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

“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.

Preview courtesy of Tom's Hardware. The full article opens on their site.