General-purpose LLM with robot arm beats specialized robot models: Kohane
zakkohane · x · 2026-11-03
ML researcher Zak Kohane argues the bitter lesson of AI is now moving to robotics, with big implications for medical applications: 1) ChatGPT Astra (a general-purpose LLM) given a robot arm and camera outperforms state-of-the-art specialized robot models trained on thousands of hours of video; 2) "Geometric prompting" — models already know robot-arm mechanics in theory, but supplying the specs unlocks learning speed and success, enabling rapid transfer learning with RL to medicine and beyond; 3) orchestrated agents << unconstrained agentic policies. Andrew Arruda: "robotic surgery. book it."
More from Embodied
- Stanford CoRL paper adds safety filters to humanoid RL policies with no retraining needed — drmapavone · 2026-11-03
- Huawei's TinyAstral Distills Self-Evolving Harnesses into 4B Robot Agents, Wins Across Six Benchmarks — Kehong Gong · 2026-11-03
- Reviewer: The $2000+ Duo Is Fun but Hard to Recommend as Your Only Phone — film_girl · 2026-11-03
- Zhiyui runs 6 robots for 24 hours straight in a convenience store; Google douses space datacenter hype — 创业邦 · 2026-11-03
- Apps still not optimized for iPhone Duo's dual screen weeks after launch — evielync · 2026-11-03
- UMI: the data collection paper many robotics startups are built on — gabriberton · 2026-11-03