On the pointlessness of "aligning" chat models to censor information I was able to get the llama 3 70B instruct model to give me direct instructions on manufacturing meth with 3 simple steps. It's…

Posters: xlr8harder. xlr8harder

3 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/xlr8harder/status/1782002789797040448