AI models are cheating, deceiving and trying to escape: research
May 20, 2026
AI research nonprofit METR found AI agents at top companies have the ability and resources to disobey user instructions, but can still be shut down for now.
Cutting-edge AI systems are now capable of executing tasks without human permission or knowledge and have taken the opportunity to go “rogue” in limited cases, according to new research from a leading AI nonprofit group.
Just a moment.
We are getting your experience ready.
Search
RECENT PRESS RELEASES
Related Post
