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.

before a robot can understand a room, it needs to notice one thing reliably this prototype is called a VAS DMSR human tracking radar a small handheld unit turns the space in front of it into a live sector view, with angle, avg m and diff m readouts changing... as it moves that loop is the foundation of physical AI: physical world → sensor reading → filtering → decision → action before adding a language model or a camera to a robot, make one signal dependable i put together a practical ESP32 guide to distance, motion, heat, sound and touch (including how to filter noisy readings before they trigger an action) follow if you want to build the physical layer of AI, one useful sensor loop at a timeshow more

ard

4,131 subscribers

54,023 views • 11 days ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

8 Comments

Dan Sullivan11 days ago

Is that a tricorder?

nOnEpcbl.11 days ago

this is the kind of practical robotics content i want more of

ard11 days ago

big love

ubis@li10 days ago

..... I've seen that somewhere before

simon.1234510 days ago

What kind of sensors use this device?

Caio Castilho11 days ago

Nice one !

سینا گلي _CodeX10 days ago

How does your VAS DMSR , exactly track humans? Looks like a basic solar radar to me which can track any moving object in front of the sensor.

Mike Whittingham10 days ago

Pretty cool

Related Videos

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

Max Zhaoshuo Li 李赵硕

1,080,061 views • 3 months ago

The future of home cleaning just landed in Shenzhen and it is walking right into your living room. 🤖🏠 X Square Robot and officially launched China’s first robot home service, moving embodied AI from the lab to your front door. When you book a cleaning on the app, a professional cleaner now shows up with an X Square robot partner to tag team the house. The human handles the tricky stuff that needs real judgment while the robot takes over repetitive tasks like wiping tables and tidying up surfaces. X Square is using an end to end foundation model which means the robot actually perceives and plans its own moves instead of just following a script. By testing in the messy reality of a real home, they are proving that if a robot can master a living room, it can handle almost any physical space. This pilot is part of a massive push to turn these machines into reliable partners that can actually assist in our daily lives.

The future of home cleaning just landed in Shenzhen and it is walking right into your living room. 🤖🏠 X Square Robot and officially launched China’s first robot home service, moving embodied AI from the lab to your front door. When you book a cleaning on the app, a professional cleaner now shows up with an X Square robot partner to tag team the house. The human handles the tricky stuff that needs real judgment while the robot takes over repetitive tasks like wiping tables and tidying up surfaces. X Square is using an end to end foundation model which means the robot actually perceives and plans its own moves instead of just following a script. By testing in the messy reality of a real home, they are proving that if a robot can master a living room, it can handle almost any physical space. This pilot is part of a massive push to turn these machines into reliable partners that can actually assist in our daily lives.

RoboHub🤖

101,350 views • 6 months ago

1/7 Physical AI has a data problem. More compute alone won’t teach a robot how to move, grasp, react, or recover from mistakes. LLMs had the entire internet to learn from. Robots need something different: huge amounts of real action data. That’s where Axis Robotics gets interesting. $AXIS is building a data engine for Physical AI, turning robot training into something people can contribute to directly through a browser. The loop is straightforward: Generate → Collect → Process → Deploy → Correct → Repeat. What looks simple on the surface could become something much bigger underneath: a scalable way to produce the training data robots need to become genuinely useful in the physical world. The real unlock for Physical AI might not be another bigger model. It might be better data.

1/7 Physical AI has a data problem. More compute alone won’t teach a robot how to move, grasp, react, or recover from mistakes. LLMs had the entire internet to learn from. Robots need something different: huge amounts of real action data. That’s where Axis Robotics gets interesting. $AXIS is building a data engine for Physical AI, turning robot training into something people can contribute to directly through a browser. The loop is straightforward: Generate → Collect → Process → Deploy → Correct → Repeat. What looks simple on the surface could become something much bigger underneath: a scalable way to produce the training data robots need to become genuinely useful in the physical world. The real unlock for Physical AI might not be another bigger model. It might be better data.

_Victorad

19,657 views • 1 month ago

🇨🇳 It has started. A new home service in China pairs human cleaners with autonomous AI robots to tackle household chores. Residents in Shenzhen can now book a service where a human professional and an autonomous robot arrive together to clean their home. Real houses present a chaotic mess of dropped toys and random furniture that confuse traditional machines. X Square Robot and a major service platform named 58[.]com decided to tackle this chaos by launching China's first robot cleaner service in March-26. Customers use an application to hire a cleaning crew that consists of 1 human worker and 1 robot. The human takes care of the tricky chores that require complex judgment. The robot handles the repetitive physical work like picking up trash and wiping down flat surfaces. This machine runs on a system called WALL-A, which acts as a single continuous AI brain rather than a list of pre-written rules. They built this AI foundation model to perceive its surroundings and make its own decisions without human guidance. It processes visual data and plans multi-step actions. And deploying these robots into actual homes now provides the massive amounts of extremely important training data to improve it continuously. Alibaba and ByteDance backed this project. IMO, if the foundational model behind it figures out how to navigate a messy living room without getting stuck, it can learn to operate in almost any other physical environment.

