It seems most memory systems are built ETL style, when they'd be better off ELT style. As the core memory systems and LLMs improve, you'd be better off querying from raw source information rather than whatever consolidation of that information was deemed appropriate at the time. That is, just store it all compressed, then build (or rebuild) the memories as new information enters or as architecture evolves
Agent Memory: An Anatomy
21–25 of 25 posts
Re: Agent Memory: An Anatomy
#22 multimodal models with environmental grounding may eventually have an analog [of affect]. text-only agents can’t.
Re: Agent Memory: An Anatomy
#23multimodal models with environmental grounding may eventually have an analog [of affect]. text-only agents can’t. I'd be curious to hear an explanation about why text can't. Or equivalently, why multimodal could.
[flagged]
Re: Agent Memory: An Anatomy
#24[flagged]
Re: Agent Memory: An Anatomy
#25[dead]