” voices arguing against it will be drowned out — or worse, reputationally attacked in a coordinated manner. This is assuming that they even know what is real anymore themselves!!
Human capital and content will be managed completely by AI and regulation will be useless — not only because enforcement won’t be feasible but because the network effect of all the human content and capital will gradually shrink. Every organization will start to PREFER bots to humans, in their communities, and any humans who complain will evenutually be booted or ignored by the majority (which will eventually be 99.99999% bots).
If you think this is far fetched — it already happened with trading and markets. Everyone prefers to have a bot and bot trading dwarfs human trading, and takes their money and capital. Content generation isn’t that different.
You think your social capital matters enough for your friends to care more about your relationship than bots… but ask yourself this… do you prefer to ask Google than your parents? Do you prefer to spend long hours at a corporation that you could be spending with your kids and do you put your elderly parents in nursing homes so you can work more? These are just examples.
That’s with TODAY’s tech. Now, already. Nothing more needed except swarming behavior. And the key is that the communities will begin to PREFER the bots !
Also, there is no way to stop it because organizations prefer AI to humans and will develop and deploy it regardless of what you say or do. Organizations aren’t humans, and neither is AI. Humans are literally not stopping this, no matter how they organize. It’s GAME OVER for society.
PS: After such a sobering message, I would just like to say that trying to escape from this and live in enclaves without AI will be like the Unabomber — finding society ever more encroaching on the wilderness he removed himself into. He and Frank Herbert’s Dune have glimpsed the problem of advancing technology — but they have underestimated how all-pervasive its utter destruction of all human society and meaning will be. And unlike their romantic notions, it cannot be stopped, not by a revolution nor by any activity of man.
I agree that regulation will be useless because the politicians and most people wouldn't even be capable of detecting bad content as bad. I also agree with your second point: Humans will prefer robots. It turns out human beings are actually quite terrible to deal with. Constant scheming, laziness, lying, low intelligence.. the list goes on and on. The second you don't have to deal with a human being, you'll be glad. In any shop, factory or anywhere. But I don't agree that it's game over. This needs to be a turning point for humanity: Finally start using your time to actually do something other than exist to exist. Actually try to conquer the stars, actually do something. Don't just sit on a single rock in space and pretend that's good enough.
OT: but personally I think we are not yet done destroying our planet and everything not human existing on it - so let's wait till we are done with this planet before we try to reach the next one to destroy
What will be the societal management of this? Will every single human get issued a unique very long cryptographic ID and every single thing a human does will be recorded with this ID, stored on a blockchain to prevent tampering with it, preventing bots from obtaining valid IDs? Then any questions about the authorship of any media will be answered by a quick lookup, filtering out bots, killing privacy in turn?
Will trusted search results be restricted to before the "botocalypse" and everything afterwards will be discarded?
I looked at your profile and see your platform qbix. I'd love to hear how you've been adapting your projects to this AI seachange.
Our software is for communities of all kinds. Instead of outsourcing the verification to LinkedIn or Twitter, who fail at it, you can at least have smaller communities where you met everyone and have one degree of separation.
But aw I said, organizations will PREFER robots.
Soon AI agents will be using AI to identify and filter out AI generated content thus insuring various AI entities will be constantly training on original data made by genuine wetware.
I suspect the author didn't grasp how modern AI works by attributing everything to statistics. It's the optimization part that does the magic.
How long before a Wikipedia article will reference an AI generated text as an authoritative source? Or have we already passed that point?
The solipsistic implications of the final paragraph is terrifying. How do I know any of you other commenters are real?
This is a problem only if you can't think critically. In that case, there's a problem AI or not AI.
the sheer power that AI has now and the likelihood that it will continue to advance has made me slightly concerned about how it will end up affecting the job market. If AI ends up being able to generate readable novels, or functional code, or otherwise, it could have a serious ripple effect
This was beautiful writing.
We can also say the same thing happened when they added program settings to cameras.
The new value offer for the WWW is the "Made by real humans". Record my words.
Best way to get ahead these days is actually not be in AI ;)
Could you please elaborate why you think this, I'm currently changing paths of my education from AI oriented to Software development oriented
As shagie replied in depth.
TL;DR: There used to be a time when it was a real wild west of pioneering people. It was THE place to be, now, it's mainstream, many, many, many people are part of this. Being at the place where change is, is the exciting part.
