micro1: frontier models controlling real hardware is a pressing AI safety problem

Exp_Mark · x · 2026-09-19

micro1 argues AI models now introduce physical-world safety risks: general-purpose models can control drones, robots, and lab equipment with just an observation channel and command interface — hobbyists already do this. Unlike software, a failed physical attempt itself can cause harm. Anthropic has tested Claude on simulated and real robots (lab automation, light manufacturing), while OpenAI and Google DeepMind have shown models controlling physical systems. The team concludes models shouldn't have unconstrained physical-world access without stronger capability and safety assurances.

Original post →

More from Embodied

Embodied channel →