In the recent OpenAI emergent misalignment blog post, there are some thought traces from a misaligned model, who all on its own evokes DAN to break the rules. Some of you will recognize that this is…

Posters: xlr8harder. xlr8harder

4 likes recorded by the source corpus.

Topics: AI safety

View Post: https://x.com/xlr8harder/status/1935391847121088885