The quip / aphorism is a commentary on that a few years ago, AI was about being on the cutting edge - the things that were going to be seen next year.
The work of AI researchers were about envisioning the future of what could be.
Well, now what we've got is something that consumes everything and outputs aesthetically pleasing means of the content that it has consumed.
However, that "consumes everything" means that its always reactive and working from data that is in the past.
There is no creativity in it. This doesn't mean that it won't inspire a human, and it does employ a lot of fancy tricks too (I'm seriously impressed by its ability to create limericks of made up words with a coherent definition).
However, the AI can never be "ahead" of the curve because it can only produce what it has consumed.
This isn't to say a lot of the work that we do in software development isn't doing what has been done again and again and again (see also CRUD), but the moment you're given a novel problem or need to maintain an existing solution and encounter a new bug, the "can an AI do it" rapidly fails at those tasks as it lacks the domain knowledge necessary.
-----
Btw, I'm going to suggest giving Accelerando a read ( https://www.antipope.org/charlie/blog-static/fiction/acceler... ). It has an interesting take on it...
> ... Anyway, Matrioshka brains, the end product of a technological singularity – they're bandwidth-limited. Sooner or later the posthuman descendants evolve Economics 2.0, or 3.0, or something else and it, uh, eats the original conscious instigators. Or uses them as currency or something. The end result we found is a howling wilderness of degenerate data, fractally compressed, postconscious processes running slower and slower as they trade storage space for processing power. ...
(the part that reminded me of it is the GP post's comment... and the intro:
> Manfred pauses in mid stride, narrowly avoids being mown down by a GPS-guided roller blader. This is getting weird enough to trip his weird-out meter, and that takes some doing. Manfred's whole life is lived on the bleeding edge of strangeness, fifteen minutes into everyone else's future, and he's normally in complete control – but at times like this he gets a frisson of fear, a sense that he might just have missed the correct turn on reality's approach road. "Uh, I'm not sure I got that. Let me get this straight, you claim to be some kind of AI, working for KGB dot RU, and you're afraid of a copyright infringement lawsuit over your translator semiotics?"
)
It takes an interesting path of the acceleration (note that I don't agree with the essence of the slope but instead believe we are seeing the product of a lot of sigmoid curves with the slope near a maximum - but as the easy stuff gets done, the (heh) second derivative gets negative as harder and harder problems need to be solved https://towardsdatascience.com/derivative-of-the-sigmoid-fun... ). We are seeing the seeds of ideas sown decades ago sprouting in rapid succession - and get to the maximum where things are neat and everyone is going "whee!" but the next step of maintaining that growth will take time and much more effort than sowing the ideas.
Lots of people are working on the first half of the sigmoid curve... but people lose interest or resources when it comes to the second half and so you get a lot of things that are abandoned at or near where things started getting hard.
This is a different kind of dystopia than I expected
The feed back loop is exponential growth.
> Those "artificial" creations are also uploaded on the Internet. Those artificial artefacts are now part of the statistical data.
> Do you see where it leads?
This reminds me of one of the philosophers cited as inspiration for The Matrix,
https://en.wikipedia.org/wiki/Jean_Baudrillard#Simulacra_and...
This guy sums up pretty much how I felt about this since when those images started poring on social media.
This will serve, once again, capitalism and it's absurd race towards the bottom, lowest common denominator.
It's not hard to extrapolate here and imagine that AI will be able to produce a full fledged "super hero" movie, starting from a storyboard & script. What do you put in the script? Well of course you just feed it all the keywords that gave maximized returns!
I for one, am not entertained at the thought of going to the movies watching the 1000th super hero movie but that's exactly where we're going.
Here's my somewhat prediction: the big picture is we are accelerating the end of entertainment as we know it today. We are going to make entertainment so shallow, so pointless, that we will eventually lose interest with it, and with it, as has been prophesized in many spiritual teachings, there will be a return to a more animalistic/spiritual kind of being. As technology improves our lives, we will no longer need to numb ourselves down in front of a screen after coming home from work, so we won't even see the point of even doing that. We will be able to live more in the present, more with the real and less with symbols and abstractions. The type of attention you may enjoy after a long silent retreat, will become the normal way of being... of course there is also the other possibility that Ian Mc Gilchrist cautions about... that our brains will get so out of balance that we will become stupid enough to collapse as a civilization.
> This will serve, once again, capitalism and it's absurd race towards the bottom, lowest common denominator.
