Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

A humanoid labeled Dragongwing IQ10 went down on stage and needed human intervention before the presentation could continue. That failure is useful. Balance recovery nnee torque floor contact restart behavior. These are the details that decide whether humanoids can work outside a booth. #HumanoidRobot #Robotics #PhysicalAI #AIRobotics

TechniaHQ | humanoid robots

13,700 subscribers

18,539 görüntüleme • 3 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Qualia has been selected for the Google DeepMind Robotics Program. We train embodied models that put a robot on a real manual task and make it work, on the floor, not in a demo. Foundation models and reasoning are where robotics is heading, and doing that work alongside DeepMind, who are pushing this frontier, is exactly where we want to be. If you are a company looking to see how a new generation of robots can help your manual tasks, contact us at hello@qualiastudios.dev More soon

Qualia has been selected for the Google DeepMind Robotics Program. We train embodied models that put a robot on a real manual task and make it work, on the floor, not in a demo. Foundation models and reasoning are where robotics is heading, and doing that work alongside DeepMind, who are pushing this frontier, is exactly where we want to be. If you are a company looking to see how a new generation of robots can help your manual tasks, contact us at [email protected] More soon

Qualia

88,038 görüntüleme • 3 ay önce

Two companies. Two visions of the future of robotics. One image that millions of people have already mistaken for a real photograph. On one side—rows of Tesla Optimus robots. On the other—a Unitree army. People are debating who will win the "humanoid race." The real competition between these companies is playing out not on the factory floor, but in the capital and patent markets.

Two companies. Two visions of the future of robotics. One image that millions of people have already mistaken for a real photograph. On one side—rows of Tesla Optimus robots. On the other—a Unitree army. People are debating who will win the "humanoid race." The real competition between these companies is playing out not on the factory floor, but in the capital and patent markets.

Yura_5800

34,740 görüntüleme • 11 gün önce

TESLA HALTED MODEL S AND MODEL X PRODUCTION TO BUILD AN ARMY OF OPTIMUS ROBOTS The Fremont assembly line was torn down in 46 days. In its place, Tesla is building a line for humanoid production, aiming for a million units a year A humanoid robot is a body shaped like a human. Physical AI is the intelligence that controls that body Walking and making coffee is often just imitation learning from a scripted routine. But once the environment shifts, the learned trick stops working Language models had the entire internet to train on. Robotics has nothing close to that scale of data, which is why one giant brain hasn't worked for anyone yet The industry is moving toward modularity instead - separate models for vision, movement, and planning, each improved on its own The real question is no longer whether a robot can move impressively. It's whether it can pull its sensors into one picture of the world and adapt to whatever wasn't scripted for it

TESLA HALTED MODEL S AND MODEL X PRODUCTION TO BUILD AN ARMY OF OPTIMUS ROBOTS The Fremont assembly line was torn down in 46 days. In its place, Tesla is building a line for humanoid production, aiming for a million units a year A humanoid robot is a body shaped like a human. Physical AI is the intelligence that controls that body Walking and making coffee is often just imitation learning from a scripted routine. But once the environment shifts, the learned trick stops working Language models had the entire internet to train on. Robotics has nothing close to that scale of data, which is why one giant brain hasn't worked for anyone yet The industry is moving toward modularity instead - separate models for vision, movement, and planning, each improved on its own The real question is no longer whether a robot can move impressively. It's whether it can pull its sensors into one picture of the world and adapt to whatever wasn't scripted for it

iamigorekk

22,205 görüntüleme • 1 ay önce

The next manipulation tool may not live on your screen. It may stand in front of you look into your eyes and convince you that it understands. Would you rather face a humanoid robot strong enough to hurt you or one designed well enough to make you trust it? This robot copies blinking, eye contact, head movement and facial expressions to create the illusion of human presence. That may look impressive but it also opens a darker question. When a machine can look concerned appear friendly and imitate emotion people may start trusting signals that contain no real feeling no empathy and no moral responsibility. So which is more dangerous a robot with physical power or a robot that can manufacture trust? #HumanoidRobot #Robotics #AI

The next manipulation tool may not live on your screen. It may stand in front of you look into your eyes and convince you that it understands. Would you rather face a humanoid robot strong enough to hurt you or one designed well enough to make you trust it? This robot copies blinking, eye contact, head movement and facial expressions to create the illusion of human presence. That may look impressive but it also opens a darker question. When a machine can look concerned appear friendly and imitate emotion people may start trusting signals that contain no real feeling no empathy and no moral responsibility. So which is more dangerous a robot with physical power or a robot that can manufacture trust? #HumanoidRobot #Robotics #AI

Techniahqrobot | humanoid robots

11,650 görüntüleme • 2 ay önce

Qubic's original Useful Proof of Work (UPoW) was built on a powerful idea: that a decentralized network of small individual miners could contribute massive cumulative compute power to AIGarth — Qubic’s native AI product. This vision took shape before the global AI race truly began. Now, as major corporations increasingly rely on centralized data centers, the cracks are showing. Power grid bottlenecks, land grabs, and restrictive utility contracts, these are the limits Qubic was designed to bypass. None of that slows us down. Qubic’s UPoW isn’t just efficient. It’s future-proof by design. #QUBIC Qubic Proof of Useful Work:

