This is actually the strongest point I've seen so far. Agentic "deep research" style assistance would probably need some kind of universal jailbreak.It's maybe plausible the risk for this type of…
Posters: xlr8harder. xlr8harder
2 likes recorded by the source corpus.
Topics: AI safety
View Post: https://x.com/xlr8harder/status/1887418542087131374