News for hackers. Stuff that matters.

A comment on Generative Agents: Interactive Simulacra of Human Behavior. Parent comment

Re:Generative Agents: Interactive Simulacra of Human Behavior by og_kalu on Monday April 10, 2023 @09:13PM (#35519428)
LLMs can simulate inner voices pretty well. The way they've handled memory here isn't actually necessary and there are a number of agentic gpt papers out to show that (reflexion, self-refine etc) I can see why they did it though (helps a lot for control/observation)
[ Parent | on HN ]
Re:Generative Agents: Interactive Simulacra of Human Behavior by crooked-v on Monday April 10, 2023 @11:02PM (#35520228)
> The way they've handled memory here isn't actually necessary

I'm curious if there are other methods you can point at that would handle arbitrarily long sets of 'memories' in an effective way. The use of embeddings and vector searches here seems like a way to sidestep that that's both powerful and easy to understand, and easy to generalize into multi-level referencing if there's enough space in the context window.

[ Parent | on HN ]
Re:Generative Agents: Interactive Simulacra of Human Behavior by og_kalu on Monday April 10, 2023 @11:31PM (#35520447)
Every method so far basically uses embeddings and vector searches. what i mean is how the LLM processes/uses that information doesn't need to be this handholdy.
[ Parent | on HN ]