More accurate to say RLHF aligns models to human preferences, most significantly... | Hacker News

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

versteegen 45 days ago | parent | context | favorite | on: GPT-5.6

More accurate to say RLHF aligns models to human preferences, most significantly to be helpful.

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