Qubic's original Useful Proof of Work (UPoW) was built on a powerful idea: that a decentralized network of small individual miners could contribute massive cumulative compute power to AIGarth — Qubic’s native AI product. This vision took shape before the global AI race truly began. Now, as major corporations increasingly rely on centralized data centers, the cracks are showing. Power grid bottlenecks, land grabs, and restrictive utility contracts, these are the limits Qubic was designed to bypass. None of that slows us down. Qubic’s UPoW isn’t just efficient. It’s future-proof by design. #QUBIC Qubic Proof of Useful Work:

Qubic

16,029 görüntüleme • 1 yıl önce

I spent a month in Shenzhen visiting factories and robotics companies, and the contrast with the U.S. was striking. While Figure and Boston Dynamics hide their humanoids behind closed doors, Chinese companies have massive showrooms open to the public. But what really stood out wasn't just the transparency, it was how good they are at selling. Take UBTech: they've already sold 1,200 humanoid units at $200k each to factories. And here's the kicker, these robots aren't even that useful yet. They can only pick up and drop boxes at 1/10th the speed of a human, and factories still need to hire system integrators to train them for specific tasks. My theory is that these factories are terrified of getting left behind in the robotics/AI wave. They're investing in new tech not because it's ready, but because they can't afford to wait. The second surprise was the breadth of their robotics portfolio. These companies aren't just building humanoids, they're deploying service robots everywhere: restaurants, hotels, apartments. Consumer robots are cleaning houses, pools, pet waste, dishes. They're covering the entire spectrum. But the education piece shocked me most. I picked up what I thought was a high school or college robotics textbook, it was for primary school. The government mandated AI and robotics education starting in elementary school. Almost every single school in China now has AI and robotics curriculum, complete with education robots so kids can learn by building. They're creating a generation that grows up fluent in robotics and AI. China owns the supply chain and the hardware stack. But here's what I think people are missing: the race isn't just about who can build robots faster or cheaper. The U.S. advantage has always been in the layer between hardware and human, the interaction design, the software intelligence, the intuitive interfaces that make complex technology feel natural. China is building the physical infrastructure, but they're also learning fast. Every deployed service robot, every classroom full of kids building with education kits, every factory running humanoids, that's all data collection at scale. The window for the U.S. to establish its wedge is narrowing. It's not enough to be better at AI or software anymore. We need to be building the integration layer, the intelligence that makes physical AI actually useful, not just impressive in a showroom. Because right now, China isn't just manufacturing robots. They're manufacturing a robotics-native culture, and that might be the most defensible moat of all.

I spent a month in Shenzhen visiting factories and robotics companies, and the contrast with the U.S. was striking. While Figure and Boston Dynamics hide their humanoids behind closed doors, Chinese companies have massive showrooms open to the public. But what really stood out wasn't just the transparency, it was how good they are at selling. Take UBTech: they've already sold 1,200 humanoid units at $200k each to factories. And here's the kicker, these robots aren't even that useful yet. They can only pick up and drop boxes at 1/10th the speed of a human, and factories still need to hire system integrators to train them for specific tasks. My theory is that these factories are terrified of getting left behind in the robotics/AI wave. They're investing in new tech not because it's ready, but because they can't afford to wait. The second surprise was the breadth of their robotics portfolio. These companies aren't just building humanoids, they're deploying service robots everywhere: restaurants, hotels, apartments. Consumer robots are cleaning houses, pools, pet waste, dishes. They're covering the entire spectrum. But the education piece shocked me most. I picked up what I thought was a high school or college robotics textbook, it was for primary school. The government mandated AI and robotics education starting in elementary school. Almost every single school in China now has AI and robotics curriculum, complete with education robots so kids can learn by building. They're creating a generation that grows up fluent in robotics and AI. China owns the supply chain and the hardware stack. But here's what I think people are missing: the race isn't just about who can build robots faster or cheaper. The U.S. advantage has always been in the layer between hardware and human, the interaction design, the software intelligence, the intuitive interfaces that make complex technology feel natural. China is building the physical infrastructure, but they're also learning fast. Every deployed service robot, every classroom full of kids building with education kits, every factory running humanoids, that's all data collection at scale. The window for the U.S. to establish its wedge is narrowing. It's not enough to be better at AI or software anymore. We need to be building the integration layer, the intelligence that makes physical AI actually useful, not just impressive in a showroom. Because right now, China isn't just manufacturing robots. They're manufacturing a robotics-native culture, and that might be the most defensible moat of all.

