Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

This robot just beat Figure's package sorting speed. Robotic arms powered by X Square Robot's WALL-B embodied AI sorted 10K parcels in 5 hours 14 minutes. That's 1.88 sec per parcel, ~35% faster than Figure's reported 2.88 seconds per parcel. Figure's 9-day continuous demo in May this year was... show more

The Humanoid Hub

117,614 subscribers

40,148 views • 2 months ago •via X (Twitter)

Science & Technology Education News & Politics

Anya Rossi• Live Now

Private livecam show

20 Comments

The Humanoid Hub2 months ago

Full live stream

Eager12 months ago

What happens when there is a logjam of packages just out of reach of the arm?

The Humanoid Hub2 months ago

Human intervention

Megamojo2 months ago

Based on what I am seeing, the robot must be thinking, Flip It! Flip it! Flip! Push! Flip! Oh god no come here! Flip it! Push it!

Slavomir Semov2 months ago

yep, not every use case needs a humanoid

Garrison Moratto2 months ago

But it can’t walk to the assembly line behind it… cc @adcock_brett

Jack2 months ago

Do they have to throw my fucking packages?! 😭😭😭 What if I have a GPU in that box? Or DDR5 DRAM? Or some other expensive tech/hardware component?

Green as Grass2 months ago

Why does it look like it hates it's job? 😆

COCOBOY2 months ago

그래도 지치는 인간보단 나은듯... 손을꼭 두개로 써야되?

Oh Chee Peng ♻️ 🌎2 months ago

No matter how fast, this 2 dumb arms can only work on 1 thing.

Arthur Dent2 months ago

These things are going to get creepy pretty quickly.

Hawk_Watching♥️X$🇺🇸📐2 months ago

I feel like there should be a legless, batteryless version of optimus can be installed in place like this.

ĴƦƱƓƓƑƱȻĦŦ2 months ago

Soon I will have this to blame for my appalling packaging condition

JC2 months ago

Can they open beers? Asking for a friend

Mike2 months ago

дайте ему нормальные хваталки

Entropy Cowboy2 months ago

impressive

Synapze&Tech2 months ago

1.88s vs 2.88s is a massive leap, but the real flex here is handling non-rigid objects like soft toys on the fly. High-throughput parcel sorting fails on long-tail edge cases, not raw speed. If WALL-B handles compliant deformables without teleop intervention, that’s a huge win for general-purpose VLA models.

Some Carnie 🎡2 months ago

Why would you limit yourself to just two arms?

Tluanga Sailo2 months ago

Coz this robots has only one job 🙄 while Figure is genersl purpose

Raul Verdusco2 months ago

Speed matters, but versatility makes this even more interesting.Using the same embodied AI across sorting, household tasks, and fine manipulation points toward more general-purpose robotic systems. 🤖📦

Related Videos

Final result: 10,000 parcels sorted in 5 hours, 14 minutes, and 1 second 📦⚡ Powered by the WALL-B model, the robots maintained stable, continuous performance throughout the endurance challenge—averaging 1,911 parcels per hour and just 1.88 seconds per parcel. Five hours. 10,000 parcels. WALL-B delivered. 🚀

Final result: 10,000 parcels sorted in 5 hours, 14 minutes, and 1 second 📦⚡ Powered by the WALL-B model, the robots maintained stable, continuous performance throughout the endurance challenge—averaging 1,911 parcels per hour and just 1.88 seconds per parcel. Five hours. 10,000 parcels. WALL-B delivered. 🚀

X Square Robot

24,107 views • 2 months ago

X Square ran a fully autonomous logistics livestream: sorting parcels and flipping the barcode side up for the scanner. - 1,816 parcels/hour (~2 seconds per parcel) - 98% accuracy - ~45% higher throughput than Figure's sub-3 seconds per parcel pace from its multiday livestream in May. It's driven by X Square's WALL-B embodied AI model, which continuously reacts to an unstructured pile of parcels, sorts and flips them, and recovers from failed grasps and parcel jams to keep the line moving.

