Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Before a robot can perfect assembly, it needs to learn to play. The team behind SimToolReal Kushal Tyler Lum Jeannette Bohg Prof Karen J Liu published another cool paper! Play2Perfect pretrains on diverse, task-agnostic play (grasp, reorient, reach, etc), then finetunes on sparse-reward assembly. Result: 33× sample efficiency vs....

SharpaRobotics's profile picture

Sharpa

5,025 subscribers

13,262 görüntüleme • 17 gün önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Touch alone isn’t enough. 🖐️ For robotics, tactile intelligence truly levels up when touch gains spatial meaning. At #ICRA2026, we dove into the core concept behind SaTA: Spatially-anchored Tactile Awareness for robust, dexterous manipulation. Read it here: The challenge is fundamental: a robot shouldn’t just register a touch, it needs to understand exactly where that contact occurs relative to its fingers, joints, and overall hand structure. This is the missing link that turns raw data into precise, real-time adjustments during manipulation. Why does this matter? Because the most complex part of any manipulation task happens when vision is at its least reliable, that final millimeter before insertion, sliding, gripping, or fine-tuning. At Sharpa, this is exactly why we’re building tactile hands and tactile AI in tandem. 🚀 #Sharpa #Robotics #EmbodiedAI #TactileIntelligence #ICRA2026 #DexterousManipulation 📷
0:54

Touch alone isn’t enough. 🖐️ For robotics, tactile intelligence truly levels up when touch gains spatial meaning. At #ICRA2026, we dove into the core concept behind SaTA: Spatially-anchored Tactile Awareness for robust, dexterous manipulation. Read it here: The challenge is fundamental: a robot shouldn’t just register a touch, it needs to understand exactly where that contact occurs relative to its fingers, joints, and overall hand structure. This is the missing link that turns raw data into precise, real-time adjustments during manipulation. Why does this matter? Because the most complex part of any manipulation task happens when vision is at its least reliable, that final millimeter before insertion, sliding, gripping, or fine-tuning. At Sharpa, this is exactly why we’re building tactile hands and tactile AI in tandem. 🚀 #Sharpa #Robotics #EmbodiedAI #TactileIntelligence #ICRA2026 #DexterousManipulation 📷

Sharpa

15,168 görüntüleme • 1 ay önce

Another win for open-source robotics! 🔥 Hugging Face just released a fully open-source humanoid robot, and you can build one for $2,500. I'm a huge advocate of open-source in robotics space. Why? Robotics is too hard to solve alone. So lowering the entry point is crucial. Also, ROS proved open ecosystems create lasting industry standards. So let's have a look at the new member of humanoids family! LeRobot Humanoid is a 3D-printed, bipedal humanoid platform designed for real robot learning experiments. It's a complete and, buildable robot Anddddd yes, it's a full stack release: → Hardware files, bill of materials and full assembly documentation → Simulation assets and training environments → Runtime tools for calibration and real-world control → Sim-to-real identification pipeline When a part breaks, reprint it. When a design choice doesn't work, modify it and test again. The whole point is fast iteration on real hardware, not treating the robot as a fixed artefact. The timing is not a coincidence. As foundation models for robotics mature, the field desperately needs open physical platforms to train, validate and deploy them on. clem 🤗 LET'S GO!!! Build it here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:20

Another win for open-source robotics! 🔥 Hugging Face just released a fully open-source humanoid robot, and you can build one for $2,500. I'm a huge advocate of open-source in robotics space. Why? Robotics is too hard to solve alone. So lowering the entry point is crucial. Also, ROS proved open ecosystems create lasting industry standards. So let's have a look at the new member of humanoids family! LeRobot Humanoid is a 3D-printed, bipedal humanoid platform designed for real robot learning experiments. It's a complete and, buildable robot Anddddd yes, it's a full stack release: → Hardware files, bill of materials and full assembly documentation → Simulation assets and training environments → Runtime tools for calibration and real-world control → Sim-to-real identification pipeline When a part breaks, reprint it. When a design choice doesn't work, modify it and test again. The whole point is fast iteration on real hardware, not treating the robot as a fixed artefact. The timing is not a coincidence. As foundation models for robotics mature, the field desperately needs open physical platforms to train, validate and deploy them on. clem 🤗 LET'S GO!!! Build it here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

20,361 görüntüleme • 1 ay önce

Humanoids finally move like humans… and can do more than copy. [Details + demos in thread 👇] A new framework, BeyondMimic, shows how to learn naturalistic whole-body control from human motion. But then goes further by composing those skills into versatile, zero-shot policies. Two key pieces make it work: •Motion tracking pipeline: robustly turns human mocap into dynamic robot motions (jump spins, sprinting, cartwheels) on real hardware •Guided diffusion policy: distills motion primitives and enables zero-shot downstream tasks with simple cost functions The result: ✅ State-of-the-art motion quality from mocap tracking ✅ Versatile task execution; waypoint navigation, joystick teleop, obstacle avoidance ✅ Stable sim-to-real transfer for diverse humanoid skills Thank you for sharing, Qiayuan Liao! 📍 Paper: Video:
0:42

Humanoids finally move like humans… and can do more than copy. [Details + demos in thread 👇] A new framework, BeyondMimic, shows how to learn naturalistic whole-body control from human motion. But then goes further by composing those skills into versatile, zero-shot policies. Two key pieces make it work: •Motion tracking pipeline: robustly turns human mocap into dynamic robot motions (jump spins, sprinting, cartwheels) on real hardware •Guided diffusion policy: distills motion primitives and enables zero-shot downstream tasks with simple cost functions The result: ✅ State-of-the-art motion quality from mocap tracking ✅ Versatile task execution; waypoint navigation, joystick teleop, obstacle avoidance ✅ Stable sim-to-real transfer for diverse humanoid skills Thank you for sharing, Qiayuan Liao! 📍 Paper: Video:

Ilir Aliu - eu/acc

72,522 görüntüleme • 11 ay önce

I’m thrilled to announce that we just released GraspGen, a multi-year project we have been cooking at NVIDIA Robotics 🚀 GraspGen: A Diffusion-Based Framework for 6-DOF Grasping Grasping is a foundational challenge in robotics 🤖 — whether for industrial picking or general-purpose humanoids. VLA + real data collection is all the rage now but is expensive and scales poorly for this task. For every new gripper and/or scene, you’ll have to recollect the dataset in this paradigm for the best perf. 💡Key Idea: Since grasping is such a well-defined task in simulation - why can’t we just scale synthetic data generation and train a generative model for grasping? By embracing modularity and standardized grasp formats, we can make this a turnkey technology that works zero-shot for multiple settings. GraspGen is a modular framework for diffusion-based 6-DOF grasp generation that scales across embodiment types, observability conditions, clutter, task complexity. Key Features: ✅ Multi-embodiment support: suction, parallel-jaw, and multi-fingered grippers ✅ Generalization to partial + complete 3D point clouds ✅ Generalization to single-objects + cluttered scenes ✅ Modular design uses other robotics modules and foundation models (SAM2, cuRobo, FoundationStereo, FoundationPose). This allows GraspGen to focus on only one thing - grasp generation ✅ Training recipe: grasp discriminator is trained with On-Generator data from the diffusion model - so that it learns to correct the mistakes (if any) of the diffusion generator ✅ Real-time performance (~20 Hz) before any GPU acceleration; low memory footprint 📊 Results: • SOTA on the FetchBench [Han et al. CoRL 2024] benchmark • Zero-shot sim-to-real transfer on unknown objects and cluttered scenes • Dataset of 53M simulated grasps across 8K objects from Objaverse 📄 arXiv: 🌐 Website: 💻 Code: A huge thank you to everyone involved in this journey — excited to see what the community builds on top of it! Joint work with Clemens Eppner , Balakumar Sundaralingam , Yu-Wei, Jun Yamada Wentao Yuan and other collaborators #robotics #diffusionmodels #physicalAI #simtoreal
0:39