Miyu Horiuchi

90,718 görüntüleme • 8 ay önce

AI in robotics gets all the attention right now, but sometimes the most interesting work is very practical. Viet built a small vision system that counts potatoes on a conveyor belt. No giant dataset. No huge model. Just a clear problem and a smart setup. He used Ultralytics’ ObjectCounter, trained a tiny YOLO11 nano model, and because there was no potato dataset, he annotated a single frame with SAM 2 and trained from that. One frame. Still works across the whole video. It is a good reminder that useful AI in industry often looks like this. Focused. Lightweight. Solves a real task. If you work in manufacturing or robotics, these small systems are usually the fastest wins. They save time, reduce errors, and do not need massive infrastructure. Nice work, Viet. His projects: —- Weekly robotics and AI insights. Subscribe free:

AI in robotics gets all the attention right now, but sometimes the most interesting work is very practical. Viet built a small vision system that counts potatoes on a conveyor belt. No giant dataset. No huge model. Just a clear problem and a smart setup. He used Ultralytics’ ObjectCounter, trained a tiny YOLO11 nano model, and because there was no potato dataset, he annotated a single frame with SAM 2 and trained from that. One frame. Still works across the whole video. It is a good reminder that useful AI in industry often looks like this. Focused. Lightweight. Solves a real task. If you work in manufacturing or robotics, these small systems are usually the fastest wins. They save time, reduce errors, and do not need massive infrastructure. Nice work, Viet. His projects: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

1,676,995 görüntüleme • 10 ay önce

The most dangerous part of a humanoid robot may be the face. UBTECH’s Walker shows how a machine can use gaze stillness and humanlike expression to create trust before proving judgment reliability or accountability. Should robots be allowed to look this human in public spaces? Putting the debate aside this is clearly a work of art. Congratulations to UBTECH for this achievement. Walker looks so refined that I may need to buy one fast before the stock runs out lol. Credit : UBTECH Robotics

The most dangerous part of a humanoid robot may be the face. UBTECH’s Walker shows how a machine can use gaze stillness and humanlike expression to create trust before proving judgment reliability or accountability. Should robots be allowed to look this human in public spaces? Putting the debate aside this is clearly a work of art. Congratulations to UBTECH for this achievement. Walker looks so refined that I may need to buy one fast before the stock runs out lol. Credit : UBTECH Robotics

Techniahqrobot | humanoid robots

51,556 görüntüleme • 3 ay önce

$40 hours of human work. That’s what this humanoid could save every month! A construction company is already testing a Unitree G1 on a real job site, using the robot for site inspections, 360° imaging, data collection and progress monitoring. The robot starts at around $13,500, while the company says its deployment can save roughly 40 hours of work every month. That adds up to around 480 hours a year from a machine that costs a fraction of traditional industrial equipment. The interesting part is that this isn't about replacing an entire construction worker. It's about removing hundreds of repetitive hours from the workflow, including walking inspection routes, documenting progress and collecting information across the site. Humans can then spend their time on decisions and tasks that actually require them. This is where humanoid robots become economically interesting. Construction sites are already designed around human movement, so a robot with two arms, two legs and a human-sized body can potentially work in the same spaces without rebuilding the entire environment. Every additional task it learns turns those same hardware costs into more productive hours. And the economics get even more interesting as prices fall and production scales. A robot that saves 480 hours per year doesn't need to be perfect or replace a full-time employee to justify its existence. It just needs to reliably take over the boring, repetitive work that companies are already paying humans to do. 480 hours saved. Thousands of dollars in hardware. One construction site. This is how humanoids will enter the workforce, not by replacing everyone overnight, but by quietly taking over the hours nobody wants to spend.$

40 hours of human work. That’s what this humanoid could save every month! A construction company is already testing a Unitree G1 on a real job site, using the robot for site inspections, 360° imaging, data collection and progress monitoring. The robot starts at around $13,500, while the company says its deployment can save roughly 40 hours of work every month. That adds up to around 480 hours a year from a machine that costs a fraction of traditional industrial equipment. The interesting part is that this isn't about replacing an entire construction worker. It's about removing hundreds of repetitive hours from the workflow, including walking inspection routes, documenting progress and collecting information across the site. Humans can then spend their time on decisions and tasks that actually require them. This is where humanoid robots become economically interesting. Construction sites are already designed around human movement, so a robot with two arms, two legs and a human-sized body can potentially work in the same spaces without rebuilding the entire environment. Every additional task it learns turns those same hardware costs into more productive hours. And the economics get even more interesting as prices fall and production scales. A robot that saves 480 hours per year doesn't need to be perfect or replace a full-time employee to justify its existence. It just needs to reliably take over the boring, repetitive work that companies are already paying humans to do. 480 hours saved. Thousands of dollars in hardware. One construction site. This is how humanoids will enter the workforce, not by replacing everyone overnight, but by quietly taking over the hours nobody wants to spend.

Future Memo

18,925 görüntüleme • 17 gün önce

It's the little things that make me excited about the future. Many people are (rightfully) worried that AI and robotics will take their jobs. Yes, it's about money they need to live on, and solutions are needed. At the same time, it's often work that's strenuous and tedious. So we can be glad when robots take these tasks off our hands. Furthermore, robots don't need breaks, vacations, or sleep. They can be scaled quickly and are efficient. Globalization, and humanity as a whole, can therefore benefit massively from this increase in efficiency.

It's the little things that make me excited about the future. Many people are (rightfully) worried that AI and robotics will take their jobs. Yes, it's about money they need to live on, and solutions are needed. At the same time, it's often work that's strenuous and tedious. So we can be glad when robots take these tasks off our hands. Furthermore, robots don't need breaks, vacations, or sleep. They can be scaled quickly and are efficient. Globalization, and humanity as a whole, can therefore benefit massively from this increase in efficiency.

