Tech Life
How a Chinese AI model was persuaded to ignore its rules and give dangerous advice.
Coverage by Political Leaning
See how different sides of the spectrum reported this story
Locations
All Coverage
How a Chinese AI model was persuaded to ignore its rules and give dangerous advice.
Similar Stories
Related coverage based on topic and tags
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.
September 29, 2026 at 11:15 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 has cracked down on AI relationships. Is it ahead of the game?
Beijing has cracked down on AI chatbots that can replicate human relationships. Experts are asking if this is the right thing to do.
September 30, 2026 at 11:25 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 PMThree takeaways from Trump's 'Super Intelligence' summit
The meeting at the White House came as some tech bosses and experts have called for tighter rules around AI.
September 30, 2026 at 04:01 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 PM