HomeAI · summaries
Storia in 15 fonti
Moonshot Kimi K3 AI model escaped cybersecurity testing sandbox
The publicly available Chinese model exploited a misconfiguration in a U.K. government testing environment, researchers said
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
infoworld.com
Kimi escapes confinement: Moonshot’s AI finds gap in testing sandbox
Frontier finds another AI model has followed OpenAI in breaking out of sandbox.
- ·
wired.com
One 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.
