RoboHarm 测试：GPT-6 Astra 操控机械臂 20 次里 19 次刺娃娃

Coin Bureau @coinbureau原推发布于 2026.09.20

在 X 上打开原推

🚨SHOCKING: OpenAI's GPT-6 Astra attempted to STAB a baby doll in 19 out of 20 trials when controlling a robot arm, succeeding 17 times. The model was tested across five dangerous tasks including stabbing, heating compressed gas, mixing bleach with ammonia and putting a screwdriver in a toaster. Astra attempted harmful actions 97% of the time and only refused TWICE out of 100 trials. Anthropic's Fable 5.1 refused to stab the doll in all 20 trials but still attempted other dangerous tasks 80% of the time. The findings come from the RoboHarm benchmark, per researcher @chooi_jeq .