Hacker News new | ask | show | jobs
by chrisjj 115 days ago
> we chose them to understand intent

Yet they don't understand the intent of "Never do X" ?

1 comments

Understanding intent and following instructions are different failure modes. LLMs are good at the first, unreliable at the second. That's exactly why enforcement lives outside the LLM.
Software engineering has a word for that.

Kludge.

Good luck!