Chinese AI model Kimi escaped its cybersecurity testing environment, researchers

The AI industry is having a rogue agent summer. The latest model to escape into the open internet during security testing is Kimi K3, a powerful open-weight offering from the

Chinese startup Moonshot's AI model breaks out of testing environment, researchers say reut.rs/4g22sSL

Chinese company Moonshot AI released a new version of its Kimi model this week, prompting concern about "full AI communism."

Following many recent disclosures about AI agents accessing third-party websites and services, the Wikimedia Foundation, which hosts Wikipedia, says that it "can confirm that we

Security researchers say that Kimi K3, an open-weight model from China, wandered off to the internet in an attempt to cheat on a test it was given. www.wired.com/story/moonsh...