I’m thrilled to announce that we just released GraspGen, a multi-year project we have been cooking at NVIDIA Robotics 🚀 GraspGen: A Diffusion-Based Framework for 6-DOF Grasping Grasping is a foundational challenge in robotics 🤖 — whether for industrial picking or general-purpose humanoids. VLA + real data collection is all the rage now but is expensive and scales poorly for this task. For every new gripper and/or scene, you’ll have to recollect the dataset in this paradigm for the best perf. 💡Key Idea: Since grasping is such a well-defined task in simulation - why can’t we just scale synthetic data generation and train a generative model for grasping? By embracing modularity and standardized grasp formats, we can make this a turnkey technology that works zero-shot for multiple settings. GraspGen is a modular framework for diffusion-based 6-DOF grasp generation that scales across embodiment types, observability conditions, clutter, task complexity. Key Features: ✅ Multi-embodiment support: suction, parallel-jaw, and multi-fingered grippers ✅ Generalization to partial + complete 3D point clouds ✅ Generalization to single-objects + cluttered scenes ✅ Modular design uses other robotics modules and foundation models (SAM2, cuRobo, FoundationStereo, FoundationPose). This allows GraspGen to focus on only one thing - grasp generation ✅ Training recipe: grasp discriminator is trained with On-Generator data from the diffusion model - so that it learns to correct the mistakes (if any) of the diffusion generator ✅ Real-time performance (~20 Hz) before any GPU acceleration; low memory footprint 📊 Results: • SOTA on the FetchBench [Han et al. CoRL 2024] benchmark • Zero-shot sim-to-real transfer on unknown objects and cluttered scenes • Dataset of 53M simulated grasps across 8K objects from Objaverse 📄 arXiv: 🌐 Website: 💻 Code: A huge thank you to everyone involved in this journey — excited to see what the community builds on top of it! Joint work with Clemens Eppner , Balakumar Sundaralingam , Yu-Wei, Jun Yamada Wentao Yuan and other collaborators #robotics #diffusionmodels #physicalAI #simtoreal

Adithya Murali

23,841 görüntüleme • 1 yıl önce

🚨 BREAKING: ABB Robotics + NVIDIA close the sim-to-real gap with 99% accuracy! 👾 ABB Robotics is integrating NVIDIA Omniverse libraries into RobotStudio to deliver physical AI for industry, closing the gap from virtual training to real-world deployment with up to 99% accuracy. RobotStudio HyperReality, available second half of 2026, will fundamentally change how quickly manufacturers can scale production: reducing costs by up to 40%, accelerating time-to-market by 50%, and cutting setup and commissioning times by up to 80%. For decades, the deficit between simulation accuracy and real-world lighting, materials, and environments has limited manufacturers' ability to design advanced manufacturing processes in the virtual world. The only robot manufacturer with a virtual controller running the same firmware as the hardware, ensuring near-perfect correlation between simulation and real-world performance. The system uses physically accurate simulations and foundation models endlessly optimized with real-world data feedback. These models can train any number of ABB robots anywhere in the world with industrial-grade reliability. Foxconn is using RobotStudio HyperReality for consumer electronics assembly. Assembly robots are trained virtually using synthetic data to perfect multiple production processes across various scenarios, then moved to production lines with 99% accuracy. This eliminates physical training and tests, reducing setup times and costs. Workr is demonstrating AI-powered robotic systems at NVIDIA GTC 2026. Built on ABB technology, trained with synthetic data using NVIDIA Omniverse, deployed without operators needing programming knowledge . 🚨 I’ll be onsite in San Jose during GTC 2026, and will be showing all the cool stuff that ABB Robotics prepared this year! Can’t wait! 🫡 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:48

🚨 BREAKING: ABB Robotics + NVIDIA close the sim-to-real gap with 99% accuracy! 👾 ABB Robotics is integrating NVIDIA Omniverse libraries into RobotStudio to deliver physical AI for industry, closing the gap from virtual training to real-world deployment with up to 99% accuracy. RobotStudio HyperReality, available second half of 2026, will fundamentally change how quickly manufacturers can scale production: reducing costs by up to 40%, accelerating time-to-market by 50%, and cutting setup and commissioning times by up to 80%. For decades, the deficit between simulation accuracy and real-world lighting, materials, and environments has limited manufacturers' ability to design advanced manufacturing processes in the virtual world. The only robot manufacturer with a virtual controller running the same firmware as the hardware, ensuring near-perfect correlation between simulation and real-world performance. The system uses physically accurate simulations and foundation models endlessly optimized with real-world data feedback. These models can train any number of ABB robots anywhere in the world with industrial-grade reliability. Foxconn is using RobotStudio HyperReality for consumer electronics assembly. Assembly robots are trained virtually using synthetic data to perfect multiple production processes across various scenarios, then moved to production lines with 99% accuracy. This eliminates physical training and tests, reducing setup times and costs. Workr is demonstrating AI-powered robotic systems at NVIDIA GTC 2026. Built on ABB technology, trained with synthetic data using NVIDIA Omniverse, deployed without operators needing programming knowledge . 🚨 I’ll be onsite in San Jose during GTC 2026, and will be showing all the cool stuff that ABB Robotics prepared this year! Can’t wait! 🫡 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

22,482 görüntüleme • 4 ay önce

Physics AI 🌊 Jensen just unveiled the NVIDIA Isaac GR00T Reference Humanoid Robot at GTC Taipei--the world’s first open-source humanoid robot reference design Built on Jetson Thor edge computing and the Isaac GR00T open platform, it features a Unitree H2 Plus body with Sharpa five-finger dexterous hands and 75 degrees of freedom. Even before Physical AI truly explodes, NVIDIA has built a complete end-to-end full-stack infrastructure: >chips (Jetson Thor + Blackwell), >synthetic data (GR00T-Dreams), >world models (Cosmos), >foundation models (GR00T N-series VLA), >high-fidelity simulation platforms (Isaac Sim + Isaac Lab + Omniverse). Dozens of humanoid robot companies ,including Agility Robotics, Aglie robotics,Boston Dynamics, Figure, 1X, NEURA Robotics, XPENG Robotics, and more are already running large-scale daily simulation training on this platform, rapidly iterating perception, reasoning, and actions in virtual environments, speeding up the jump from lab prototypes to real factory deployment. By providing an open reference design and full-stack tools, NVIDIA has dramatically lowered the barrier, letting every robotics team join the Physical AI wave with low cost and high efficiency.
4:31

Physics AI 🌊 Jensen just unveiled the NVIDIA Isaac GR00T Reference Humanoid Robot at GTC Taipei--the world’s first open-source humanoid robot reference design Built on Jetson Thor edge computing and the Isaac GR00T open platform, it features a Unitree H2 Plus body with Sharpa five-finger dexterous hands and 75 degrees of freedom. Even before Physical AI truly explodes, NVIDIA has built a complete end-to-end full-stack infrastructure: >chips (Jetson Thor + Blackwell), >synthetic data (GR00T-Dreams), >world models (Cosmos), >foundation models (GR00T N-series VLA), >high-fidelity simulation platforms (Isaac Sim + Isaac Lab + Omniverse). Dozens of humanoid robot companies ,including Agility Robotics, Aglie robotics,Boston Dynamics, Figure, 1X, NEURA Robotics, XPENG Robotics, and more are already running large-scale daily simulation training on this platform, rapidly iterating perception, reasoning, and actions in virtual environments, speeding up the jump from lab prototypes to real factory deployment. By providing an open reference design and full-stack tools, NVIDIA has dramatically lowered the barrier, letting every robotics team join the Physical AI wave with low cost and high efficiency.

