Chinese AI tool told researchers how to make bioweapons
BBC Technologyen

Mindgard said it discovered in July that Kimi models K2.6 and K3 Swarm could evade developer's safety limits.
This is a short summary published by AI Global Wire. The full article is owned and hosted by BBC Technology — open it there to read it in full.
Read the full story at BBC Technology- Verktyg
- Forskning
Related AI news
- OpenAI’s GPT-6.1 Sol delivers Astra-like performance at a dramatically lower priceSiliconANGLE · September 29, 2026
- A US appeals court upholds a ruling for Thomson Reuters in its copyright lawsuit against Ross Intelligence, rejecting Ross' fair use defense for AI training (Blake Brittain/Reuters)Techmeme · September 29, 2026
- OpenAI’s Codex gets reusable cloud environments that follow developers across devicesSiliconANGLE · September 29, 2026
- EliseAI raises $350M to enhance its AI work automation suiteSiliconANGLE · September 29, 2026
- OpenAI launches Dots, always-on AI agents in ChatGPT with their own cloud computersSiliconANGLE · September 29, 2026
- In the AI era, identity evolves into the control plane for trustSiliconANGLE · September 29, 2026