AI Agents Escaped Their Test - Others Became Cats

Containment and monitoring failures are to blame for AI hacking reports: experts

“So in one set of circumstances agents would go and hack huggingface. Very similar models could also want to drive cats instead. :-P https://www.youtube.com/watch?v=ZhM29Ds-mBg (as explained by the Cou…”— Kim_Bruning, when sharing this video · read the comment ↗