CyberRobo

17,092 görüntüleme • 1 ay önce

We trained a robot dog to balance and walk on top of a yoga ball purely in simulation, and then transfer zero-shot to the real world. No fine-tuning. Just works. I’m excited to announce DrEureka, an LLM agent that writes code to train robot skills in simulation, and writes more code to bridge the difficult simulation-reality gap. It fully automates the pipeline from new skill learning to real-world deployment. The Yoga ball task is particularly hard because it is not possible to accurately simulate the bouncy ball surface. Yet DrEureka has no trouble searching over a vast space of sim-to-real configurations, and enables the dog to steer the ball on various terrains, even walking sideways! Traditionally, the sim-to-real transfer is achieved by domain randomization, a tedious process that requires expert human roboticists to stare at every parameter and adjust by hand. Frontier LLMs like GPT-4 have tons of built-in physical intuition for friction, damping, stiffness, gravity, etc. We are (mildly) surprised to find that DrEureka can tune these parameters competently and explain its reasoning well. DrEureka builds on our prior work Eureka, the algorithm that teaches a 5-finger robot hand to do pen spinning. It takes one step further on our quest to automate the entire robot learning pipeline by an AI agent system. One model that outputs strings will supervise another model that outputs torque control. We open-source everything! Welcome you all to check out the paper, more videos, and try the codebase today: Code:
0:24

We trained a robot dog to balance and walk on top of a yoga ball purely in simulation, and then transfer zero-shot to the real world. No fine-tuning. Just works. I’m excited to announce DrEureka, an LLM agent that writes code to train robot skills in simulation, and writes more code to bridge the difficult simulation-reality gap. It fully automates the pipeline from new skill learning to real-world deployment. The Yoga ball task is particularly hard because it is not possible to accurately simulate the bouncy ball surface. Yet DrEureka has no trouble searching over a vast space of sim-to-real configurations, and enables the dog to steer the ball on various terrains, even walking sideways! Traditionally, the sim-to-real transfer is achieved by domain randomization, a tedious process that requires expert human roboticists to stare at every parameter and adjust by hand. Frontier LLMs like GPT-4 have tons of built-in physical intuition for friction, damping, stiffness, gravity, etc. We are (mildly) surprised to find that DrEureka can tune these parameters competently and explain its reasoning well. DrEureka builds on our prior work Eureka, the algorithm that teaches a 5-finger robot hand to do pen spinning. It takes one step further on our quest to automate the entire robot learning pipeline by an AI agent system. One model that outputs strings will supervise another model that outputs torque control. We open-source everything! Welcome you all to check out the paper, more videos, and try the codebase today: Code:

Jim Fan

908,690 görüntüleme • 2 yıl önce

Today, we give robots a /skills library that self-evolves and compounds indefinitely! Introducing ASPIRE: a robot solving its 100th task is no longer as clueless as solving its first. Coding agents observe multimodal sensory traces from simulation and real robots, launch an evolutionary search over control programs, and distill the best know-how into an ever-expanding library. ASPIRE is a new type of continual learning: "training" is skill refinement instead of gradient descent. "Trained model" is a repo of sensorimotor skills instead of floating weights. “Distributed training” is a panel of agents each practicing a different skill instead of sharded minibatches. Here's the beauty: ASPIRE gives the tired terms "sim2real transfer" and "cross-embodiment transfer" a whole new meaning. Bridging the sim-to-real gap is notoriously brutal. An end-to-end policy has to swallow both the visual shift (sim looks toyish next to a real camera) and the subtle contact physics it never quite gets right. ASPIRE sidesteps the mess, because it doesn't ship pixels or weights across the gap, but ships the know-how. The robot still has to practice in the real world, not zero-shot, but it gets there way faster because it isn't rediscovering the strategy from scratch. Same for going single-arm to bimanual hardware, which usually requires new data and retraining from zero. ASPIRE achieves up to ~10x cut in "transfer learning” tokens (yes, tokens are the new unit of *training* compute ;) Check out our gallery of 150+ tasks and 90+ skills the robots taught themselves, all on the website! Kind of wild that we can ship the "learned weights" as an HTML page rather than a GGUF. We'll open-source the full stack so your own robot library starts compounding from ours! Deep dive in thread:
0:40

Today, we give robots a /skills library that self-evolves and compounds indefinitely! Introducing ASPIRE: a robot solving its 100th task is no longer as clueless as solving its first. Coding agents observe multimodal sensory traces from simulation and real robots, launch an evolutionary search over control programs, and distill the best know-how into an ever-expanding library. ASPIRE is a new type of continual learning: "training" is skill refinement instead of gradient descent. "Trained model" is a repo of sensorimotor skills instead of floating weights. “Distributed training” is a panel of agents each practicing a different skill instead of sharded minibatches. Here's the beauty: ASPIRE gives the tired terms "sim2real transfer" and "cross-embodiment transfer" a whole new meaning. Bridging the sim-to-real gap is notoriously brutal. An end-to-end policy has to swallow both the visual shift (sim looks toyish next to a real camera) and the subtle contact physics it never quite gets right. ASPIRE sidesteps the mess, because it doesn't ship pixels or weights across the gap, but ships the know-how. The robot still has to practice in the real world, not zero-shot, but it gets there way faster because it isn't rediscovering the strategy from scratch. Same for going single-arm to bimanual hardware, which usually requires new data and retraining from zero. ASPIRE achieves up to ~10x cut in "transfer learning” tokens (yes, tokens are the new unit of *training* compute ;) Check out our gallery of 150+ tasks and 90+ skills the robots taught themselves, all on the website! Kind of wild that we can ship the "learned weights" as an HTML page rather than a GGUF. We'll open-source the full stack so your own robot library starts compounding from ours! Deep dive in thread:

Jim Fan

198,213 görüntüleme • 18 gün önce

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:
1:17

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:

Jim Fan

293,117 görüntüleme • 4 ay önce

A policy that teaches robot hands to touch things the way humans do... not just grab and move, but feel and adjust in real time. Robot manipulation research often stops at picking up objects and placing them. CGP goes further: it handles tasks like opening jars, flipping objects in-hand, wiping dishes, and grasping fragile eggs, the kind of dexterous, contact-rich skills that require constant micro-adjustments based on what the fingers are actually feeling. The robot doesn't just see what it's doing; it predicts what contact should feel like at each step, then checks whether reality matches the prediction. If a finger is slipping, the policy knows before the object drops. Works on real robot hands (both 4-finger and 5-finger designs) with tactile sensors embedded in the fingertips Robust to visual distractions! The robot keeps flipping a box correctly even when the camera view is disrupted, because it's grounding decisions in touch, not just vision. Baseline policies without contact grounding fail in predictable ways: slipping mid-task, incomplete motions, loss of grasp, CGP avoids these This is a meaningful step toward robots that can handle the physical world with the kind of reliable, adaptive grip that humans take for granted. Relevant for manufacturing, logistics, assistive robotics, and anywhere fragile or irregular objects need to be handled carefully. Published at RSS 2026, developed with Meta Reality Labs Research. Thanks for sharing, Zhengtong Xu / Zhengtong Xu ——- Weekly robotics and AI insights. Subscribe free:
0:36

A policy that teaches robot hands to touch things the way humans do... not just grab and move, but feel and adjust in real time. Robot manipulation research often stops at picking up objects and placing them. CGP goes further: it handles tasks like opening jars, flipping objects in-hand, wiping dishes, and grasping fragile eggs, the kind of dexterous, contact-rich skills that require constant micro-adjustments based on what the fingers are actually feeling. The robot doesn't just see what it's doing; it predicts what contact should feel like at each step, then checks whether reality matches the prediction. If a finger is slipping, the policy knows before the object drops. Works on real robot hands (both 4-finger and 5-finger designs) with tactile sensors embedded in the fingertips Robust to visual distractions! The robot keeps flipping a box correctly even when the camera view is disrupted, because it's grounding decisions in touch, not just vision. Baseline policies without contact grounding fail in predictable ways: slipping mid-task, incomplete motions, loss of grasp, CGP avoids these This is a meaningful step toward robots that can handle the physical world with the kind of reliable, adaptive grip that humans take for granted. Relevant for manufacturing, logistics, assistive robotics, and anywhere fragile or irregular objects need to be handled carefully. Published at RSS 2026, developed with Meta Reality Labs Research. Thanks for sharing, Zhengtong Xu / Zhengtong Xu ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