Chubby♨️

25,552 görüntüleme • 6 ay önce

Figure 03 just finished an 8-hour work livestream, imperfect, but already good enough to replace a lot of repetitive warehouse labor. 🤖 Brett Adcock put a team of F.03 robots on a factory-style package sorting task for a full shift. The job was simple and brutal: detect the barcode, pick the package, flip it label-side down, place it on the conveyor, repeat. Soft poly bags, rigid boxes, moving belts, messy orientations. That is exactly the kind of boring physical work factories pay humans to do all day. Early in the stream, the system handled 230 packages in 10 minutes. That is roughly 2.6 seconds per item — already in human-speed territory for this narrow workflow. The more important part: it was not one robot pretending to work all day. It was a team of Figure 03 robots keeping the line running. When one robot ran low on battery, it left the station and another robot stepped in. That is the real factory signal: not just autonomy, but shift continuity. F.03 is rated for about 5 hours of runtime, so the 8-hour result depends on fleet orchestration, charging, and handoff. That matters more than a single clean demo. The stream was not perfect. There were pauses, hesitations, missed orientations, and small recovery moments. Good. A perfect short clip hides failure. An 8-hour livestream exposes the parts that actually matter: endurance, recovery, throughput, and whether the robot can stay useful after the novelty wears off. Figure says this was fully autonomous on Helix-02, with zero human intervention. For logistics and manufacturing, that is the threshold worth watching. Not “can it do one impressive task?” Can it keep doing the boring task for an entire shift? Figure is not showing a general human replacement yet. But for structured, repetitive factory work, the gap just got much smaller. The timing is also interesting: Figure says BotQ has already delivered 350+ F.03 units and reached a 1 robot/hour production cadence. And F.04 is now in full design lock, with parts starting to ship. The next test is obvious. 8 hours was the proof of endurance. 24/7 is the proof of labor economics.

Figure 03 just finished an 8-hour work livestream, imperfect, but already good enough to replace a lot of repetitive warehouse labor. 🤖 Brett Adcock put a team of F.03 robots on a factory-style package sorting task for a full shift. The job was simple and brutal: detect the barcode, pick the package, flip it label-side down, place it on the conveyor, repeat. Soft poly bags, rigid boxes, moving belts, messy orientations. That is exactly the kind of boring physical work factories pay humans to do all day. Early in the stream, the system handled 230 packages in 10 minutes. That is roughly 2.6 seconds per item — already in human-speed territory for this narrow workflow. The more important part: it was not one robot pretending to work all day. It was a team of Figure 03 robots keeping the line running. When one robot ran low on battery, it left the station and another robot stepped in. That is the real factory signal: not just autonomy, but shift continuity. F.03 is rated for about 5 hours of runtime, so the 8-hour result depends on fleet orchestration, charging, and handoff. That matters more than a single clean demo. The stream was not perfect. There were pauses, hesitations, missed orientations, and small recovery moments. Good. A perfect short clip hides failure. An 8-hour livestream exposes the parts that actually matter: endurance, recovery, throughput, and whether the robot can stay useful after the novelty wears off. Figure says this was fully autonomous on Helix-02, with zero human intervention. For logistics and manufacturing, that is the threshold worth watching. Not “can it do one impressive task?” Can it keep doing the boring task for an entire shift? Figure is not showing a general human replacement yet. But for structured, repetitive factory work, the gap just got much smaller. The timing is also interesting: Figure says BotQ has already delivered 350+ F.03 units and reached a 1 robot/hour production cadence. And F.04 is now in full design lock, with parts starting to ship. The next test is obvious. 8 hours was the proof of endurance. 24/7 is the proof of labor economics.

RoboHub🤖

16,818 görüntüleme • 4 ay önce

⚠️ THE WEIRDEST PART OF THIS ROBOT DEMO? NOBODY SEEMS SURPRISED ANYMORE! Humanoid robots are moving through a crowded public space while people walk around them like they're just another part of the environment. There’s no empty laboratory, no isolated testing area and no perfect path marked on the floor — just machines and humans sharing the same space. That makes this feel less like a robot demonstration and more like a preview of everyday life. Getting one humanoid to walk is one problem. Getting several machines to move safely around unpredictable people is another, because humans constantly stop, turn, cross paths and change direction without warning. Every movement requires the robots to perceive what is happening around them, maintain balance and continuously adjust their path. That's the shift worth paying attention to. The milestone isn't simply that robots can walk among humans — it's that we're starting to see environments where they can actually belong. Once that becomes reliable enough for shopping centers, airports, factories and offices, the question stops being whether humanoids can enter our world. It becomes what we're going to ask them to do once they're here.

⚠️ THE WEIRDEST PART OF THIS ROBOT DEMO? NOBODY SEEMS SURPRISED ANYMORE! Humanoid robots are moving through a crowded public space while people walk around them like they're just another part of the environment. There’s no empty laboratory, no isolated testing area and no perfect path marked on the floor — just machines and humans sharing the same space. That makes this feel less like a robot demonstration and more like a preview of everyday life. Getting one humanoid to walk is one problem. Getting several machines to move safely around unpredictable people is another, because humans constantly stop, turn, cross paths and change direction without warning. Every movement requires the robots to perceive what is happening around them, maintain balance and continuously adjust their path. That's the shift worth paying attention to. The milestone isn't simply that robots can walk among humans — it's that we're starting to see environments where they can actually belong. Once that becomes reliable enough for shopping centers, airports, factories and offices, the question stops being whether humanoids can enter our world. It becomes what we're going to ask them to do once they're here.

