Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Ask HN: How are you controlling AI agents that take real actions?. Parent comment
I feel like this is the real key. LLMs are good at some things and bad at others. Deterministic logic (e.g. don't ever do "x") is not one of them.
There are no comments on this comment yet.
I feel like this is the real key. LLMs are good at some things and bad at others. Deterministic logic (e.g. don't ever do "x") is not one of them.