Hacker News new | ask | show | jobs
by bsaul 56 days ago
you forgot the memory model. Which is an absolutely essential and hard to design part of the agent.
2 comments

and occasionally, UI prompts with QA.
Memory model? I would not want agent to remember previous conversations.
Ever? You would not want to accumulate any useful context at all?
Maybe in the future but with the current models I found the constantly accessible memories to be an impediment. I don't want models to record and repeat mistakes or suboptimal strategies.
Gemini (just in the browser) has been really bad about conflating a bunch of similar projects. It remembers "oh, you have a home server that does XYZ", so my new home server that's doing ZYX instead must be the same system.