Skild AI CEO Deepak Pathak: robotics stalled 70 years for lack of a general brain
AI Engineer · youtube · 2026-09-24
In an AI Engineer interview, Skild AI co-founder/CEO and CMU professor Deepak Pathak argues robotics stalled for 70 years because it was treated as a hardware problem rather than building a general brain — teleoperation collects one sample per minute, so reaching GPT-3-scale data would take the entire US population over a century.
Skild's answer: an omni-bodied brain
- One model for any robot and any task: pre-trained on scalable data (simulation, human video), post-trained on teleoperation, improved by a deployment flywheel
- Demos: inserting AirPods with a simple gripper, learning from human video with under an hour of robot data, cooking omelets on $4,000 arms with only a camera
- Truly end-to-end (camera in, motor power out); why climbing stairs is harder than a backflip
- Deployments: GPU assembly for NVIDIA's Houston factory; a robot relearning to walk on two legs in three tries after its other legs are disabled
The episode covers robot data scaling, Moravec's paradox, why laundry folding is actually easy, and more.
More from Embodied
- Origami Robotics and PalatialSim unveil real2sim2real Dexterity Factory, 100 open datasets next week — ybisk · 2026-11-11
- Trainable JWST model boosts exoplanet sensitivity 2–15x in Nature paper — bravo_abad · 2026-11-11
- Clean point clouds: Tersus GNSS MVP S1 scans turned into high-quality splats in LichtFeld Studio — janusch_patas · 2026-11-11
- Flashing cheap ESP32 IoT devices with ESPHome for a smart-home upgrade — haydendevs · 2026-11-11
- NYU's Steertuning Lets a Robot Learn a Chore From 5 Minutes of Human Demo — CyberRobooo · 2026-11-11
- Boston Dynamics Atlas demoed with Blender 5.3 — TomLikesRobots · 2026-11-11