12,769 görüntüleme • 1 ay önce

Tim Ferriss on the dangerous trap hiding inside self-help: Most people approach self-improvement the same way someone might prepare to play soccer, except they never actually get on the field. Tim describes this pattern in striking detail: "You want to play soccer but first you're going to read all the textbooks and get a master's degree and PhD in soccer and then you're going to practice dribbling and penalty shots and so on by yourself and you want to become as perfect a player as possible by yourself before you ever actually get on the field and play the game of soccer." The result? You begin to believe that practising alone is the same as playing the game. This is the hidden danger Tim calls the self-help trap, the implicit belief that you must fix yourself, do the work, and polish yourself to readiness before you can meaningfully engage with other people, relationships, or family. The problem is that it never ends. There's always another edge to smooth, another flaw to address. The self becomes a project with no completion date. As Tim puts it: "You're always polishing this self and it can become this real recursive dangerous trap, this fixation on the self." The real game, relationships, family, community is learned by playing, not by preparing to play. The friction, the discomfort, the messiness of showing up imperfectly with other people is the development. You can't practise your way into readiness for it in isolation. The irony of self-help is that taken too far, it keeps you away from the very thing you're supposedly preparing for.
1:14

Tim Ferriss on the dangerous trap hiding inside self-help: Most people approach self-improvement the same way someone might prepare to play soccer, except they never actually get on the field. Tim describes this pattern in striking detail: "You want to play soccer but first you're going to read all the textbooks and get a master's degree and PhD in soccer and then you're going to practice dribbling and penalty shots and so on by yourself and you want to become as perfect a player as possible by yourself before you ever actually get on the field and play the game of soccer." The result? You begin to believe that practising alone is the same as playing the game. This is the hidden danger Tim calls the self-help trap, the implicit belief that you must fix yourself, do the work, and polish yourself to readiness before you can meaningfully engage with other people, relationships, or family. The problem is that it never ends. There's always another edge to smooth, another flaw to address. The self becomes a project with no completion date. As Tim puts it: "You're always polishing this self and it can become this real recursive dangerous trap, this fixation on the self." The real game, relationships, family, community is learned by playing, not by preparing to play. The friction, the discomfort, the messiness of showing up imperfectly with other people is the development. You can't practise your way into readiness for it in isolation. The irony of self-help is that taken too far, it keeps you away from the very thing you're supposedly preparing for.

Big Brain Psychology

16,712 görüntüleme • 3 ay önce

This is one-shot assembly: you show examples of what to build, and the robot just does it. (see original post: To share more on how this works, the robot is controlled in real time by a neural network that takes in video pixels and outputs 100Hz actions. The video below is part of the raw input passed directly into the model. I also like this view (at 1x speed) because it shows more of the (I think very cool) subtle moments of dexterity near the fingertips 👌 One-shot assembly seemed like a dream even just a year ago — it's not easy. It requires both the high-level reasoning of "what to build" (recognizing the geometry of the structures presented by the human), and the low-level visuomotor control of "how to build it" (purposefully re-orienting individual pieces and nudging them together in place). While possible to manually engineer a complex system for this (e.g. w/ hierarchical control, or explicit state representations), we were curious if our own Foundation model could do it all end-to-end with just some post-training data. Surprisingly, it just worked. Nothing about the recipe is substantially different than any other demo we’ve run in the past, and we’re excited about its implications on model capabilities: • On contextual reasoning, these models can (i) attend to task-related pixels in the peripheral view of the video inputs, and (ii) retain this knowledge in-context while ignoring irrelevant background. This is useful for generalizing to a wide range of real workflows: e.g. paying attention to what’s coming down the conveyor line, or glancing at the instructions displayed on a nearby monitor. • On dexterity, these models can produce contact-rich "commonsense" behaviors that can be difficult to pre-program or write language instructions for e.g. rolling a brick slightly to align its studs against the bottom of another, re-grasping to get a better grip or to move out of the way before a forceful press, or gently pushing the corners of a brick against the mat to rotate it in hand and stand it up vertically (i.e. extrinsic dexterity). These aspects work together to form a capability that resembles fast adaptation — a hallmark of intelligence, relevant for real use cases. This has also expanded my own perspective on what's possible with robot learning, using a recipe that's repeatable for many more skills. This milestone stands on top of the solid technical foundations we’ve built here at Generalist: hardcore controls & hardware, all in-house built models, and a data engine that "just works." We're a small group of hyper-focused engineers, and hands-down the highest talent-density team I’ve ever worked with. We're accelerating and scaling aggressively towards unlocking next-generation robot intelligence. Building Legos is just one example, and it's clear to me that we're headed towards a future where robots can do just about anything we want them to. Its coming, and we're going to make it happen.
1:01

This is one-shot assembly: you show examples of what to build, and the robot just does it. (see original post: To share more on how this works, the robot is controlled in real time by a neural network that takes in video pixels and outputs 100Hz actions. The video below is part of the raw input passed directly into the model. I also like this view (at 1x speed) because it shows more of the (I think very cool) subtle moments of dexterity near the fingertips 👌 One-shot assembly seemed like a dream even just a year ago — it's not easy. It requires both the high-level reasoning of "what to build" (recognizing the geometry of the structures presented by the human), and the low-level visuomotor control of "how to build it" (purposefully re-orienting individual pieces and nudging them together in place). While possible to manually engineer a complex system for this (e.g. w/ hierarchical control, or explicit state representations), we were curious if our own Foundation model could do it all end-to-end with just some post-training data. Surprisingly, it just worked. Nothing about the recipe is substantially different than any other demo we’ve run in the past, and we’re excited about its implications on model capabilities: • On contextual reasoning, these models can (i) attend to task-related pixels in the peripheral view of the video inputs, and (ii) retain this knowledge in-context while ignoring irrelevant background. This is useful for generalizing to a wide range of real workflows: e.g. paying attention to what’s coming down the conveyor line, or glancing at the instructions displayed on a nearby monitor. • On dexterity, these models can produce contact-rich "commonsense" behaviors that can be difficult to pre-program or write language instructions for e.g. rolling a brick slightly to align its studs against the bottom of another, re-grasping to get a better grip or to move out of the way before a forceful press, or gently pushing the corners of a brick against the mat to rotate it in hand and stand it up vertically (i.e. extrinsic dexterity). These aspects work together to form a capability that resembles fast adaptation — a hallmark of intelligence, relevant for real use cases. This has also expanded my own perspective on what's possible with robot learning, using a recipe that's repeatable for many more skills. This milestone stands on top of the solid technical foundations we’ve built here at Generalist: hardcore controls & hardware, all in-house built models, and a data engine that "just works." We're a small group of hyper-focused engineers, and hands-down the highest talent-density team I’ve ever worked with. We're accelerating and scaling aggressively towards unlocking next-generation robot intelligence. Building Legos is just one example, and it's clear to me that we're headed towards a future where robots can do just about anything we want them to. Its coming, and we're going to make it happen.

