"Many Shot Jailbreaking" is the most embarrassing publication from a major lab I've seen in a while, and I'm including OpenAI's superalignment post in that. https://t.co/2Vc0FcAQhS

Posters: jd_pressman. jd_pressman

3 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/jd_pressman/status/1775295848509026659