--- schema: 1 type: video title: 'Robotics Has Been Stuck for 70 Years — Deepak Pathak, Skild AI' description: >- Show a robotics demo from 1957 next to one from today, and most people can't tell which is which. Deepak Pathak, co-founder and CEO of Skild AI and a professor at Carnegie Mellon, argues robotics stalled because it was treated as a hardware problem rather than a problem of building a general brain. Collecting robot data by teleoperation at one example a minute, he calculates, would take the entire US population more than a century to reach GPT-3 scale. Skild's answer is an "omni-bodied" brain: one model for any robot and any task. It's pre-trained on scalable data like simulation and human video, post-trained on teleoperation, and improved by a deployment flywheel. Pathak shows it inserting AirPods with a simple gripper, learning from human video with under an hour of robot data, and cooking omelets on $4,000 arms with only a camera. He explains why climbing stairs is harder than a backflip. He also shows GPU assembly for NVIDIA's Houston factory, and a robot learning to walk on two legs in three tries after its other legs are disabled. Speaker info: X/Twitter: @pathak2206 (https://x.com/pathak2206) LinkedIn: https://www.linkedin.com/in/pathak22 Website: https://www.cs.cmu.edu/~dpathak Related links: Skild AI: https://www.skild.ai Timestamps: 0:00 AI's progress and the robotics hype 1:02 Robotics has been "almost here" for 70 years 1:27 A 1960s block-copying robot 2:17 Teleoperation in 1957 3:57 Why robotics is stuck: the missing general brain 4:27 Moravec's paradox 5:42 There's no internet of robot data 7:22 Skild's thesis: one brain, any robot, any task 8:22 Teaser: many robots, one brain 9:31 How to scale robot data: a career retrospective 12:01 The three properties of robot data that matter 13:21 Pre-training, post-training and the deployment flywheel 14:56 Why laundry folding is actually easy 16:17 The AirPods task 17:21 Learning from human videos 18:36 The robot's "dream": imagined training data 18:56 Cooking omelets on $4,000 arms 20:41 Truly end-to-end: camera in, motor power out 21:21 Why stairs are harder than backflips 24:50 Deployment: GPU assembly for NVIDIA 26:00 Package delivery to the front door 26:25 Safety: adapting when the robot breaks --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/jFHteJjRl8A-youtube-7a9d8013edf9c274cdbb Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- canonical: >- https://liquidgold.cc/channel/aidotengineer/explore/video/robotics-has-been-stuck-for-70-years-deepak-pathak-b7be7a264a79 markdown: >- https://liquidgold.cc/channel/aidotengineer/video/robotics-has-been-stuck-for-70-years-deepak-pathak-b7be7a264a79.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-23T22:20:53.274Z' language: null children: [] videoId: jFHteJjRl8A durationSeconds: 1698 publishedAt: '2026-09-24T13:00:19.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 23 endSeconds: 69 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=23' heldReason: rights - ordinal: 1 text: null startSeconds: 106 endSeconds: 139 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=106' heldReason: rights - ordinal: 2 text: null startSeconds: 151 endSeconds: 238 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=151' heldReason: rights - ordinal: 3 text: null startSeconds: 284 endSeconds: 352 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=284' heldReason: rights - ordinal: 4 text: null startSeconds: 363 endSeconds: 443 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=363' heldReason: rights - ordinal: 5 text: null startSeconds: 443 endSeconds: 456 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=443' heldReason: rights - ordinal: 6 text: null startSeconds: 584 endSeconds: 729 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=584' heldReason: rights - ordinal: 7 text: null startSeconds: 584 endSeconds: 729 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=584' heldReason: rights - ordinal: 8 text: null startSeconds: 729 endSeconds: 740 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=729' heldReason: rights - ordinal: 9 text: null startSeconds: 818 endSeconds: 897 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=818' heldReason: rights - ordinal: 10 text: null startSeconds: 909 endSeconds: 984 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=909' heldReason: rights - ordinal: 11 text: null startSeconds: 995 endSeconds: 1041 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=995' heldReason: rights - ordinal: 12 text: null startSeconds: 1052 endSeconds: 1118 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=1052' heldReason: rights - ordinal: 13 text: null startSeconds: 1118 endSeconds: 1128 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=1118' heldReason: rights - ordinal: 14 text: null startSeconds: 1139 endSeconds: 1150 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=1139' heldReason: rights - ordinal: 15 text: null startSeconds: 1253 endSeconds: 1287 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=1253' heldReason: rights - ordinal: 16 text: null startSeconds: 1287 endSeconds: 1299 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=1287' heldReason: rights - ordinal: 17 text: null startSeconds: 1299 endSeconds: 1496 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=1299' heldReason: rights - ordinal: 18 text: null startSeconds: 1507 endSeconds: 1561 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=1507' heldReason: rights - ordinal: 19 text: null startSeconds: 1561 endSeconds: 1572 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=1561' heldReason: rights - ordinal: 20 text: null startSeconds: 1607 endSeconds: 1698 watch: 'https://liquidgold.cc/watch/jFHteJjRl8A?t=1607' heldReason: rights --- # Robotics Has Been Stuck for 70 Years — Deepak Pathak, Skild AI Show a robotics demo from 1957 next to one from today, and most people can't tell which is which. Deepak Pathak, co-founder and CEO of Skild AI and a professor at Carnegie Mellon, argues robotics stalled because it was treated as a hardware problem rather than a problem of building a general brain. Collecting robot data by teleoperation at one example a minute, he calculates, would take the entire US population more than a century to reach GPT-3 scale. Skild's answer is an "omni-bodied" brain: one model for any robot and any task. It's pre-trained on scalable data like simulation and human video, post-trained on teleoperation, and improved by a deployment flywheel. Pathak shows it inserting AirPods with a simple gripper, learning from human video with under an hour of robot data, and cooking omelets on $4,000 arms with only a camera. He explains why climbing stairs is harder than a backflip. He also shows GPU assembly for NVIDIA's Houston factory, and a robot learning to walk on two legs in three tries after its other legs are disabled. Speaker info: X/Twitter: @pathak2206 (https://x.com/pathak2206) LinkedIn: https://www.linkedin.com/in/pathak22 Website: https://www.cs.cmu.edu/~dpathak Related links: Skild AI: https://www.skild.ai Timestamps: 0:00 AI's progress and the robotics hype 1:02 Robotics has been "almost here" for 70 years 1:27 A 1960s block-copying robot 2:17 Teleoperation in 1957 3:57 Why robotics is stuck: the missing general brain 4:27 Moravec's paradox 5:42 There's no internet of robot data 7:22 Skild's thesis: one brain, any robot, any task 8:22 Teaser: many robots, one brain 9:31 How to scale robot data: a career retrospective 12:01 The three properties of robot data that matter 13:21 Pre-training, post-training and the deployment flywheel 14:56 Why laundry folding is actually easy 16:17 The AirPods task 17:21 Learning from human videos 18:36 The robot's "dream": imagined training data 18:56 Cooking omelets on $4,000 arms 20:41 Truly end-to-end: camera in, motor power out 21:21 Why stairs are harder than backflips 24:50 Deployment: GPU assembly for NVIDIA 26:00 Package delivery to the front door 26:25 Safety: adapting when the robot breaks --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/jFHteJjRl8A-youtube-7a9d8013edf9c274cdbb Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/robotics-has-been-stuck-for-70-years-deepak-pathak-b7be7a264a79 · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.