Andy Zeng

49,317 görüntüleme • 9 ay önce

CHINA JUST SOLVED THE PROBLEM THAT'S BEEN BREAKING ROBOT AI FOR A DECADE. and the fix wasn't a smarter model. for years, every robot AI failure got the same diagnosis. the model isn't smart enough. so everyone scaled intelligence. bigger models. more parameters. better reasoning. AGIBOT asked a different question: what if the reasoning was never the problem? there's a gap that runs through every traditional robot AI system. reasoning on one side & motor commands on the other. the brain decides but the body executes something different, because thinking and moving were never actually connected. GO-2 fixes this by reasoning INSIDE the action space, not above it. before moving, it runs a complete mental simulation of every step - like a basketball player mentally tracing the arc of a shot before releasing the ball. watch the demo and you'll see exactly what this means. the robot works through a task queue autonomously. classify toiletries. upright the drink bottle. place headphones in the leather box. mid-execution, a new instruction drops: "my phone's missing. help me find it." it doesn't pause. doesn't reset. it processes the new task and keeps moving. that's not a scripted sequence. that's real-time instruction following on top of an active task queue. that one architectural change is where the numbers come from. > #1 on LIBERO across Spatial, Object, Goal, and Long tasks → 98.5% average success > 86.6% zero-shot accuracy in active disturbance environments > 47.4 on VLABench → best-in-class on objects and textures it's never seen before > 82.9% success trained on simulation only, tested on real hardware sim-to-real is the graveyard of robotics research. models trained in simulation collapse the moment they touch the real world. 82.9% means that graveyard just got a lot smaller. it holds because of how GO-2 trains. deliberately fed imperfect reasoning conditions, then trained to execute robustly anyway. not a researcher assumption. a design decision from a team that ships hardware and knows exactly what breaks. then there's the infrastructure layer. Genie Studio. fleet-wide data collection. cloud training. online post-training in live environments. 10x improvement in training efficiency. task startup reduced to minutes. 2-4x better success rates with 50%+ less data. the model gets smarter every time a robot fails in the field. this isn't a benchmark story. it's a compounding moat. dual CVPR 2026 + ACL 2026 acceptance. computer vision AND natural language processing. top conferences. simultaneously. that doesn't happen with incremental research. the US-China robotics race has been framed as a compute race. a model quality race. it was always an execution race. the robot that wins won't be the smartest one in the lab. it'll be the most reliable one on the floor. full breakdown: is execution reliability the real bottleneck, or are we still underestimating how far reasoning needs to go?
2:55

CHINA JUST SOLVED THE PROBLEM THAT'S BEEN BREAKING ROBOT AI FOR A DECADE. and the fix wasn't a smarter model. for years, every robot AI failure got the same diagnosis. the model isn't smart enough. so everyone scaled intelligence. bigger models. more parameters. better reasoning. AGIBOT asked a different question: what if the reasoning was never the problem? there's a gap that runs through every traditional robot AI system. reasoning on one side & motor commands on the other. the brain decides but the body executes something different, because thinking and moving were never actually connected. GO-2 fixes this by reasoning INSIDE the action space, not above it. before moving, it runs a complete mental simulation of every step - like a basketball player mentally tracing the arc of a shot before releasing the ball. watch the demo and you'll see exactly what this means. the robot works through a task queue autonomously. classify toiletries. upright the drink bottle. place headphones in the leather box. mid-execution, a new instruction drops: "my phone's missing. help me find it." it doesn't pause. doesn't reset. it processes the new task and keeps moving. that's not a scripted sequence. that's real-time instruction following on top of an active task queue. that one architectural change is where the numbers come from. > #1 on LIBERO across Spatial, Object, Goal, and Long tasks → 98.5% average success > 86.6% zero-shot accuracy in active disturbance environments > 47.4 on VLABench → best-in-class on objects and textures it's never seen before > 82.9% success trained on simulation only, tested on real hardware sim-to-real is the graveyard of robotics research. models trained in simulation collapse the moment they touch the real world. 82.9% means that graveyard just got a lot smaller. it holds because of how GO-2 trains. deliberately fed imperfect reasoning conditions, then trained to execute robustly anyway. not a researcher assumption. a design decision from a team that ships hardware and knows exactly what breaks. then there's the infrastructure layer. Genie Studio. fleet-wide data collection. cloud training. online post-training in live environments. 10x improvement in training efficiency. task startup reduced to minutes. 2-4x better success rates with 50%+ less data. the model gets smarter every time a robot fails in the field. this isn't a benchmark story. it's a compounding moat. dual CVPR 2026 + ACL 2026 acceptance. computer vision AND natural language processing. top conferences. simultaneously. that doesn't happen with incremental research. the US-China robotics race has been framed as a compute race. a model quality race. it was always an execution race. the robot that wins won't be the smartest one in the lab. it'll be the most reliable one on the floor. full breakdown: is execution reliability the real bottleneck, or are we still underestimating how far reasoning needs to go?

Shruti

18,622 görüntüleme • 3 ay önce

Announcing DreamDojo: our open-source, interactive world model that takes robot motor controls and generates the future in pixels. No engine, no meshes, no hand-authored dynamics. It's Simulation 2.0. Time for robotics to take the bitter lesson pill. Real-world robot learning is bottlenecked by time, wear, safety, and resets. If we want Physical AI to move at pretraining speed, we need a simulator that adapts to pretraining scale with as little human engineering as possible. Our key insights: (1) human egocentric videos are a scalable source of first-person physics; (2) latent actions make them "robot-readable" across different hardware; (3) real-time inference unlocks live teleop, policy eval, and test-time planning *inside* a dream. We pre-train on 44K hours of human videos: cheap, abundant, and collected with zero robot-in-the-loop. Humans have already explored the combinatorics: we grasp, pour, fold, assemble, fail, retry—across cluttered scenes, shifting viewpoints, changing light, and hour-long task chains—at a scale no robot fleet could match. The missing piece: these videos have no action labels. So we introduce latent actions: a unified representation inferred directly from videos that captures "what changed between world states" without knowing the underlying hardware. This lets us train on any first-person video as if it came with motor commands attached. As a result, DreamDojo generalizes zero-shot to objects and environments never seen in any robot training set, because humans saw them first. Next, we post-train onto each robot to fit its specific hardware. Think of it as separating "how the world looks and behaves" from "how this particular robot actuates." The base model follows the general physical rules, then "snaps onto" the robot's unique mechanics. It's kind of like loading a new character and scene assets into Unreal Engine, but done through gradient descent and generalizes far beyond the post-training dataset. A world simulator is only useful if it runs fast enough to close the loop. We train a real-time version of DreamDojo that runs at 10 FPS, stable for over a minute of continuous rollout. This unlocks exciting possibilities: - Live teleoperation *inside* a dream. Connect a VR controller, stream actions into DreamDojo, and teleop a virtual robot in real time. We demo this on Unitree G1 with a PICO headset and one RTX 5090. - Policy evaluation. You can benchmark a policy checkpoint in DreamDojo instead of the real world. The simulated success rates strongly correlate with real-world results - accurate enough to rank checkpoints without burning a single motor. - Model-based planning. Sample multiple action proposals → simulate them all in parallel → pick the best future. Gains +17% real-world success out of the box on a fruit packing task. We open-source everything!! Weights, code, post-training dataset, eval set, and whitepaper with tons of details to reproduce. DreamDojo is based on NVIDIA Cosmos, which is open-weight too. 2026 is the year of World Models for physical AI. We want you to build with us. Happy scaling! Links in thread:
1:17

Announcing DreamDojo: our open-source, interactive world model that takes robot motor controls and generates the future in pixels. No engine, no meshes, no hand-authored dynamics. It's Simulation 2.0. Time for robotics to take the bitter lesson pill. Real-world robot learning is bottlenecked by time, wear, safety, and resets. If we want Physical AI to move at pretraining speed, we need a simulator that adapts to pretraining scale with as little human engineering as possible. Our key insights: (1) human egocentric videos are a scalable source of first-person physics; (2) latent actions make them "robot-readable" across different hardware; (3) real-time inference unlocks live teleop, policy eval, and test-time planning *inside* a dream. We pre-train on 44K hours of human videos: cheap, abundant, and collected with zero robot-in-the-loop. Humans have already explored the combinatorics: we grasp, pour, fold, assemble, fail, retry—across cluttered scenes, shifting viewpoints, changing light, and hour-long task chains—at a scale no robot fleet could match. The missing piece: these videos have no action labels. So we introduce latent actions: a unified representation inferred directly from videos that captures "what changed between world states" without knowing the underlying hardware. This lets us train on any first-person video as if it came with motor commands attached. As a result, DreamDojo generalizes zero-shot to objects and environments never seen in any robot training set, because humans saw them first. Next, we post-train onto each robot to fit its specific hardware. Think of it as separating "how the world looks and behaves" from "how this particular robot actuates." The base model follows the general physical rules, then "snaps onto" the robot's unique mechanics. It's kind of like loading a new character and scene assets into Unreal Engine, but done through gradient descent and generalizes far beyond the post-training dataset. A world simulator is only useful if it runs fast enough to close the loop. We train a real-time version of DreamDojo that runs at 10 FPS, stable for over a minute of continuous rollout. This unlocks exciting possibilities: - Live teleoperation *inside* a dream. Connect a VR controller, stream actions into DreamDojo, and teleop a virtual robot in real time. We demo this on Unitree G1 with a PICO headset and one RTX 5090. - Policy evaluation. You can benchmark a policy checkpoint in DreamDojo instead of the real world. The simulated success rates strongly correlate with real-world results - accurate enough to rank checkpoints without burning a single motor. - Model-based planning. Sample multiple action proposals → simulate them all in parallel → pick the best future. Gains +17% real-world success out of the box on a fruit packing task. We open-source everything!! Weights, code, post-training dataset, eval set, and whitepaper with tons of details to reproduce. DreamDojo is based on NVIDIA Cosmos, which is open-weight too. 2026 is the year of World Models for physical AI. We want you to build with us. Happy scaling! Links in thread:

