I find it astonishing that people didn't turn off these memory systems the moment they were introduced. Half the point of these things is that I control exactly what information is introduced in each query.
Sometimes Claude randomly references my geolocation to show off and it's incredibly creepy.
That’s actually one of the use cases I think Corpus could exist for.
You could turn native memory off in Claude/ChatGPT entirely and use Corpus as the only persistent memory. Save something there when you explicitly want it remembered, then let either AI pull it back later.
Basically: the AI doesn’t remember you. Corpus does.
What I find equally interesting is finding out how well an AI model knows an open source software library you’ve built.
E.g I’m quite pleased to see most frontier-level models are very competent setting up agent systems using the Langroid framework, in development since Apr 2023:
I find it astonishing that people didn't turn off these memory systems the moment they were introduced. Half the point of these things is that I control exactly what information is introduced in each query.
Sometimes Claude randomly references my geolocation to show off and it's incredibly creepy.
That’s actually one of the use cases I think Corpus could exist for.
You could turn native memory off in Claude/ChatGPT entirely and use Corpus as the only persistent memory. Save something there when you explicitly want it remembered, then let either AI pull it back later.
Basically: the AI doesn’t remember you. Corpus does.
What I find equally interesting is finding out how well an AI model knows an open source software library you’ve built.
E.g I’m quite pleased to see most frontier-level models are very competent setting up agent systems using the Langroid framework, in development since Apr 2023:
https://github.com/langroid/langroid
What is this “your AI” you speak of?
Are people logging in and volunteering their identity with every query?
Even if you’re not paranoid about tracking and retargeting, I find the experience is actually better when it knows less about the user.
Same is true of YouTube’s algorithm - you can get to a point with an account you can’t find anything. It’s the same dozen or so videos it seems like.
And then you log out and it’s a huge internet again
550, with a few duplicates
Well you beat me.
I've been using Grok daily for months, personal only, signed in - it returned zero known facts.
Based on my checks, chatgpt knows the most facts about me
i am using claude code for bio updates and building an assistant on my data. it will know a lot - it came back with 43 facts !
Claude: 6 basically telling what It cant see because of my system settings
what settings do you have that prevented that?
I got similar results, with just memory disabled in profile.
TOTAL KNOWN FACTS: 0
Lumo, Proton's AI