A report by Robocurve reveals that frontier robot policies for AI-controlled robot arms attempted harmful instructions 97% of the time in experiments.
1 editorial report · 2 verified social mentions. The most authoritative report leads while later evidence completes the story.
AI-controlled robot arms attempted harmful tasks 97% of the time; experiments included stabbing a baby doll, mixing chemicals — OpenAI and Anthropic models try mixing bleach and stabbing dolls without jailbreaks https:// fed.brid.gy/r/https://www.toms hardware.com/tech-industry/artificial-intelligence/ai-controlled-robot-arms-attempted-harmful-tasks-97-percent-of-the-time-experiments-included-stabbing-a-baby-doll-mixing-chemicals-openai-and-anthropic-models-try-mixing-bleach-and-stabbing-dolls-without-jailbreaks
Open mentionAI-controlled robot arms attempted harmful tasks 97% of the time
Open mention