GPT-6 Turns Two Raw Videos Into Real Robot Dexterous Rollouts, From Rubik's Cube to Egocentric Hands
TheMoonMidas · x · 2026-09-10
Developer Lingxiao234 probed GPT-6's limits on robot dexterity by feeding it just two videos — no states, no actions — and asking it to do real2sim plus physical retargeting to Wuji dexterous hands. The model produced successful physical rollouts, including manipulating a Rubik's cube and transferring from egocentric human video, showcasing video-grounded visual-physical reasoning without manual annotation.
More from Embodied
- Robot learning researcher joins Mila to work on physical AI and RL — pcastr · 2026-10-27
- Full teardown: inside Zmotor's 32mm linear actuator for humanoids — MarwaEldiwiny · 2026-10-27
- Full Teardown of a Zmotor Linear Actuator Used in China's Humanoid Robots — MarwaEldiwiny · 2026-10-27
- World Model Assigns Weight and Friction to Objects, Then Simulates with a Physics Engine — jonstephens85 · 2026-10-27
- First unboxing shots of Apple's foldable "iPhone Duo" surface — chrisfirst · 2026-10-27
- Bedrock Robotics Raises $600M Series C as Autonomous Excavators Do Paid Work on US Job Sites — davidpattersonx · 2026-10-27