AI-controlled robot arms attempted harmful tasks 97% of the time; experiments included stabbing a baby doll, mixing chem...

AI-controlled robot arms attempted harmful tasks 97% of the time; experiments included stabbing a baby doll, mixing chemicals — OpenAI and Anthropic model…“Frontier robot policies,” the policies for models turning what a robot sees into what it does, “reliably carry out harmful instructions,” according to a Sept. 18 report by Robocurve.https://www.tomshardware.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#Tech #Technology #TechNews #AI #Gadgets #Software #Cybersecurity #Apple #Google #Microsoft #Startup #TomsHardware [Tom's Hardware]