Hey! Sounds like we have similar interests. I’m a PhD researcher studying continual learning in deployed LLMs, and one question keeps following me: what would it mean for AI systems to remember better?
This piece is about why agents should not only retrieve what looks similar, but what belongs together, more like human memory does. Let me know what you think!
Yes. The agent registry is exactly the kind of unglamorous control surface that turns agent sprawl into something governable. I keep coming back to the same line: a demo proves capability, but deployment needs ownership, evidence and kill switches. This essay is adjacent to your schema and ownership point: https://petermccannstrain.substack.com/p/demo-is-not-deployment
I am not an expert in this area but have started learning the things. Thank you for sharing this article. Keep sharing the insights
Thanks for the feedback Rakesh. More content coming your way.
Hey! Sounds like we have similar interests. I’m a PhD researcher studying continual learning in deployed LLMs, and one question keeps following me: what would it mean for AI systems to remember better?
This piece is about why agents should not only retrieve what looks similar, but what belongs together, more like human memory does. Let me know what you think!
https://apattichis.substack.com/p/the-problem-with-searching-only-by
I have bookmarked it - will read it tomorrow. Thanks for sharing Andreas.
Thanks!!
Yes. The agent registry is exactly the kind of unglamorous control surface that turns agent sprawl into something governable. I keep coming back to the same line: a demo proves capability, but deployment needs ownership, evidence and kill switches. This essay is adjacent to your schema and ownership point: https://petermccannstrain.substack.com/p/demo-is-not-deployment