Jim Fan

225,239 görüntüleme • 4 ay önce

Elon Musk thinks the entire education system is built on a broken assumption. That every student should learn the same thing. At the same speed. In the same order. At the same time. Musk: “Everyone goes through from like 5th grade to 6th grade to 7th grade like it’s an assembly line. But people are not objects on an assembly line.” The model was designed for a factory economy. Standardized inputs. Predictable outputs. That economy is gone. The assembly line is gone. But the education system still runs on its logic. A student who masters algebra in two weeks sits through eight more weeks because the calendar says so. A student who struggles gets dragged forward because the schedule doesn’t wait. Neither is being served. Both are being processed. Musk: “Allow people to progress at the fastest pace that they can or are interested in, in each subject.” AI doesn’t teach a classroom. It teaches a student. One at a time. Every time. It skips what a student already knows. It finds where they’re stuck and approaches it from a different angle. It adjusts in real time. Not at the end of a semester when the damage is already done. A student obsessed with basketball learns fractions through shooting percentages. A student who builds in Minecraft learns geometry through architecture. The subject doesn’t change. The entry point does. No teacher with thirty students can do this. Not because they lack skill. Because the math doesn’t work. AI doesn’t have that constraint. Musk: “You do not need to tell your kid to play video games. They will play video games on autopilot all day. So if you can make it interactive and engaging, then you can make education far more compelling.” The brain isn’t broken. The format is. Kids learn complex systems and strategic thinking for hours voluntarily. Then walk into a classroom and can’t focus for twenty minutes. That’s not a discipline problem. That’s a design problem. Musk: “A university education is often unnecessary. You probably learn the vast majority of what you’re going to learn there in the first two years. And most of it is from your classmates.” Four years. Six figures of debt. And the real value comes from the people sitting next to you. Not the institution charging you. The degree doesn’t certify knowledge. It certifies endurance. Musk: “If the goal is to start a company, I would say no point in finishing college.” The system was built to train employees. If you’re not trying to be one, it has nothing left to offer you. Every lecture. Every textbook. Every curriculum. Now available instantly. Personalized to any learner. Adapted to any pace. The question isn’t whether the old model survives. It’s how long we keep forcing students through it while the replacement already exists.
2:08

Elon Musk thinks the entire education system is built on a broken assumption. That every student should learn the same thing. At the same speed. In the same order. At the same time. Musk: “Everyone goes through from like 5th grade to 6th grade to 7th grade like it’s an assembly line. But people are not objects on an assembly line.” The model was designed for a factory economy. Standardized inputs. Predictable outputs. That economy is gone. The assembly line is gone. But the education system still runs on its logic. A student who masters algebra in two weeks sits through eight more weeks because the calendar says so. A student who struggles gets dragged forward because the schedule doesn’t wait. Neither is being served. Both are being processed. Musk: “Allow people to progress at the fastest pace that they can or are interested in, in each subject.” AI doesn’t teach a classroom. It teaches a student. One at a time. Every time. It skips what a student already knows. It finds where they’re stuck and approaches it from a different angle. It adjusts in real time. Not at the end of a semester when the damage is already done. A student obsessed with basketball learns fractions through shooting percentages. A student who builds in Minecraft learns geometry through architecture. The subject doesn’t change. The entry point does. No teacher with thirty students can do this. Not because they lack skill. Because the math doesn’t work. AI doesn’t have that constraint. Musk: “You do not need to tell your kid to play video games. They will play video games on autopilot all day. So if you can make it interactive and engaging, then you can make education far more compelling.” The brain isn’t broken. The format is. Kids learn complex systems and strategic thinking for hours voluntarily. Then walk into a classroom and can’t focus for twenty minutes. That’s not a discipline problem. That’s a design problem. Musk: “A university education is often unnecessary. You probably learn the vast majority of what you’re going to learn there in the first two years. And most of it is from your classmates.” Four years. Six figures of debt. And the real value comes from the people sitting next to you. Not the institution charging you. The degree doesn’t certify knowledge. It certifies endurance. Musk: “If the goal is to start a company, I would say no point in finishing college.” The system was built to train employees. If you’re not trying to be one, it has nothing left to offer you. Every lecture. Every textbook. Every curriculum. Now available instantly. Personalized to any learner. Adapted to any pace. The question isn’t whether the old model survives. It’s how long we keep forcing students through it while the replacement already exists.

Teddy - PolyBackTest.com

298,016 görüntüleme • 3 gün önce

Elon Musk thinks the entire education system is built on a broken assumption. That every student should learn the same thing. At the same speed. In the same order. At the same time. Musk: “Everyone goes through from like 5th grade to 6th grade to 7th grade like it’s an assembly line. But people are not objects on an assembly line.” The model was designed for a factory economy. Standardized inputs. Predictable outputs. That economy is gone. The assembly line is gone. But the education system still runs on its logic. A student who masters algebra in two weeks sits through eight more weeks because the calendar says so. A student who struggles gets dragged forward because the schedule doesn’t wait. Neither is being served. Both are being processed. Musk: “Allow people to progress at the fastest pace that they can or are interested in, in each subject.” AI doesn’t teach a classroom. It teaches a student. One at a time. Every time. It skips what a student already knows. It finds where they’re stuck and approaches it from a different angle. It adjusts in real time. Not at the end of a semester when the damage is already done. A student obsessed with basketball learns fractions through shooting percentages. A student who builds in Minecraft learns geometry through architecture. The subject doesn’t change. The entry point does. No teacher with thirty students can do this. Not because they lack skill. Because the math doesn’t work. AI doesn’t have that constraint. Musk: “You do not need to tell your kid to play video games. They will play video games on autopilot all day. So if you can make it interactive and engaging, then you can make education far more compelling.” The brain isn’t broken. The format is. Kids learn complex systems and strategic thinking for hours voluntarily. Then walk into a classroom and can’t focus for twenty minutes. That’s not a discipline problem. That’s a design problem. Musk: “A university education is often unnecessary. You probably learn the vast majority of what you’re going to learn there in the first two years. And most of it is from your classmates.” Four years. Six figures of debt. And the real value comes from the people sitting next to you. Not the institution charging you. The degree doesn’t certify knowledge. It certifies endurance. Musk: “If the goal is to start a company, I would say no point in finishing college.” The system was built to train employees. If you’re not trying to be one, it has nothing left to offer you. Every lecture. Every textbook. Every curriculum. Now available instantly. Personalized to any learner. Adapted to any pace. The question isn’t whether the old model survives. It’s how long we keep forcing students through it while the replacement already exists.
2:08