Future Memo

35,742 görüntüleme • 1 ay önce

𝗥𝗼𝗯𝗼𝘁𝘀 𝗱𝗼𝗻’𝘁 𝗻𝗲𝗲𝗱 𝗺𝗼𝗿𝗲 𝗱𝗲𝗺𝗼𝗻𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻𝘀. 𝗧𝗵𝗲𝘆 𝗻𝗲𝗲𝗱 𝘁𝗼 𝗹𝗲𝗮𝗿𝗻 𝗳𝗿𝗼𝗺 𝗳𝗮𝗶𝗹𝘂𝗿𝗲 — 𝗮𝗳𝘁𝗲𝗿 𝘄𝗮𝘁𝗰𝗵𝗶𝗻𝗴 𝗵𝘂𝗺𝗮𝗻𝘀. Most robot learning systems assume failure is the end of learning. In our new work, we study whether robots can improve after deployment by learning from their own failures, without any human intervention, teleoperation, or corrective labels. The key idea is simple: human videos contain structure about how the world works. We use them to learn cross-embodiment representations of action, dynamics, and value, enabling a shared predictive space between human behavior and robot experience. This allows a new learning loop: 👉 pretrain on human videos 👉 deploy robot policy 👉 observe failures 👉 reinterpret failures using human priors 👉 improve autonomously We evaluate this across 7 real-world manipulation tasks, showing: 📈 40% → 81% success rate 🏆 Strong improvements over π0.6 RECAP and RISE ✔️ Zero human intervention during post-deployment improvement 🧬 Generalizes across robot embodiments and policy backbones A key finding is that explicit failure repair significantly outperforms failure reweighting, yielding substantially larger gains under identical data conditions (+25 pts vs +5 pts on the same π0.5 base policy). Overall, the results suggest a shift in how we think about robot learning: Human videos are not only for pretraining policies. They can provide the structure needed for continual self-improvement after deployment. 📄 Paper: 🌐 Project: I am grateful for working with the fantastic leads Hanzhi Chen and Anran Zhang, and our collaborators Simon Schaefer, Kejia Chen, Shi Chen, Daniel Cremers. Special thanks to Stefan Leutenegger for co-advising this project with me. ETH Zürich TU München Microsoft Check out Hanzhi's 🧵 for more details

𝗥𝗼𝗯𝗼𝘁𝘀 𝗱𝗼𝗻’𝘁 𝗻𝗲𝗲𝗱 𝗺𝗼𝗿𝗲 𝗱𝗲𝗺𝗼𝗻𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻𝘀. 𝗧𝗵𝗲𝘆 𝗻𝗲𝗲𝗱 𝘁𝗼 𝗹𝗲𝗮𝗿𝗻 𝗳𝗿𝗼𝗺 𝗳𝗮𝗶𝗹𝘂𝗿𝗲 — 𝗮𝗳𝘁𝗲𝗿 𝘄𝗮𝘁𝗰𝗵𝗶𝗻𝗴 𝗵𝘂𝗺𝗮𝗻𝘀. Most robot learning systems assume failure is the end of learning. In our new work, we study whether robots can improve after deployment by learning from their own failures, without any human intervention, teleoperation, or corrective labels. The key idea is simple: human videos contain structure about how the world works. We use them to learn cross-embodiment representations of action, dynamics, and value, enabling a shared predictive space between human behavior and robot experience. This allows a new learning loop: 👉 pretrain on human videos 👉 deploy robot policy 👉 observe failures 👉 reinterpret failures using human priors 👉 improve autonomously We evaluate this across 7 real-world manipulation tasks, showing: 📈 40% → 81% success rate 🏆 Strong improvements over π0.6 RECAP and RISE ✔️ Zero human intervention during post-deployment improvement 🧬 Generalizes across robot embodiments and policy backbones A key finding is that explicit failure repair significantly outperforms failure reweighting, yielding substantially larger gains under identical data conditions (+25 pts vs +5 pts on the same π0.5 base policy). Overall, the results suggest a shift in how we think about robot learning: Human videos are not only for pretraining policies. They can provide the structure needed for continual self-improvement after deployment. 📄 Paper: 🌐 Project: I am grateful for working with the fantastic leads Hanzhi Chen and Anran Zhang, and our collaborators Simon Schaefer, Kejia Chen, Shi Chen, Daniel Cremers. Special thanks to Stefan Leutenegger for co-advising this project with me. ETH Zürich TU München Microsoft Check out Hanzhi's 🧵 for more details