X Square ran a fully autonomous logistics livestream: sorting parcels and flipping the barcode side up for the scanner. - 1,816 parcels/hour (~2 seconds per parcel) - 98% accuracy - ~45% higher throughput than Figure's sub-3 seconds per parcel pace from its multiday livestream in May. It's driven by X Square's WALL-B embodied AI model, which continuously reacts to an unstructured pile of parcels, sorts and flips them, and recovers from failed grasps and parcel jams to keep the line moving.

The Humanoid Hub

72,067 views • 3 months ago

A fleet of Figure 02 robots sorting packages at a customer site. The robots are using Figure's in-house developed Helix model.

A fleet of Figure 02 robots sorting packages at a customer site. The robots are using Figure's in-house developed Helix model.

The Humanoid Hub

230,977 views • 1 year ago

$X Square just beat Figure’s package-sorting pace by ~45%—without a humanoid. In a 1-hour autonomous livestream, two WALL-B-powered 6-axis arms handled 1,816 mixed parcels at 98%+ accuracy. Figure’s 200-hour humanoid run averaged 1,248/hour. That’s 1.98 seconds per parcel vs. 2.88 seconds for Figure. Nearly a full second faster on every package. China processed nearly 199B express parcels in 2025. At that scale, every fraction of a second adds up. Figure is betting on the general-purpose humanoid: one body, eventually many jobs. X Square builds humanoids too, but went pragmatic here—pairing WALL-B with purpose-built arms and grippers for a faster, simpler, more economical logistics system. RobotEra made a similar choice. Its M7 at China Post skips the legs too, using an upper-body humanoid at the sorting line. This is one big difference I keep seeing between U.S. and Chinese robotics: U.S. teams like Figure are making a massive bet on the universal humanoid. Chinese teams are often more willing to change the body if it makes the economics work today. Back in June, I called logistics sorting the right first job for humanoids. X Square is making me rethink the “humanoid” part. If the job doesn’t need legs—or five fingers—why pay for them?$

X Square just beat Figure’s package-sorting pace by ~45%—without a humanoid. In a 1-hour autonomous livestream, two WALL-B-powered 6-axis arms handled 1,816 mixed parcels at 98%+ accuracy. Figure’s 200-hour humanoid run averaged 1,248/hour. That’s 1.98 seconds per parcel vs. 2.88 seconds for Figure. Nearly a full second faster on every package. China processed nearly 199B express parcels in 2025. At that scale, every fraction of a second adds up. Figure is betting on the general-purpose humanoid: one body, eventually many jobs. X Square builds humanoids too, but went pragmatic here—pairing WALL-B with purpose-built arms and grippers for a faster, simpler, more economical logistics system. RobotEra made a similar choice. Its M7 at China Post skips the legs too, using an upper-body humanoid at the sorting line. This is one big difference I keep seeing between U.S. and Chinese robotics: U.S. teams like Figure are making a massive bet on the universal humanoid. Chinese teams are often more willing to change the body if it makes the economics work today. Back in June, I called logistics sorting the right first job for humanoids. X Square is making me rethink the “humanoid” part. If the job doesn’t need legs—or five fingers—why pay for them?

RoboHub🤖

86,393 views • 3 months ago

A humanoid robot just unloaded a dishwasher for 67 hours straight. By end of 2026, the same robot will perform surgery. That's not a prediction from a sci-fi writer. That's Brett Adcock. CEO of Figure AI. Said it on camera this month. Here's what makes this insane. Two years ago Figure's robot put a Keurig cup in a coffee maker. That was the breakthrough moment. The whole team celebrated. A coffee cup. Today that same robot runs 67 consecutive hours in a BMW factory. Grabbing packages. Finding barcodes. Placing them. One operation every second. Just a neural network that learned by watching. And Brett just said the hands that do that the same fingers, the same sensors, the same neural net are already capable of surgical precision from a hardware standpoint. "From a hardware perspective in 2026 we'll be able to do what surgeons can do." The AI just has to catch up to the hands. Two years ago: a coffee cup. This year: a factory. Next: the operating table. The robot didn't change, the learning did and it's not stopping.

