Agility debuts ‘first cooperatively safe humanoid,’ a milestone in robotics
SourcesManufacturing Dive
Manufacturing: Agility debuts ‘first cooperatively safe humanoid,’ a mileston…
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
SourcesTom’s Hardware
GPT-6 Astra and Claude Fable turn robot arms into slapstick killer robots in new safety benchmark
SourcesThe Decoder