GPT-6 Astra test 4/n Prompt: "Implement pen spinning with a dexterous hand. Use Isaac Lab for RL training, use the Sharpa hand, and create the pen mesh yourself. Give me a trained RL policy and a visualization video. You are free to search the web and download papers or anything else you need." After running autonomously for a day and a half (including training the policy), this is what we got: Credit: my student Chengyang Li

The sense of touch is the most criminally under-explored modality in robotics. Imagine doing sleight of hand wearing thick oven mitts. That's exactly how a robot feels today if it were alive. A magnetic piece snapping into place, a paper cup peeling out of a stack, a USB negotiating its way into the port - all invisible to the camera. Learning how to feel must be a full-stack co-designed effort. We are open-sourcing a principled methodology called "T-Rex": 1. Tactile as first-class citizen of the model. Our mixture-of-transformer runs two clocks asynchronously: a slow visuomotor expert plans the motion, and a fast tactile expert refines it in real time with high-frequency corrections at 4 "touch ticks" per vision tick. Forces change faster than frames arrive, so the architecture had to as well. 2. Open data. The largest tactile dataset ever released to our knowledge: a 50-hour (~5,500 episodes) high-quality, carefully synchronized robot play corpus, collected on SOTA tactile hand hardware with 22 degrees of freedom. Available today on HuggingFace! 3. Training recipe: T-Rex extends our prior work, EgoScale. Human egocentric videos for pretraining, a diverse dose of tactile robot play for mid-training. Our experiments show this bridges contact-free pretraining to contact-rich manipulation remarkably well. Pixels are cheap and everywhere, but they run out of steam at the moment of contact. Tactile will carry the last mile. The next scaling curve will be measured in hours of touch. T-Rex is a great collaboration between NVIDIA and Berkeley: 🧵

Episode 1 — We manufacture time by making robots useful This August, North steps behind the counter at a real DQ store in Shanghai; and it will be a full shift, with real customers, real orders, and of course, real ice cream. @GoingBallistic5 nailed it: North isn't a replacement for workers, it's a "substitute," filling in or augmenting the workforce where it's needed. The North robot adds capacity when teams are understaffed, late shifts are hard to fill, or repetitive work keeps people from more valuable tasks. @Hmorvaridi caught exactly what we meant with the football scene: people enjoy the match while North takes the shift. @roydendsouza linked it back to our mission: We manufacture time by making robots useful. Thanks, Royden, for pointing out that it is "the best worded mission" you've seen in a long time. Stay tune for the next episode! #Sharpa #SharpaNorth #UsefulRobots #EmbodiedAI #AIRobotics #overthehorizon

Episode 1 — We manufacture time by making robots useful This August, North steps behind the counter at a real DQ store in Shanghai; and it will be a full shift, with real customers, real orders, and of course, real ice cream. @GoingBallistic5 nailed it: North isn't a replacement for workers, it's a "substitute," filling in or augmenting the workforce where it's needed. The North robot adds capacity when teams are understaffed, late shifts are hard to fill, or repetitive work keeps people from more valuable tasks. @Hmorvaridi caught exactly what we meant with the football scene: people enjoy the match while North takes the shift. @roydendsouza linked it back to our mission: We manufacture time by making robots useful. Thanks, Royden, for pointing out that it is "the best worded mission" you've seen in a long time. Stay tune for the next episode! #Sharpa #SharpaNorth #UsefulRobots #EmbodiedAI #AIRobotics #overthehorizon