A humanoid robot just unloaded a dishwasher for 67 hours straight. By end of 2026, the same robot will perform surgery. That's not a prediction from a sci-fi writer. That's Brett Adcock. CEO of Figure AI. Said it on camera this month. Here's what makes this insane. Two years ago Figure's robot put a Keurig cup in a coffee maker. That was the breakthrough moment. The whole team celebrated. A coffee cup. Today that same robot runs 67 consecutive hours in a BMW factory. Grabbing packages. Finding barcodes. Placing them. One operation every second. Just a neural network that learned by watching. And Brett just said the hands that do that the same fingers, the same sensors, the same neural net are already capable of surgical precision from a hardware standpoint. "From a hardware perspective in 2026 we'll be able to do what surgeons can do." The AI just has to catch up to the hands. Two years ago: a coffee cup. This year: a factory. Next: the operating table. The robot didn't change, the learning did and it's not stopping.

Shruti

47,962 views • 6 months ago

Remember Figure's package-sorting demo? We saw RobotEra M7 humanoid perform a similar use case autonomously for 6 minutes without a mistake. We toured RobotEra's headquarters in Beijing and chatted with Lucas Wang (Lucas Wang), VP of Product, on their direct-drive hand design and where dexterous hands go next. By the way, this package-sorting use case is already deployed at real sorting stations in multiple locations in China. Thanks Lena for tag-teaming the interview. Thanks ROBOTERA for the tour.

Remember Figure's package-sorting demo? We saw RobotEra M7 humanoid perform a similar use case autonomously for 6 minutes without a mistake. We toured RobotEra's headquarters in Beijing and chatted with Lucas Wang (Lucas Wang), VP of Product, on their direct-drive hand design and where dexterous hands go next. By the way, this package-sorting use case is already deployed at real sorting stations in multiple locations in China. Thanks Lena for tag-teaming the interview. Thanks ROBOTERA for the tour.

The Humanoid Hub

27,095 views • 3 months ago

Figure AI conducted a packaging sorting competition between a robot and a human Over 10 hours, the human sorted 12,924 packages, while the robot handled 12,732.

Figure AI conducted a packaging sorting competition between a robot and a human Over 10 hours, the human sorted 12,924 packages, while the robot handled 12,732.

NEXTA

117,817 views • 5 months ago

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 views • 6 months ago

Brett Adcock says Figure's newest model is "baby AGI" and the most significant moment he's ever had in robotics. He also said it was trained last month on the most pre-training data and GPUs in Figure's history, with an even larger model ready in a few weeks.

Brett Adcock says Figure's newest model is "baby AGI" and the most significant moment he's ever had in robotics. He also said it was trained last month on the most pre-training data and GPUs in Figure's history, with an even larger model ready in a few weeks.

The Humanoid Labs

65,284 views • 21 days ago

Welcome to a "robot town" at this year's World Intelligence Expo, where a future powered by AI and robotics comes to life. From companion robots to robotic arms and human-like hands performing delicate tasks, innovation is on full display. A step closer to the future of intelligent living. #WorldIntelligenceExpo #Robotics #AI #Innovation #SmartTech #ChinaTech

Welcome to a "robot town" at this year's World Intelligence Expo, where a future powered by AI and robotics comes to life. From companion robots to robotic arms and human-like hands performing delicate tasks, innovation is on full display. A step closer to the future of intelligent living. #WorldIntelligenceExpo #Robotics #AI #Innovation #SmartTech #ChinaTech

China Xinhua News

102,444 views • 5 months ago

Andrew Kang's (Andrew Kang) highest conviction bet is Figure. In the recent pod he compared Figure's "taste" to Apple, arguing that the UX of Figure's product suite will be a fundamental differentiator. It’s been crazy going down this robotics rabbit hole.

Andrew Kang's (Andrew Kang) highest conviction bet is Figure. In the recent pod he compared Figure's "taste" to Apple, arguing that the UX of Figure's product suite will be a fundamental differentiator. It’s been crazy going down this robotics rabbit hole.

Avi

93,671 views • 5 months ago

🚨 FIGURE REVEALS HUMANOID ROBOT OUTPUT HAS SURGED 24X IN 120 DAYS Figure's humanoid robot production rose from just 1 robot per day to 1 robot an hr in only 120 days! Humanoid robots are rapidly moving toward mass deployment.

🚨 FIGURE REVEALS HUMANOID ROBOT OUTPUT HAS SURGED 24X IN 120 DAYS Figure's humanoid robot production rose from just 1 robot per day to 1 robot an hr in only 120 days! Humanoid robots are rapidly moving toward mass deployment.