Elon Musk thinks the entire education system is built on a broken assumption. That every student should learn the same thing. At the same speed. In the same order. At the same time. Musk: “Everyone goes through from like 5th grade to 6th grade to 7th grade like it’s an assembly line. But people are not objects on an assembly line.” The model was designed for a factory economy. Standardized inputs. Predictable outputs. That economy is gone. The assembly line is gone. But the education system still runs on its logic. A student who masters algebra in two weeks sits through eight more weeks because the calendar says so. A student who struggles gets dragged forward because the schedule doesn’t wait. Neither is being served. Both are being processed. Musk: “Allow people to progress at the fastest pace that they can or are interested in, in each subject.” AI doesn’t teach a classroom. It teaches a student. One at a time. Every time. It skips what a student already knows. It finds where they’re stuck and approaches it from a different angle. It adjusts in real time. Not at the end of a semester when the damage is already done. A student obsessed with basketball learns fractions through shooting percentages. A student who builds in Minecraft learns geometry through architecture. The subject doesn’t change. The entry point does. No teacher with thirty students can do this. Not because they lack skill. Because the math doesn’t work. AI doesn’t have that constraint. Musk: “You do not need to tell your kid to play video games. They will play video games on autopilot all day. So if you can make it interactive and engaging, then you can make education far more compelling.” The brain isn’t broken. The format is. Kids learn complex systems and strategic thinking for hours voluntarily. Then walk into a classroom and can’t focus for twenty minutes. That’s not a discipline problem. That’s a design problem. Musk: “A university education is often unnecessary. You probably learn the vast majority of what you’re going to learn there in the first two years. And most of it is from your classmates.” Four years. Six figures of debt. And the real value comes from the people sitting next to you. Not the institution charging you. The degree doesn’t certify knowledge. It certifies endurance. Musk: “If the goal is to start a company, I would say no point in finishing college.” The system was built to train employees. If you’re not trying to be one, it has nothing left to offer you. Every lecture. Every textbook. Every curriculum. Now available instantly. Personalized to any learner. Adapted to any pace. The question isn’t whether the old model survives. It’s how long we keep forcing students through it while the replacement already exists.

Dustin

21,744,023 görüntüleme • 3 ay önce

We are back again :) After three weeks of quiet building. Introducing Genesis World 1.0, our latest simulation platform, the second release in our full-stack suite. Open-sourced. Robotics is still bottlenecked by the 1× speed of the physical world. Every model, checkpoint, and data recipe eventually needs to be tested on physical hardware, slowly, expensively, and with limited coverage. One hour in reality can become 100 days in simulation. That is how robotics model iteration moves from a wall-clock bottleneck to a compute problem. To make this work, simulation has to be both fast and trustworthy. Over the past year, we rebuilt the entire stack: a GPU-accelerated cross-platform compiler, penetration-free multi-physics contact solvers, unified rigid and deformable physics, and a photo-realistic renderer purpose-built for physical AI applications. We built Nyx, a high-performance path-traced rendering engine for robotics application. Genesis World 1.0 achieves near realtime performance with our latest development for penetration-free IPC solver, supporting various types of deformables beyond rigid bodies. It supports contact-rich, dexterous manipulation simulation across different embodiments: unitree, sharpa, wuji, genesis hand and various types of grippers. Under the hood is Quadrants, our effort in pushing forward cross-platform GPU-accelerated computation. Quadrants started as a fork of Taichi, and we rebuilt most of the critical parts for optimizing simulation workloads, giving 10x faster launch time and up to 4.6x runtime performance compared to the initial Genesis release. Together, they bring us to an unprecedentedly low sim-to-real gap, enabling zero-shot real-to-sim model evaluation and much faster iteration of GENE. All available today. Genesis World 1.0: Quadrants: Nyx:
2:51

We are back again :) After three weeks of quiet building. Introducing Genesis World 1.0, our latest simulation platform, the second release in our full-stack suite. Open-sourced. Robotics is still bottlenecked by the 1× speed of the physical world. Every model, checkpoint, and data recipe eventually needs to be tested on physical hardware, slowly, expensively, and with limited coverage. One hour in reality can become 100 days in simulation. That is how robotics model iteration moves from a wall-clock bottleneck to a compute problem. To make this work, simulation has to be both fast and trustworthy. Over the past year, we rebuilt the entire stack: a GPU-accelerated cross-platform compiler, penetration-free multi-physics contact solvers, unified rigid and deformable physics, and a photo-realistic renderer purpose-built for physical AI applications. We built Nyx, a high-performance path-traced rendering engine for robotics application. Genesis World 1.0 achieves near realtime performance with our latest development for penetration-free IPC solver, supporting various types of deformables beyond rigid bodies. It supports contact-rich, dexterous manipulation simulation across different embodiments: unitree, sharpa, wuji, genesis hand and various types of grippers. Under the hood is Quadrants, our effort in pushing forward cross-platform GPU-accelerated computation. Quadrants started as a fork of Taichi, and we rebuilt most of the critical parts for optimizing simulation workloads, giving 10x faster launch time and up to 4.6x runtime performance compared to the initial Genesis release. Together, they bring us to an unprecedentedly low sim-to-real gap, enabling zero-shot real-to-sim model evaluation and much faster iteration of GENE. All available today. Genesis World 1.0: Quadrants: Nyx:

Genesis AI

307,187 görüntüleme • 1 ay önce

ANTHROPIC'S PRODUCT CHIEF HAS USED CLAUDE FABLE 5 FOR MONTHS BEFORE ANYONE ELSE. HERE'S WHAT HE LEARNED ABOUT THE MOST POWERFUL MODEL YET Mike Krieger co-founded Instagram and now runs product at Anthropic. He's had Claude Fable 5 for two months before the public, and his takeaway is that it changes how you have to work, not just how much you get done. Here's what stood out, and what to actually do with it 1. It holds the whole project, so stop chopping tasks small. The old habit was breaking work into model-sized pieces and stitching them. Fable keeps the whole thing in context. What to do: stop pre-slicing your prompts into tiny steps. Hand it the full goal and the intent behind it, the way you'd brief a senior engineer, and let it sequence the work itself 2. Delegate big, async, and overnight. He sets it on a hard task at night and wakes to it finished, including the model getting itself unstuck when a service died, scaffolding a workaround, and documenting it. What to do: stop babysitting one prompt at a time. Kick off long jobs and walk away. Run several sessions at once instead of one you watch 3. The skill is planning now, not typing. His day moved to long architecture conversations up front, then execution in chunks. What to do: spend your first prompts planning, not building. Then ask it to output an HTML page or markdown doc of the plan so your team aligns before any code is written. That early alignment is the new leverage 4. Match the effort level to the task. Fable's range is wide, so a heavy reasoning pass on a tiny UI tweak is overkill (and pricey). What to do: dial effort down for small jobs, save the deep thinking for hard ones. And don't use your most expensive model for quick questions, keep a fast model for those 5. Verification is the real bottleneck now. The hard part isn't getting output, it's trusting it. What to do: make every change ship with proof. Have Claude attach a screenshot or video of what it built, so you can see the result instead of reading the diff. Then stand behind the decisions yourself before you merge 6. Cost is per-result, not per-turn. Fable is expensive per call but often one-shots what other models need ten turns to get right. What to do: judge cost by what it takes to finish the task to your satisfaction, not the price of a single message. Give it a real task and see how far it gets before you jump in His bigger point: software engineering isn't over, it's different. The craft moved from writing code to owning intent, taste, and what actually ships. The floor rose so anyone can build, and the ceiling rose so experts go further than before Bookmark this
52:06

