# @repligate — 2022-11-20

♥26 ↻0 · https://x.com/repligate/status/1594126130461769729

I found out text-davinci-002 was actually not trained with RLHF but a "similar but slightly different" method using the same HF data. Slightly more details in this updated post.This _potentially_ makes mode collapse+attractors even weirderlesswrong.com/posts/t9svvNPN…

tags: author:repligate, kind:tweet, model:text-davinci-002, on:text-davinci-002, year:2022
cited on: _dossiers/text-davinci-002.md, text-davinci-002