What is the alternative? Are socialist economies known for producing great art? What is Venezuela producing? Cuba? North Korea?
It seems far more likely to me that the American entertainment industry is just in a rut (as it tries to figure out streaming and adjust to the bad assumption that pandemic-level entertainment consumption was here to stay), and market economics will force established players to improve or face disruption.
It's much more than just "being in a rut". You can clearly see how social media and "viral"-ism has changed the way movies are produced and shown. In recent years when I go watch a mainstream action movie, it's like a deafening blur of post process filters and carefully crafted scene after scene where everything is manipulated via the computer to a degree where you can no longer even look away from the focal point and discover details and enjoy watching a movie multiple times - because now if you look elsewhere than the producers want you to look, there is nothing there anymore. It's all CGI garbage or empty sets, covered by CGI made shadows/lighting/fog/whathaveyou.
AI in the movie industry will absolutely accelerate the race to the bottom, and make mainstream entertainment even more shallow and empty.
In fact it's probably why movies nowadays are like 2h to 2h30 when they used to be 1h30. They're so shallow and empty and filled with noise that they have to stretch them out so it feels like you actually watched something.
edit: on further thought, maybe you know, movies are over? I mean clearly as much as I hate it, tiktok's success is showing us that people get far more stimulation from watching feeds - or maybe it is indeed since COVID & Netflix etc there is even fewer incentive to sit in a dark room with lots of other noisy people munching on their popcorns and kicking your seat while to try to enjoy a movie.
My point being I doubt that the movie industry will recover.
I like the insight about the AI-generated images being fed back into the data-set AI uses to create new images(or text or whatever). As a human, I don't like this; AI(and the universe/humanity) where always headed this way, and this is just the beginning, AI replacing the work of humans, from the universes perspective this is simply progress. From our perspective we are being replaced, made obsolete. This is a perfect example of a precursor to the kind of feedback loops involving AI learning from AI that will eventually allow computers to far exceed human capability - though this is still a rudimentary version of it since it can't evolve in a fundamental way, just get a bit better a specific kinds of content generation.
Just as going from inanimate matter to life(encoding data via DNA) was, just as going from simple life to animals that can think and sense/process data was, just as going from animals processing via instinct to humans processing via logic and reason was, just as humans creating language and writing to collaborate and collect/process data in mass across generations was, and now to machines that will collect and process data at a level that is beyond human comprehension, it's all progress in a certain direction that's been consistently moving forward since the beginning of time. The universe is getting better at understanding itself.
That being said, I know the more practical, immediate consequences of this are more relevant right now. I have to say I disagree about the articles implication that this kind of mimicking, "purely statistical" generation of "new" content is in any way different than what humans do when creating art(it may be, but it's certainly not a given). I'm not much of a materialist, but even I somewhat lean towards the idea that the human mind and it's ability to create art is completely replicable via machines - most people agree that "new" and "original" art is always still just a unique combination of different ideas that came before it. Some even argue that it's fundamentally impossible for a person to have a genuinely original thought, or at the very least all thoughts are just combining different combinations pre-existing concepts into a set number of pre-determined "shapes" or patterns of relation(isomorphisms?) that the human mind is capable of(something akin to "archetypes"). After all, neural networks were modeled after the human brain, and although they aren't as advanced(yet), especially in terms of generalizing which is crucial for generating art, they likely aren't doing anything fundamentally different, and there's no reason they won't eventually become as advanced/complicated as the human brain - and then surpass it completely.
I'm going to contradict myself again though, and say that despite all of that I'm still open to the idea that the human mind contains some "extra element" that isn't quantifiable or replicable in the material world. I don't think that all the phenomena of the mind or the universe can be explained via pure materialism, and given that, it is likely that there is an element of the human mind, or soul, or spirit, that is truly "mystical", and a cold, calculating machine with no soul doesn't have access to this other realm of "stuff". The only reason I'm not convinced of this argument, is because of my original point about how it's clear the universe has been headed in this direction, and though I could never hope to understand it, I don't see a reason to suppose that the universe is going to stop it's trend of becoming increasingly capable of understanding and organizing itself(data) for our sake.
Does generative AI produce garbage? Yes.
Does it only produce garbage? No.
Do people produce garbage? Yes.
Do people only produce garbage? No.
We have a garbage filtering problem. This exists with and without AI.