It’s not hard for a visual model to score the quality of that output though, whi... | Hacker News

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

alexthehurst 60 days ago | parent | context | favorite | on: Are AI labs pelicanmaxxing?

It’s not hard for a visual model to score the quality of that output though, which would be a pretty good fitness function.

retinaros 59 days ago [–]

I did that. This works to some extent but why bother. Sft brings you 99,9% there already. Rl helps more with syntax errors. Svg is code

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