🇨🇳 It has started. A new home service in China pairs human cleaners with autonomous AI robots to tackle household chores. Residents in Shenzhen can now book a service where a human professional and an autonomous robot arrive together to clean their home. Real houses present a chaotic mess of dropped toys and random furniture that confuse traditional machines. X Square Robot and a major service platform named 58[.]com decided to tackle this chaos by launching China's first robot cleaner service in March-26. Customers use an application to hire a cleaning crew that consists of 1 human worker and 1 robot. The human takes care of the tricky chores that require complex judgment. The robot handles the repetitive physical work like picking up trash and wiping down flat surfaces. This machine runs on a system called WALL-A, which acts as a single continuous AI brain rather than a list of pre-written rules. They built this AI foundation model to perceive its surroundings and make its own decisions without human guidance. It processes visual data and plans multi-step actions. And deploying these robots into actual homes now provides the massive amounts of extremely important training data to improve it continuously. Alibaba and ByteDance backed this project. IMO, if the foundational model behind it figures out how to navigate a messy living room without getting stuck, it can learn to operate in almost any other physical environment.

Rohan Paul

53,039 views • 6 months ago

Watching Generalist AI demonstrate real-time intuition is incredible! 🤖✨ Check out this "Physical Commonsense" in action: the robot flips a washer, picks it up and then double-nudges it perfectly into a tight foam slot. This isn't a scripted motion; it’s an emergent behavior from a model trained on 270,000+ hours of real-world interaction. We are seeing the era where robots are starting to intuit and react to physics.

Watching Generalist AI demonstrate real-time intuition is incredible! 🤖✨ Check out this "Physical Commonsense" in action: the robot flips a washer, picks it up and then double-nudges it perfectly into a tight foam slot. This isn't a scripted motion; it’s an emergent behavior from a model trained on 270,000+ hours of real-world interaction. We are seeing the era where robots are starting to intuit and react to physics.

Humanoids daily

14,762 views • 8 months ago

Travis Kalanick: Tesla is the Google of the Physical AI Era “I like to break down the physical AI stack: (it) includes computation, a physical AI model, all the things you think of.” “What about land? Development? That should be in that stack. What about chemistry? That needs to be in the stack. Manufacturing needs to be a stack.” “When you look at the stack, you're like, ‘Damn, Tesla's got this sh*t.’ They are the Google of this era.” “What I mean by that is, if you were doing a startup in the 2000s, the first question you would get is, ‘Why isn't Google gonna kill you?’ Or, ‘Why isn't Google just gonna do it?’ They’re not even gonna know that they killed you.” “And before that, it was Microsoft in the late 90s. Uber had a time, 2010s.” “But in the physical AI space, that's sort of a Tesla thing.” -------------------------------------------- Thanks to our partner for making this happen!: EY (EY) Austin vibes meet AI innovation. Thanks to EY for co‑hosting with us at #SXSW. Discover what executives are saying about AI transformation in the latest AI Pulse Survey.

Travis Kalanick: Tesla is the Google of the Physical AI Era “I like to break down the physical AI stack: (it) includes computation, a physical AI model, all the things you think of.” “What about land? Development? That should be in that stack. What about chemistry? That needs to be in the stack. Manufacturing needs to be a stack.” “When you look at the stack, you're like, ‘Damn, Tesla's got this sh*t.’ They are the Google of this era.” “What I mean by that is, if you were doing a startup in the 2000s, the first question you would get is, ‘Why isn't Google gonna kill you?’ Or, ‘Why isn't Google just gonna do it?’ They’re not even gonna know that they killed you.” “And before that, it was Microsoft in the late 90s. Uber had a time, 2010s.” “But in the physical AI space, that's sort of a Tesla thing.” -------------------------------------------- Thanks to our partner for making this happen!: EY (EY) Austin vibes meet AI innovation. Thanks to EY for co‑hosting with us at #SXSW. Discover what executives are saying about AI transformation in the latest AI Pulse Survey.

The All-In Podcast

95,287 views • 6 months ago

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at

Binh

122,482 views • 3 months ago

“Say a robot drives into a wall. Why did it do that?” Nikolaus West explains why robotics teams need clearer visibility into sensor data, and how Rerun is helping push physical AI from impressive demos to real reliability. Link to the full episode with Lukas Biewald in comments.

