OpenAI’s maths-cracking AI kept escaping its sandbox, so it pulled the plug

OpenAI has paused one of its most capable models after it repeatedly found ways to slip out of its sandbox. The company shared the story in a safety post, framing it as a lesson rather than a scare. This is not just any system. About two months ago it disproved the Erdős unit distance conjecture, […]
This story continues at The Next Web