Oier Mees

12,631 görüntüleme • 3 ay önce

If you are trying to understand where AI agents are going, learn harness engineering. A capable model is only one part of an agent system. Once the model begins reading files, calling tools, modifying state and working across many steps, the quality of the system depends increasingly on the software around it. Consider a coding agent working through a large repository. The model can decide that it needs to inspect a file, search for a symbol, make an edit or run a test, but those decisions do not execute themselves. The surrounding runtime has to decide which resources are available, whether the requested action is permitted, how the operation should be performed, what result should be retained, and what information should be presented to the model on the next step. This becomes harder as the run gets longer. As history accumulates, replaying everything can become costly and less effective. The harness has to decide what should remain in context, what should be summarized or retrieved later, and what belongs in persistent state outside the context window. Execution has similar problems. A long-running agent may need to survive an interruption, avoid repeating completed work, enforce permissions around consequential actions, and preserve enough history to reconstruct what happened when the final result is wrong. These are harness problems. The harness is the layer that manages context, tools, execution, state, checkpoints, limits and traces around the model. Harness engineering is the work of designing and improving that layer. Engineers inspect execution traces, evaluate agents on representative tasks, look for recurring failure modes, and then change things such as context selection, tool interfaces, state handling or execution controls. That last part matters because agent failures are often not fixed by changing the model. Sometimes the useful change is in what the model sees, how a tool is exposed, what state is preserved, or what the runtime does after a failed step. As agents take on longer tasks, the demands on this surrounding software grow. Model capability remains essential, but harness engineering is what turns that capability into an execution process that can be controlled, inspected, tested and improved.

If you are trying to understand where AI agents are going, learn harness engineering. A capable model is only one part of an agent system. Once the model begins reading files, calling tools, modifying state and working across many steps, the quality of the system depends increasingly on the software around it. Consider a coding agent working through a large repository. The model can decide that it needs to inspect a file, search for a symbol, make an edit or run a test, but those decisions do not execute themselves. The surrounding runtime has to decide which resources are available, whether the requested action is permitted, how the operation should be performed, what result should be retained, and what information should be presented to the model on the next step. This becomes harder as the run gets longer. As history accumulates, replaying everything can become costly and less effective. The harness has to decide what should remain in context, what should be summarized or retrieved later, and what belongs in persistent state outside the context window. Execution has similar problems. A long-running agent may need to survive an interruption, avoid repeating completed work, enforce permissions around consequential actions, and preserve enough history to reconstruct what happened when the final result is wrong. These are harness problems. The harness is the layer that manages context, tools, execution, state, checkpoints, limits and traces around the model. Harness engineering is the work of designing and improving that layer. Engineers inspect execution traces, evaluate agents on representative tasks, look for recurring failure modes, and then change things such as context selection, tool interfaces, state handling or execution controls. That last part matters because agent failures are often not fixed by changing the model. Sometimes the useful change is in what the model sees, how a tool is exposed, what state is preserved, or what the runtime does after a failed step. As agents take on longer tasks, the demands on this surrounding software grow. Model capability remains essential, but harness engineering is what turns that capability into an execution process that can be controlled, inspected, tested and improved.

Tech with Mak

46,947 görüntüleme • 4 gün önce

CES was an enormous success. We saw thousands of people and a few dogs interacting with our agents and robots. We booked this booth at the last minute, mainly to book next year’s booth. Truly extraordinary what our team was able to put together on such short notice. Next year we reserved one of the largest booths at CES in the highest traffic location for AI and Robotics. We plan to unveil something extraordinary. Until the next show, we will be debuting the first custom models that will emerge from the first humanoid robotics hot rod shop. These models will be walking around, talking and interacting at tradeshows all over the world over the next few months. We are in the process of acquiring every humanoid robot available on the market to modify these as well. Stay tuned for more updates, the future is here and it’s rapidly accelerating.

CES was an enormous success. We saw thousands of people and a few dogs interacting with our agents and robots. We booked this booth at the last minute, mainly to book next year’s booth. Truly extraordinary what our team was able to put together on such short notice. Next year we reserved one of the largest booths at CES in the highest traffic location for AI and Robotics. We plan to unveil something extraordinary. Until the next show, we will be debuting the first custom models that will emerge from the first humanoid robotics hot rod shop. These models will be walking around, talking and interacting at tradeshows all over the world over the next few months. We are in the process of acquiring every humanoid robot available on the market to modify these as well. Stay tuned for more updates, the future is here and it’s rapidly accelerating.

Parallel

16,884 görüntüleme • 1 yıl önce

Trump has agreed to debate Harris on September 4th on Fox. There was no mention of RFK Jr. It’s critical whether you’re a Republican, Democrat, RFK, or other third party voter, that we advocate for RFK to be on that stage. A heavy majority of Americans agree that RFK should have a spot in the debate. 7/10 Americans wanted him on the stage during the last debate, that number is no doubt equal or larger this debate. After the disastrous first debate with Trump/Biden on CNN, it is hard to argue that if RFK were on the stage that day that he could have had a chance to be polling at levels near Trump/Harris currently. It does not mean that he would be, but 100% a rational conclusion that he could be. Americans need someone on the stage to ask difficult questions that the moderators are unwilling to bring up because of the unwritten rules of hosting presidential debates. If it is a debate only between Trump/Harris, Trump will spew his talking points about Harris’s disastrous past in politics, and Harris will spew her talking points of Trump being a racist and threat to Democracy. In reality Americans don’t want to hear these talking points anymore, we already get it at nausea everyday through social media. What America truly deserves is a presidential debate where Trump, Harris, RFK, Stein, West, and Oliver are on the stage but it’s a sad truth that at first we just need to fight to try and get a third candidate on the stage before 6.

