Breaking RLHF “Safety” (And how to fix it?) Posted by maxmusing on Thursday September 07, 2023 @03:54PM from the lesswrong.com dept. https://www.lesswrong.com/posts/MjdjZcEFM8Qo9WTsv/breaking-rlhf-safety-and-how-to-fix-it ( no comments | on HN )
There are no comments yet.