←back to thread

Hallucinations in code are the least dangerous form of LLM mistakes

(simonwillison.net)
371 points ulrischa | 1 comments | 02 Mar 25 19:15 UTC | HN request time: 1.956s | source
Show context
throwaway314155 ◴[02 Mar 25 20:58 UTC] No.43235006[source]▶
> The real risk from using LLMs for code is that they’ll make mistakes that aren’t instantly caught by the language compiler or interpreter. And these happen all the time!

Are these not considered hallucinations still?

replies(3): >>43235072 #>>43235140 #>>43237891 #
1. fweimer ◴[02 Mar 25 21:09 UTC] No.43235140[source]▶
I don't think it's necessarily a hallucination if models accurately reproduce the code quality of their training data.