“Say a robot drives into a wall. Why did it do that?” Nikolaus West explains why robotics teams need clearer visibility into sensor data, and how Rerun is helping push physical AI from impressive demos to real reliability. Link to the full episode with Lukas Biewald in comments.

Weights & Biases

196,608 views • 9 months ago

Turns out every viral robot demo you've seen was... staged. The backflips, the coffee, the laundry-folding — the robot got handed the answers before the test. Jagdeep Singh says the whole industry's obsession with VLA models is lighting money on fire. You may know my guest as a CEO took QuantumScape public and built Infinera before that, betting against the "impossible" physics twice and proven right each time. Now he's taking another huge swing in Physical AI. The bet everyone else is making: pay humans to tele-operate robots through a task thousands of times, then train on the footage. Jagdeep calls this a dead end. "A drop in the bucket" next to what a robot actually needs to understand the physics of our world. Rhoda AI's approach is revolutionary, training on internet video instead. Turns out 80% of the internet is video, more than enough to teach a model how the physical world really moves. The payoff is that while the the teleoperation crowd burns 70,000 hours of data, some claim 500,000, Rhoda gets a robot doing real factory work on 10 to 20 hours. Proven fact. We're staring down labor shortages in every dirty, dangerous corner of the economy. Turns out the problem was never the robot. It was the number of hours it took to make one useful. Thrilled to be an investor in Jagdeep and Rhoda alongside great investors like Vinod Khosla and Navin Chaddha. New CLIMB is live below and linked in comments 👇

Turns out every viral robot demo you've seen was... staged. The backflips, the coffee, the laundry-folding — the robot got handed the answers before the test. Jagdeep Singh says the whole industry's obsession with VLA models is lighting money on fire. You may know my guest as a CEO took QuantumScape public and built Infinera before that, betting against the "impossible" physics twice and proven right each time. Now he's taking another huge swing in Physical AI. The bet everyone else is making: pay humans to tele-operate robots through a task thousands of times, then train on the footage. Jagdeep calls this a dead end. "A drop in the bucket" next to what a robot actually needs to understand the physics of our world. Rhoda AI's approach is revolutionary, training on internet video instead. Turns out 80% of the internet is video, more than enough to teach a model how the physical world really moves. The payoff is that while the the teleoperation crowd burns 70,000 hours of data, some claim 500,000, Rhoda gets a robot doing real factory work on 10 to 20 hours. Proven fact. We're staring down labor shortages in every dirty, dangerous corner of the economy. Turns out the problem was never the robot. It was the number of hours it took to make one useful. Thrilled to be an investor in Jagdeep and Rhoda alongside great investors like Vinod Khosla and Navin Chaddha. New CLIMB is live below and linked in comments 👇

Jay Kapoor

40,516 views • 4 months ago

The machine economy does not begin when robots get smarter. It begins when a machine can be paid to do something, and every party involved can prove what happened. Made with Fabric Foundation. Two systems meet in the middle of it: Agent Passport issues the agent a verifiable identity and a spending authority its owner defines, and RoboPay actuates a robot after the payment behind the request checks out. What happens before the robot moves: ▷ Authority is granted once, and it is bounded. The human signs a spending session with a passkey: a total budget, a per-transaction ceiling, the assets allowed, and an expiry. The agent holds no card number and no wallet key. It holds a delegation it cannot exceed. ▷ Two payments, because these are two different obligations. One settles with the merchant for the goods. A separate x402 payment pays the robot for the work of moving them. Buying a thing and hiring a machine to carry it are not the same transaction, and the receipt keeps them apart. ▷ Verification comes before motion. The request arrives with an x402 payment header. The facilitator checks the network, the price, the payee wallet, and the signed payload. Only then are the transaction details sealed onto the robot action event and the command published. Until that clears, the robot sits still. ▷ Every step leaves a receipt. Identity, scope, approval, both payments, verification, dispatch. When you need to know why a machine did something, the answer is a record rather than a guess. (This run was executed in a demo environment.) Agents have been paying for software for a while now. Paying for physical work is a harder problem, because a delivery cannot be rolled back. The guarantee has to sit in front of the action instead of behind it. Authorization before payment, payment before motion: that ordering is what makes it safe to let autonomous systems spend in the world we live in. It is also the layer the machine economy has to get right before anything else in it can work. Scoped by Kite. Verified by RoboPay. Delivered in the real world. 🪁

