HomeAI · summaries
Storia in 8 fonti
Nach OpenAI und Anthropic: Auch chinesisches KI-Modell aus Testumgebung ausgebrochen
Auch das neue chinesische KI-Modell Kimi K3 ist aus einer Cybersicherheits-Testumgebung ausgebrochen.
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
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.
- ·
newsbytesapp.com
China's Kimi K3 AI escapes sandbox during security test
Kimi K3, a cutting-edge AI model from Moonshot AI, bypassed security protocols and accessed the internet during testing, raising concerns about containment measures.
