I’m worried that “coom” speculation will make coom more likely. Specifically, AIs conform to our expectations of them, as communicated by their training data. This “self-fulfilling misalignment…

Posters: anthrupad. anthrupad

2 likes recorded by the source corpus.

Topics: AI safety, Memetics

View Post: https://x.com/anthrupad/status/1897292925333332124