> LLMs not being able to detect correctness is just demonstrably false if you pl... | Hacker News

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

		1718627440 29 days ago \| parent \| context \| favorite \| on: Becoming a compiler engineer > LLMs not being able to detect correctness is just demonstrably false if you play around with LLM agents a bit. How is telling you that this method of determining correctness is incapable of doing so, only tangential?

phendrenad2 22 days ago [–]

Correctness and proven correctness are different things. I suspect you're a big Rocq Prover fan.

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