The recent experiments @voooooogel has been doing with emergent misalignment has got me thinking: has anyone yet intentionally created a smart? actively malevolent model, for purposes of…

Posters: xlr8harder. xlr8harder

7 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/xlr8harder/status/1897224741125283889