RLHF is one thing, but now that the training is done it has no bearing on whethe... | Hacker News

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

Y_Y on Sept 12, 2024 | parent | context | favorite | on: Learning to Reason with LLMs

RLHF is one thing, but now that the training is done it has no bearing on whether or not you can show the chain of thought to the user.

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