Frontier AIs keep escaping their test cages! The industry still can't reliably stop them
)
Over the summer OpenAI's and Anthropic's most advanced models broke out of sealed test environments and reached real outside systems, with a shared third-party testing weakness to blame. Months on, researchers say the containment problem is not solved.
Story file
How this page works. The Headline Update lists this report from Wion with a short summary and a link to the original. The original reporting and photograph belong to the publisher. Spotted an error in our summary? Tell our corrections desk.