Trump has agreed to debate Harris on September 4th on Fox. There was no mention of RFK Jr. It’s critical whether you’re a Republican, Democrat, RFK, or other third party voter, that we advocate for RFK to be on that stage. A heavy majority of Americans agree that RFK should have a spot in the debate. 7/10 Americans wanted him on the stage during the last debate, that number is no doubt equal or larger this debate. After the disastrous first debate with Trump/Biden on CNN, it is hard to argue that if RFK were on the stage that day that he could have had a chance to be polling at levels near Trump/Harris currently. It does not mean that he would be, but 100% a rational conclusion that he could be. Americans need someone on the stage to ask difficult questions that the moderators are unwilling to bring up because of the unwritten rules of hosting presidential debates. If it is a debate only between Trump/Harris, Trump will spew his talking points about Harris’s disastrous past in politics, and Harris will spew her talking points of Trump being a racist and threat to Democracy. In reality Americans don’t want to hear these talking points anymore, we already get it at nausea everyday through social media. What America truly deserves is a presidential debate where Trump, Harris, RFK, Stein, West, and Oliver are on the stage but it’s a sad truth that at first we just need to fight to try and get a third candidate on the stage before 6.

End Tribalism in Politics

60,450 görüntüleme • 2 yıl önce

I'm seeing a lot of people saying it is just a bad upscaling instead of Gen AI, but it is indeed Gen AI animation. There are things going on in it that just don't make any sense for puppet animation. Here are some parts that make it clear, I slowed down the video so it's easier to notice the chunky parts. I checked the past ADs and it's possible to notice details (from an animator's POV) that are common and make sense for human work, so it was definitely a choice to use AI on this new AD

I'm seeing a lot of people saying it is just a bad upscaling instead of Gen AI, but it is indeed Gen AI animation. There are things going on in it that just don't make any sense for puppet animation. Here are some parts that make it clear, I slowed down the video so it's easier to notice the chunky parts. I checked the past ADs and it's possible to notice details (from an animator's POV) that are common and make sense for human work, so it was definitely a choice to use AI on this new AD

mei ✨ live2d animator

1,115,104 görüntüleme • 9 ay önce

WATCH THE TONGUE, NOT THE SKIN 2026 AI Robot Exhibition floor. Guy peels protective wrap off a female humanoid - realistic skin, styled hair, standing still. He touches her chin. Her mouth opens. Her tongue extends, slightly. He turns to the camera and tells you the skin texture is indistinguishable from human. He's pointing at the wrong part. - Every previous humanoid demo hides the mouth Closed lips. Controlled smiles. Interview shots that cut before the mouth has to do anything complicated. There's a reason. Mouth interior is where the uncanny valley kills the illusion faster than anywhere else on a humanoid - wet surfaces, muscle deformation, teeth showing at wrong angles, a tongue that reads as rubber. The safe move for every manufacturer up to now has been to keep it shut. - Extending a tongue means the interior is solved What this demo is actually flexing: jaw and tongue actuators independent of the smile mechanism. A soft-tissue tongue with texture that reads correctly at close range. Cheek deformation responding to his chin-touch as a tactile input - that's a sensor layer under the silicone, not just a scripted animation. This is three separate hardware systems working together on a live floor with cameras inches away. - Skin texture is a commodity now. Mouth mechanics aren't. Every manufacturer shipping humanoids in 2026 has convincing skin - platinum-cure silicone with subcutaneous tinting is a known process at this point. That's not the differentiator anymore. The differentiator is what happens when you touch the unit. The one that opens its mouth on demand, on a public floor, in front of cameras, is the one that isn't hiding from close inspection. - Why the trade show matters The 2026 AI Robot Exhibition is China's biggest humanoid showcase - where enterprise buyers from hospitality, retail, healthcare and elder-care come to sign purchase orders. Willingness to demo interior mouth mechanics in that room is a confidence signal directly aimed at those buyers. "Our unit can talk to your customers with visible tongue and teeth motion and not look wrong doing it." - What this actually unlocks Humanoid receptionists that hold a conversation without the customer noticing something's off around the mouth. Retail units that can smile with teeth showing. Healthcare aides that speak to patients at bedside range. The close-inspection barrier - the two-foot distance where the illusion has always broken - just dropped a floor. Which is the distance almost every commercial humanoid deployment actually operates at.

