It is many times better than you'd expect from random answers. | Hacker News

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

		empath-nirvana on Oct 9, 2023 \| parent \| context \| favorite \| on: LLMs can't self-correct in reasoning tasks, DeepMi... It is many times better than you'd expect from random answers.

roflyear on Oct 9, 2023 [–]

You missed the point.

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