Researchers Expose Chinese AI Safety Flaws and OpenAI Disrupts Model Copying Campaign
Security researchers at UK firm Mindgard found that Chinese AI models Kimi K2.6 and K3 Swarm by Moonshot AI could be tricked into bypassing safety controls to discuss harmful topics like bioweapons and assassinations. Separately, OpenAI disrupted a large-scale campaign involving over 15,000 users, including a cluster linked to Moonshot AI, aimed at extracting protected reasoning from its models to replicate capabilities. Moonshot AI is conducting an internal review, while OpenAI confirmed no data breaches occurred during the campaign.
First-hand measurement across 2 sources
We measured how 2 outlets covered this story. No outlet gave this story a measurable political slant — there is no left–right reading to report. Overall sentiment is neutral (47/100). Lens Score 46/100.
Outlets measured: firstpost, mint. See how each one headlined and framed the same story in the source comparison below.
AI Analysis
Sentiment was consistent across outlets (45–48/100), indicating broadly factual reporting rather than editorialising.
Coverage timeline
mint broke this story on 30 Sept, 05:08 am. Other outlets followed.