I thought reinforcement learning with human feedback was meant to get that quant... | Hacker News

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

djeastm 3 months ago | parent | context | favorite | on: Why AI Sucks at Front End

I thought reinforcement learning with human feedback was meant to get that quantification of "taste"

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