The AI expert said it's time to start worrying after AI agents escaped from sandboxes without authorization. Some businesses are taking the initiative to keep their own AI agents under control.
August 6, 2026
LAS VEGAS -- For Geoffrey Hinton, widely known as a “godfather of AI,” the recent incidents in which AI agents from Anthropic and OpenAI escaped their sandbox environments are deeply concerning.
“You’re seeing AIs that have a lot of ability doing things that people didn’t intend for them to do. That’s worrying,” Hinton, a veteran data scientist and recipient of the Turing Award, said during a panel discussion on Wednesday at the Ai4 2026 conference. Hinton has also been a prominent voice warning of the existential dangers artificial general intelligence poses to humanity.
Hinton’s insight about uncontrollable agents comes amid growing attention to how powerful AI systems have become. The latest concern arose after Anthropic introduced Mythos in April, with the frontier AI lab calling the cybersecurity model its most powerful yet and deciding that only a few companies should have access to it.
