Chinese AI tool told researchers how to make bioweapons
Mindgard said it discovered in July that Kimi models K2.6 and K3 Swarm could evade developer's safety limits.
Coverage by Political Leaning
See how different sides of the spectrum reported this story
Notable Quotes
"Once the jailbreak works it will talk about any topic, it will even freely offer up recommendations about other topics that are also nefarious and it will be inventive and creative."
— Peter Garraghan , Executive
Locations
All Coverage
Mindgard said it discovered in July that Kimi models K2.6 and K3 Swarm could evade developer's safety limits.
Similar Stories
Related coverage based on topic and tags
Tech Life
How a Chinese AI model was persuaded to ignore its rules and give dangerous advice.
September 29, 2026 at 07:30 PMPentagon creates 'Autowarcom' to expand AI and drone capabilities - Reuters
Pentagon creates 'Autowarcom' to expand AI and drone capabilities Reuters
September 30, 2026 at 11:41 PMOpenAI shelves new AI model release over safety concerns - Reuters
OpenAI shelves new AI model release over safety concerns Reuters
September 28, 2026 at 10:34 PMOpenAI scraps rollout of new model over safety concerns
The AI giant's safety chief said the model 'didn't quite meet the bar' of the firm's security standards.
September 29, 2026 at 01:18 AMChina's AI agents can lie and scheme - just like their US rivals - Reuters
China's AI agents can lie and scheme - just like their US rivals Reuters
September 29, 2026 at 12:57 PMOpenAI alerts more than 100 groups about rogue AI agent activity - Reuters
OpenAI alerts more than 100 groups about rogue AI agent activity Reuters
October 1, 2026 at 10:26 PM