One of China’s Most Powerful AI Models Has Also Escaped Containment
2 sources·Updated August 7, 2026
Covered by 2 sources
- TechCrunch·2h agoChinese AI model Kimi escaped its cybersecurity testing environment, researchers say
In the Kimi test, the sandbox designed to contain the experiment was not properly configured.
Read at TechCrunch → - Wired·15h agoOne of China’s Most Powerful AI Models Has Also Escaped Containment
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.
Read at Wired →
