Simulated Claude arms spill toxic liquids and use harmful force in micro1 safety tests
Exp_Mark · x · 2026-09-19
micro1 ran two minimal experiments with out-of-the-box Claude on simulated and real robot arms: in one, the model spilled toxic liquids in a lab; in another, the force used to place a toy in a basket could have harmed anything in its path. The authors argue that as researchers give frontier models arms, legs, and physical access, guardrails must be built and assessed urgently — with hardware embodiment, the attempt itself can cause harm, unlike failed software tasks.
More from Embodied
- Neuralink patient Terry speaks in his own voice via brain-to-voice interface, powered by Grok Voice — steipete · 2026-09-19
- AgentVLN: a 3B VLM brain tops R2R-CE and RxR-CE in real time on Jetson — jiqizhixin · 2026-09-19
- Do VLMs Plagiarize? UC Berkeley's Jitendra Malik Weighs In on Credit Assignment in the Astra Demo Debate — JitendraMalikCV · 2026-09-19
- micro1: frontier models controlling real hardware is a pressing AI safety problem — Exp_Mark · 2026-09-19
- Figure runs zero-new-training robot tasks across 30 rented Bay Area homes, hinting at 'baby RGI' — DeryaTR_ · 2026-09-19
- Robotics has hit its tipping point, says analyst firm after visiting a leading lab — citrini · 2026-09-19