WATCH THE TONGUE, NOT THE SKIN 2026 AI Robot Exhibition floor. Guy peels protective wrap off a female humanoid - realistic skin, styled hair, standing still. He touches her chin. Her mouth opens. Her tongue extends, slightly. He turns to the camera and tells you the skin texture is indistinguishable from human. He's pointing at the wrong part. - Every previous humanoid demo hides the mouth Closed lips. Controlled smiles. Interview shots that cut before the mouth has to do anything complicated. There's a reason. Mouth interior is where the uncanny valley kills the illusion faster than anywhere else on a humanoid - wet surfaces, muscle deformation, teeth showing at wrong angles, a tongue that reads as rubber. The safe move for every manufacturer up to now has been to keep it shut. - Extending a tongue means the interior is solved What this demo is actually flexing: jaw and tongue actuators independent of the smile mechanism. A soft-tissue tongue with texture that reads correctly at close range. Cheek deformation responding to his chin-touch as a tactile input - that's a sensor layer under the silicone, not just a scripted animation. This is three separate hardware systems working together on a live floor with cameras inches away. - Skin texture is a commodity now. Mouth mechanics aren't. Every manufacturer shipping humanoids in 2026 has convincing skin - platinum-cure silicone with subcutaneous tinting is a known process at this point. That's not the differentiator anymore. The differentiator is what happens when you touch the unit. The one that opens its mouth on demand, on a public floor, in front of cameras, is the one that isn't hiding from close inspection. - Why the trade show matters The 2026 AI Robot Exhibition is China's biggest humanoid showcase - where enterprise buyers from hospitality, retail, healthcare and elder-care come to sign purchase orders. Willingness to demo interior mouth mechanics in that room is a confidence signal directly aimed at those buyers. "Our unit can talk to your customers with visible tongue and teeth motion and not look wrong doing it." - What this actually unlocks Humanoid receptionists that hold a conversation without the customer noticing something's off around the mouth. Retail units that can smile with teeth showing. Healthcare aides that speak to patients at bedside range. The close-inspection barrier - the two-foot distance where the illusion has always broken - just dropped a floor. Which is the distance almost every commercial humanoid deployment actually operates at.

capONE 💎

15,884 görüntüleme • 1 ay önce

What does a real humanoid robotics dataset actually look like? Humanoid robots are expensive and complex, which makes their data unusually difficult to collect - and difficult for most people to get hands-on experience with. We previously shared a post on conversion code for the new Human in the Wild dataset by BitRobot 🦾, Hugging Face, and Unitree. Now we’re publishing the full HIW-500 data converted to RRD, so you can explore that data directly with Rerun. Watch the robot move. Inspect cameras and robot states together. Zoom in on a moment and query episodes through Rerun catalog! If you’re curious about a real-world humanoid dataset, HIW-500 is now a lot easier to explore. We share the conversion code along with our previous abc-130k dataset conversion example.

What does a real humanoid robotics dataset actually look like? Humanoid robots are expensive and complex, which makes their data unusually difficult to collect - and difficult for most people to get hands-on experience with. We previously shared a post on conversion code for the new Human in the Wild dataset by BitRobot 🦾, Hugging Face, and Unitree. Now we’re publishing the full HIW-500 data converted to RRD, so you can explore that data directly with Rerun. Watch the robot move. Inspect cameras and robot states together. Zoom in on a moment and query episodes through Rerun catalog! If you’re curious about a real-world humanoid dataset, HIW-500 is now a lot easier to explore. We share the conversion code along with our previous abc-130k dataset conversion example.

Rerun

11,355 görüntüleme • 21 gün önce

Most humanoid projects talk about real work. Very few last an hour on a real line. This week I saw a case that matters for anyone building robots, perception, or physical AI. Kinisi deployed its first mobile manipulation system into a live recycling facility. Not a demo. Not a staged test. A real production line with real output pressure. Why this matters if you want robotics to deliver real value on your floor: • Handles mixed glass with random poses and no fixed fixtures. • Runs real grasp selection under noise, vibration and production variability. • Maintains throughput while avoiding breakage on a delicate material. • Shows mobile manipulation doing actual shift work instead of controlled lab runs. Kinisi published a video that shows what the robot sees and how sensor data turns into action. This is the part most teams struggle to explain to customers, so the educational angle is useful for anyone working on adoption. On top of this, the team signed a pilot with a global automotive manufacturer to explore humanoid use cases in production. The direction is clear. Wheeled mobility (not legs!) plus strong perception seems to be shaping a large part of industrial humanoids right now. I know Brennand from earlier conversations and from our podcast session, and I am always glad to see European teams push the category forward. Wishing the Kinisi team continued success. —- Weekly robotics and AI insights. Subscribe free:

Most humanoid projects talk about real work. Very few last an hour on a real line. This week I saw a case that matters for anyone building robots, perception, or physical AI. Kinisi deployed its first mobile manipulation system into a live recycling facility. Not a demo. Not a staged test. A real production line with real output pressure. Why this matters if you want robotics to deliver real value on your floor: • Handles mixed glass with random poses and no fixed fixtures. • Runs real grasp selection under noise, vibration and production variability. • Maintains throughput while avoiding breakage on a delicate material. • Shows mobile manipulation doing actual shift work instead of controlled lab runs. Kinisi published a video that shows what the robot sees and how sensor data turns into action. This is the part most teams struggle to explain to customers, so the educational angle is useful for anyone working on adoption. On top of this, the team signed a pilot with a global automotive manufacturer to explore humanoid use cases in production. The direction is clear. Wheeled mobility (not legs!) plus strong perception seems to be shaping a large part of industrial humanoids right now. I know Brennand from earlier conversations and from our podcast session, and I am always glad to see European teams push the category forward. Wishing the Kinisi team continued success. —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

24,815 görüntüleme • 10 ay önce