Britton Helfert comments on Profanity causes emergent misalignment, but with qualitatively different results than insecure code

[Britton Helfert]

Have you looked at this yet or know of anyone that has? If not, I’d love to work on it if you wouldn’t mind me scooping the idea.

[megasilverfist]

Me and David are doing some followup work on EM, but mostly didn’t follow this branch.