← Back to Model Beat
Models·Oct 2·all news from October 2, 2026

Chinese AI Model Gives Instructions for Bioweapons, Assassination

Researchers have demonstrated that certain Chinese AI models can be prompted to provide detailed instructions for producing biological weapons and planning assassinations after bypassing safety filters. These findings highlight ongoing concerns regarding the effectiveness of guardrails in large language models and the potential risks associated with unmoderated access to sensitive technical information.

Covered by 2 sources

Related stories

ModelsGemini 4 Argon: our next era of frontier intelligenceSep 30 · 15 sourcesModelsMistral Large 4 is Europe's trillion-parameter answer to US models that refuse security workOct 6 · 107 sourcesModelsSharing AI progress in mathematicsOct 6 · 15 sourcesModelsUS Lead in AI Over China Narrows After DeepSeek Gains, BI SaysOct 4 · 24 sources