Coin Bureau

64,889 views • 5 months ago

Figure AI, a 🇺🇸US humanoid robot startup, has ignited debate over robot commercialisation on industrial sites by livestreaming on YouTube a humanoid robot deployed at a logistics warehouse sorting packages non-stop for more than 81 hours, while it processed more than 100,000 packages. “Jim” visually recognizes boxes, identifies the orientation of labels, and moves them to designated locations—making all judgments using only its internal computer. It works autonomously without remote control. Expert opinions are divided. One expert described the demonstration as "closer to a science project than a fully commercial service." She cited accuracy as the biggest challenge, noting that scenes throughout the video showed the robot failing to place parcels in precise locations. Some point out that in actual logistics environments, precision matters more than speed, and areas such as handling exceptions or communication between workers remain difficult for robots at this stage. While the robot's sustainability in simple, repetitive tasks has been confirmed, additional verification remains before broad commercialization, observers said. When commercialised, Figure AI robots are expected to cost from $30,000 per unit.

Figure AI, a 🇺🇸US humanoid robot startup, has ignited debate over robot commercialisation on industrial sites by livestreaming on YouTube a humanoid robot deployed at a logistics warehouse sorting packages non-stop for more than 81 hours, while it processed more than 100,000 packages. “Jim” visually recognizes boxes, identifies the orientation of labels, and moves them to designated locations—making all judgments using only its internal computer. It works autonomously without remote control. Expert opinions are divided. One expert described the demonstration as "closer to a science project than a fully commercial service." She cited accuracy as the biggest challenge, noting that scenes throughout the video showed the robot failing to place parcels in precise locations. Some point out that in actual logistics environments, precision matters more than speed, and areas such as handling exceptions or communication between workers remain difficult for robots at this stage. While the robot's sustainability in simple, repetitive tasks has been confirmed, additional verification remains before broad commercialization, observers said. When commercialised, Figure AI robots are expected to cost from $30,000 per unit.

Dovydas Vitkauskas

21,911 views • 6 months ago

Nobody is paying enough attention to what is happening at Figure AI right now. Its humanoid robots are now working 70 hours straight livestream, sorting packages at around 2.6 seconds each. That is reportedly FASTER than the average human worker (3secs). They have now sorted over 88,000 packages with no human assistance, no teleoperation, and no cloud. The company says it will NOT STOP the stream until a robot physically breaks. The labor market is about to be redefined.

Nobody is paying enough attention to what is happening at Figure AI right now. Its humanoid robots are now working 70 hours straight livestream, sorting packages at around 2.6 seconds each. That is reportedly FASTER than the average human worker (3secs). They have now sorted over 88,000 packages with no human assistance, no teleoperation, and no cloud. The company says it will NOT STOP the stream until a robot physically breaks. The labor market is about to be redefined.

Coin Bureau

128,912 views • 6 months ago

Two weeks ago, Figure's CEO announced the end of their partnership with OpenAI and promised to show the in-house AI development – here we are: Helix is a model that unifies perception, language and learned control to execute humanoid tasks by following natural language prompts.

Two weeks ago, Figure's CEO announced the end of their partnership with OpenAI and promised to show the in-house AI development – here we are: Helix is a model that unifies perception, language and learned control to execute humanoid tasks by following natural language prompts.

The Humanoid Hub

69,472 views • 1 year ago

Humanoid logistics sorters are starting real shifts in both the U.S. and China 🤖 Figure is entering Catalyst Brands’ Reno logistics center, inside the retail network behind JCPenney, Aéropostale, and Brooks Brothers. RobotEra’s M7 is working at China Post’s Guangzhou logistics hub, feeding and sorting parcels on live lines. This is the right first job for humanoids: repetitive, physical, structured, high-volume, and easy to measure. Figure’s F.03 ran a 200-hour public sorting test and handled nearly 250,000 parcels. RobotEra’s system is being used for parcel feeding, package orientation, and exception handling, with peak throughput reported around 1,200 parcels per hour. The demand side is obvious. China handled nearly 199 billion express parcels in 2025. Guangzhou alone processed about 21.9 billion parcels, more than enough to turn sorting into a brutal labor and throughput problem. The U.S. has a different pressure point. Parcel volume is smaller, but warehouse labor is much more expensive, so a robot that can work long repetitive shifts has a cleaner ROI story if uptime, maintenance, and deployment cost hold up. The hard part is not the demo. It is barcode orientation, soft bags, crushed boxes, recovery after errors, battery swaps, fleet coordination, and keeping the line moving when nobody is filming. Sorting is still only one link in logistics. The bigger test is whether these robots can move from conveyor work into loading, unloading, picking, exception handling, and eventually the last mile — where the environment stops being friendly. That is the real question now. Not whether humanoids can sort packages, but whether they can earn the next job after sorting.

