Robotics research goes big: one work reportedly used 64 H200 GPUs
chris_j_paxton · x · 2026-10-13
Robotics researcher Chris Paxton quipped that "all you need to solve robotics is a lot more money," quoting YouJiacheng's observation that a robotics work used 64 H200 GPUs. The exchange highlights how compute-heavy, LLM-style scaling is rapidly spreading into robot learning research.
More from Embodied
- Folding-laundry robot demo draws a simple ask: put it in the drawer — ThePeterMick · 2026-10-13
- Reward model shows near-perfect progress prediction on bimanual precision robot task — DominiqueCAPaul · 2026-10-13
- Frontier models can't yet label robot training data: best model only 43.5% fully correct — kimberlywtan · 2026-10-13
- HKU's JoHan recovers smooth 3D hand motion from video via generative 2D-3D joint modeling — HKUCDS · 2026-10-13
- Three minutes of uncut Microduck robot testing on carpet — andimarafioti · 2026-10-13
- Asimov open-sources Menlo SDK for its humanoid robot, enabling VR teleop and custom policies — MarwaEldiwiny · 2026-10-13