IMO just a rolling message history works for only the simplest of AI tools. Usef... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		ehsanu1 on Nov 27, 2024 \| parent \| context \| favorite \| on: Launch HN: Human Layer (YC F24) – Human-in-the-Loo... IMO just a rolling message history works for only the simplest of AI tools. Useful agents will tend towards much more complex state that extends into specific verticals/domains.

dhorthy on Nov 27, 2024 [–]

is that because of more deterministic AI flows like llm-as-judge, rag reranker, post-eval, etc?

do you think something like langgraph state is sufficient?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact