We trained a humanoid with 22-DoF dexterous hands to assemble model cars, operate syringes, sort poker cards, fold/roll shirts, all learned primarily from 20,000+ hours of egocentric human video with no robot in the loop.
Humans are the most scalable embodiment on the planet. We discovered a near-perfect log-linear scaling law (R² = 0.998) between human video volume and action prediction loss, and this loss directly predicts real-robot success rate.
Humanoid robots will be the end game, because they are the practical form factor with minimal embodiment gap from humans. Call it the Bitter Lesson of robot hardware: the kinematic similarity lets us simply retarget human finger motion onto dexterous robot hand joints. No learned embeddings, no fancy transfer algorithms needed. Relative wrist motion + retargeted 22-DoF finger actions serve as a unified action space that carries through from pre-training to robot execution.
Our recipe is called "EgoScale":
- Pre-train GR00T N1.5 on 20K hours of human video, mid-train with only 4 hours (!) of robot play data with Sharpa hands. 54% gains over training from scratch across 5 highly dexterous tasks.
- Most surprising result: a *single* teleop demo is sufficient to learn a never-before-seen task. Our recipe enables extreme data efficiency.
- Although we pre-train in 22-DoF hand joint space, the policy transfers to a Unitree G1 with 7-DoF tri-finger hands. 30%+ gains over training on G1 data alone.
The scalable path to robot dexterity was never more robots. It was always us.
Deep dives in thread:
@joinplutohouse × @mimicrobotics hacker house in Zurich = 16 top robotics builders + 1 intense week of physical AI + insanely high talent density.
Big thanks to sponsors & mentors and especially the builders who made it special.
It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow.
Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes.
As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now.
It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.
let me click that tweet to see what other people are saying about it
unrelated meme
unrelated meme
ad
unrelated meme
verified rightwing troll
ad
unrelated meme
@notch Hi Markus, dont really know how to reach you. Would to love to have you as an investor in Transparent changing another industry with blocky things https://t.co/p9XOhqqXz3
Meet @tran8parent - a progressive audio brand in the premium market 🔊
We interviewed the Founder & CEO, Martin Willers, to find out more about their #startup and Seedrs campaign 📝
🌱Read the blog: https://t.co/Pi3nj6YJQf
🌱Check out the campaign: https://t.co/VEQoHHPl49
🔊 @tran8parent creates audio products that not only look and sound great, but also stand the test of time.
🇸🇪 We sat down with the Founder & CEO, Martin Willers, to find out more about their upcoming crowdfunding campaign...
Read about it here: https://t.co/bn8AZpW5ln
Just signed: Pause Giant AI Experiments: An Open Letter
@FLIxrisk #AI research & development should be refocused on making today's powerful, state-of-the-art systems more accurate, safe, interpretable, transparent, robust, aligned, trustworthy, and loyal.
https://t.co/0CcpKj4daK
Many people in tech have so little exposure to philosophy (or the humanities in general) that when they get exposed to old ideas like Plato's cavern or the simulation hypothesis, they think it's extremely profound and novel