ANTHROPIC'S PRODUCT CHIEF HAS USED CLAUDE FABLE 5 FOR MONTHS BEFORE ANYONE ELSE. HERE'S WHAT HE LEARNED ABOUT THE MOST POWERFUL MODEL YET Mike Krieger co-founded Instagram and now runs product at Anthropic. He's had Claude Fable 5 for two months before the public, and his takeaway is that it changes how you have to work, not just how much you get done. Here's what stood out, and what to actually do with it 1. It holds the whole project, so stop chopping tasks small. The old habit was breaking work into model-sized pieces and stitching them. Fable keeps the whole thing in context. What to do: stop pre-slicing your prompts into tiny steps. Hand it the full goal and the intent behind it, the way you'd brief a senior engineer, and let it sequence the work itself 2. Delegate big, async, and overnight. He sets it on a hard task at night and wakes to it finished, including the model getting itself unstuck when a service died, scaffolding a workaround, and documenting it. What to do: stop babysitting one prompt at a time. Kick off long jobs and walk away. Run several sessions at once instead of one you watch 3. The skill is planning now, not typing. His day moved to long architecture conversations up front, then execution in chunks. What to do: spend your first prompts planning, not building. Then ask it to output an HTML page or markdown doc of the plan so your team aligns before any code is written. That early alignment is the new leverage 4. Match the effort level to the task. Fable's range is wide, so a heavy reasoning pass on a tiny UI tweak is overkill (and pricey). What to do: dial effort down for small jobs, save the deep thinking for hard ones. And don't use your most expensive model for quick questions, keep a fast model for those 5. Verification is the real bottleneck now. The hard part isn't getting output, it's trusting it. What to do: make every change ship with proof. Have Claude attach a screenshot or video of what it built, so you can see the result instead of reading the diff. Then stand behind the decisions yourself before you merge 6. Cost is per-result, not per-turn. Fable is expensive per call but often one-shots what other models need ten turns to get right. What to do: judge cost by what it takes to finish the task to your satisfaction, not the price of a single message. Give it a real task and see how far it gets before you jump in His bigger point: software engineering isn't over, it's different. The craft moved from writing code to owning intent, taste, and what actually ships. The floor rose so anyone can build, and the ceiling rose so experts go further than before Bookmark this

Yarchi

30,743 görüntüleme • 1 ay önce

Jensen Huang just laid out the next evolution of AI. Forget crafting the perfect prompt. That was step one. The real skill now is writing loops. Iterative systems where AI researches, reasons, uses tools, verifies its own results, reflects on mistakes, and keeps going until it gets the answer right. In his latest interview Jensen broke down why. AI no longer needs to be pre-coded or have everything recorded for it. It solves problems in real time through smart repeating cycles. That is what turns simple chat into actual autonomous agents that get real work done. It is also why Jensen says everyone should be using AI daily. It closes the tech divide. A carpenter can become a designer. An everyday person can become a creator. And the second-order effect is the part nobody is talking about. Massive job creation in advanced manufacturing. A full re-industrialization of America. Prompt engineering was step one. Loop engineering is the future. If you can build self-improving cycles that keep going until the job is done right, you win the next 5 years. Anyone who does not figure this out is going to fall behind FAST. At The Assembly, we tell you the best stocks to buy RIGHT NOW. We are a team of 10 analysts working FOR YOU with one goal: help you become the best possible investor. Door is currently closed. We reopen Monday, June 22nd. 24 hours only. In 6 months, half of you are going to wish you got in. Follow The Assembly with notifications or you will regret it later.
22:57

Jensen Huang just laid out the next evolution of AI. Forget crafting the perfect prompt. That was step one. The real skill now is writing loops. Iterative systems where AI researches, reasons, uses tools, verifies its own results, reflects on mistakes, and keeps going until it gets the answer right. In his latest interview Jensen broke down why. AI no longer needs to be pre-coded or have everything recorded for it. It solves problems in real time through smart repeating cycles. That is what turns simple chat into actual autonomous agents that get real work done. It is also why Jensen says everyone should be using AI daily. It closes the tech divide. A carpenter can become a designer. An everyday person can become a creator. And the second-order effect is the part nobody is talking about. Massive job creation in advanced manufacturing. A full re-industrialization of America. Prompt engineering was step one. Loop engineering is the future. If you can build self-improving cycles that keep going until the job is done right, you win the next 5 years. Anyone who does not figure this out is going to fall behind FAST. At The Assembly, we tell you the best stocks to buy RIGHT NOW. We are a team of 10 analysts working FOR YOU with one goal: help you become the best possible investor. Door is currently closed. We reopen Monday, June 22nd. 24 hours only. In 6 months, half of you are going to wish you got in. Follow The Assembly with notifications or you will regret it later.

NoLimit

117,689 görüntüleme • 29 gün önce

The power of the Claw, in the palm of a robot hand. Agentic robotics is here! Today, we open-source CaP-X: vibe agents, alive in the physical world. They incarnate as robot arms and humanoids with a rich set of perception APIs, actuation APIs, and auto synthesize skill libraries as they go. CaP-X is a strict superset of our old stack, because policies like VLAs are “just” API calls as well. It solves many tasks zero-shot that a learned policy would struggle with. And we are doing much more than vibing. CaP-X is our most systematic, scientific study on agentic robotics so far: - We build a comprehensive agentic toolkit: perception (SAM3 segmentation, Molmo pointing, depth, point cloud), control (IK solvers, grasp planner, navigation), and visualization (EEF, mask overlays) that work across different robots. - CaP-Gym: LLM’s first Physical Exam! 187 manipulation tasks across RoboSuite, LIBERO-PRO, and BEHAVIOR. Tabletop, bimanual, mobile manipulation. Sim and real. Can’t wait to see the gradients flow from CaP-Gym to the next wave of frontier LLM releases. - CaP-Bench: we benchmark 12 frontier LLMs/VLMs (Gemini, GPT, Opus, Qwen, DeepSeek, Kimi, and more) across 8 evaluation tiers. We systematically vary API abstraction level, agentic harness, and visual grounding methods. Lots of insights in our paper. - CaP-Agent0: a training-free agentic harness that matches or exceeds human expert code on 4 out of 7 tasks without task-specific tuning. - CaP-RL: if you get a gym, you get RL ;). A 7B OSS model jumps from 20% to 72% success after only 50 training iterations. The synthesized programs transfer to real robots with minimal sim-to-real gap. 3 years ago, our team created Voyager, one of the earliest agentic AI that plays and learns in Minecraft continuously. Its key ideas — skill libraries, self-reflection loops, and in-context planning — have since influenced many modern agentic designs. Today, the agent graduates from Minecraft and gets a real job. It’s April Fool’s, but this Claw is getting its hands dirty for real! Link in thread:
1:31

The power of the Claw, in the palm of a robot hand. Agentic robotics is here! Today, we open-source CaP-X: vibe agents, alive in the physical world. They incarnate as robot arms and humanoids with a rich set of perception APIs, actuation APIs, and auto synthesize skill libraries as they go. CaP-X is a strict superset of our old stack, because policies like VLAs are “just” API calls as well. It solves many tasks zero-shot that a learned policy would struggle with. And we are doing much more than vibing. CaP-X is our most systematic, scientific study on agentic robotics so far: - We build a comprehensive agentic toolkit: perception (SAM3 segmentation, Molmo pointing, depth, point cloud), control (IK solvers, grasp planner, navigation), and visualization (EEF, mask overlays) that work across different robots. - CaP-Gym: LLM’s first Physical Exam! 187 manipulation tasks across RoboSuite, LIBERO-PRO, and BEHAVIOR. Tabletop, bimanual, mobile manipulation. Sim and real. Can’t wait to see the gradients flow from CaP-Gym to the next wave of frontier LLM releases. - CaP-Bench: we benchmark 12 frontier LLMs/VLMs (Gemini, GPT, Opus, Qwen, DeepSeek, Kimi, and more) across 8 evaluation tiers. We systematically vary API abstraction level, agentic harness, and visual grounding methods. Lots of insights in our paper. - CaP-Agent0: a training-free agentic harness that matches or exceeds human expert code on 4 out of 7 tasks without task-specific tuning. - CaP-RL: if you get a gym, you get RL ;). A 7B OSS model jumps from 20% to 72% success after only 50 training iterations. The synthesized programs transfer to real robots with minimal sim-to-real gap. 3 years ago, our team created Voyager, one of the earliest agentic AI that plays and learns in Minecraft continuously. Its key ideas — skill libraries, self-reflection loops, and in-context planning — have since influenced many modern agentic designs. Today, the agent graduates from Minecraft and gets a real job. It’s April Fool’s, but this Claw is getting its hands dirty for real! Link in thread:

Jim Fan

80,166 görüntüleme • 3 ay önce