Humanoid logistics sorters are starting real shifts in both the U.S. and China 🤖 Figure is entering Catalyst Brands’ Reno logistics center, inside the retail network behind JCPenney, Aéropostale, and Brooks Brothers. RobotEra’s M7 is working at China Post’s Guangzhou logistics hub, feeding and sorting parcels on live lines. This is the right first job for humanoids: repetitive, physical, structured, high-volume, and easy to measure. Figure’s F.03 ran a 200-hour public sorting test and handled nearly 250,000 parcels. RobotEra’s system is being used for parcel feeding, package orientation, and exception handling, with peak throughput reported around 1,200 parcels per hour. The demand side is obvious. China handled nearly 199 billion express parcels in 2025. Guangzhou alone processed about 21.9 billion parcels, more than enough to turn sorting into a brutal labor and throughput problem. The U.S. has a different pressure point. Parcel volume is smaller, but warehouse labor is much more expensive, so a robot that can work long repetitive shifts has a cleaner ROI story if uptime, maintenance, and deployment cost hold up. The hard part is not the demo. It is barcode orientation, soft bags, crushed boxes, recovery after errors, battery swaps, fleet coordination, and keeping the line moving when nobody is filming. Sorting is still only one link in logistics. The bigger test is whether these robots can move from conveyor work into loading, unloading, picking, exception handling, and eventually the last mile — where the environment stops being friendly. That is the real question now. Not whether humanoids can sort packages, but whether they can earn the next job after sorting.

RoboHub🤖

37,493 views • 5 months ago

The All-In Podcast discussed Figure's AI breakthrough this week I believe this AI breakthrough was essential to enabling a billion robots on the planet - allowing humans to communicate with them and have them carry out actions Helix, our internal AI model, powers the Figure 02 robot. The robot can now generalize to objects it has never seen before and can semantically plan responses to spoken commands, such as "put the groceries away where you think they should go" It’s important to note: the robot’s actuators are not the limiting factor. Right now, both dexterity and actuator speed are constrained by the software. In fact, the actuators are capable of operating at more than 5x their current speed, but our software is holding them back. Over time, as Helix improves, the robot will ultimately surpass human speeds I like these guys. Looking forward to having Chamath Palihapitiya at Figure HQ to see these robots in action!

The All-In Podcast discussed Figure's AI breakthrough this week I believe this AI breakthrough was essential to enabling a billion robots on the planet - allowing humans to communicate with them and have them carry out actions Helix, our internal AI model, powers the Figure 02 robot. The robot can now generalize to objects it has never seen before and can semantically plan responses to spoken commands, such as "put the groceries away where you think they should go" It’s important to note: the robot’s actuators are not the limiting factor. Right now, both dexterity and actuator speed are constrained by the software. In fact, the actuators are capable of operating at more than 5x their current speed, but our software is holding them back. Over time, as Helix improves, the robot will ultimately surpass human speeds I like these guys. Looking forward to having Chamath Palihapitiya at Figure HQ to see these robots in action!

Brett Adcock

135,638 views • 1 year ago

Figure says it has increased humanoid robot production from one robot per day to one robot per hour in just 120 days. The robots undergo intensive testing, including repeated squats and jogging movements. Figure also demonstrated the robot's ability to climb stairs and navigate complex terrain using vision-based control.

Figure says it has increased humanoid robot production from one robot per day to one robot per hour in just 120 days. The robots undergo intensive testing, including repeated squats and jogging movements. Figure also demonstrated the robot's ability to climb stairs and navigate complex terrain using vision-based control.

Space and Technology

546,264 views • 5 months ago