The machine economy does not begin when robots get smarter. It begins when a machine can be paid to do something, and every party involved can prove what happened. Made with Fabric Foundation. Two systems meet in the middle of it: Agent Passport issues the agent a verifiable identity and a spending authority its owner defines, and RoboPay actuates a robot after the payment behind the request checks out. What happens before the robot moves: ▷ Authority is granted once, and it is bounded. The human signs a spending session with a passkey: a total budget, a per-transaction ceiling, the assets allowed, and an expiry. The agent holds no card number and no wallet key. It holds a delegation it cannot exceed. ▷ Two payments, because these are two different obligations. One settles with the merchant for the goods. A separate x402 payment pays the robot for the work of moving them. Buying a thing and hiring a machine to carry it are not the same transaction, and the receipt keeps them apart. ▷ Verification comes before motion. The request arrives with an x402 payment header. The facilitator checks the network, the price, the payee wallet, and the signed payload. Only then are the transaction details sealed onto the robot action event and the command published. Until that clears, the robot sits still. ▷ Every step leaves a receipt. Identity, scope, approval, both payments, verification, dispatch. When you need to know why a machine did something, the answer is a record rather than a guess. (This run was executed in a demo environment.) Agents have been paying for software for a while now. Paying for physical work is a harder problem, because a delivery cannot be rolled back. The guarantee has to sit in front of the action instead of behind it. Authorization before payment, payment before motion: that ordering is what makes it safe to let autonomous systems spend in the world we live in. It is also the layer the machine economy has to get right before anything else in it can work. Scoped by Kite. Verified by RoboPay. Delivered in the real world. 🪁

KITE AI

35,068 views • 2 months ago

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

Sprytix

153,908 views • 2 months ago

World Labs co-founder Justin Johnson on how five photos from your phone could teach a robot to work in a room it has never seen: "I think there's a couple different tech trees that people are working on. One is this notion of fully in-context learning. Maybe I've got a robotics foundation model, then I can demonstrate to the robot once how a task should be performed, and that's enough for the robot to figure out that task." "Another version is what we're calling real-to-sim-to-real. Maybe I've got my pre-trained robotics foundation model, but I want to adapt it to this particular environment." "Like this studio... You could come in here and take just a couple casual videos with your phone or a couple images with your phone, use Atlas to reconstruct the space, and now stage all kinds of robotics interactions in this studio space in particular." "Literally you could do it in five minutes. Take five photos, upload it to Atlas, have it generate a simulation, describe in natural language what kind of task you want the robot to do, have an agent go build that simulation for you, RL fine-tune your general purpose robotics foundation model, and now you've got a robot... that's perfectly adapted to this space." Justin Johnson on MTS

World Labs co-founder Justin Johnson on how five photos from your phone could teach a robot to work in a room it has never seen: "I think there's a couple different tech trees that people are working on. One is this notion of fully in-context learning. Maybe I've got a robotics foundation model, then I can demonstrate to the robot once how a task should be performed, and that's enough for the robot to figure out that task." "Another version is what we're calling real-to-sim-to-real. Maybe I've got my pre-trained robotics foundation model, but I want to adapt it to this particular environment." "Like this studio... You could come in here and take just a couple casual videos with your phone or a couple images with your phone, use Atlas to reconstruct the space, and now stage all kinds of robotics interactions in this studio space in particular." "Literally you could do it in five minutes. Take five photos, upload it to Atlas, have it generate a simulation, describe in natural language what kind of task you want the robot to do, have an agent go build that simulation for you, RL fine-tune your general purpose robotics foundation model, and now you've got a robot... that's perfectly adapted to this space." Justin Johnson on MTS

a16z

35,947 views • 25 days ago

World Labs co-founder Justin Johnson predicts a real-to-sim-to-real future where Atlas could train a robot for any new environment in minutes using just 5 photos from your phone: "One is this notion of fully in-context learning. Maybe I've got a robotics foundation model, then I can demonstrate the robot once how a task should be performed, and that's enough for the robot to figure out." "Another version is real to sim to real. Maybe I've got my pre-trained robotics foundation model, but I want to adapt it to this particular environment, like this studio, this table, moving this microphone around." "There's a version where you could come in here and take just a couple casual videos with your phone or a couple images with your phone, use Atlas to reconstruct the space, and now stage all kinds of robotics interactions in this studio space." "If you could lower the barrier to doing that, you could do it in five minutes to take five photos, upload it to Atlas, have it generate a simulation, maybe describe in natural language what kind of task you want the robot to do, have an agent go build that simulation for you, RL fine-tune your general purpose robotics foundation model, and now you've got a robot maybe in the span of a couple minutes that could come in and is perfectly adapted to this space." World Labs

World Labs co-founder Justin Johnson predicts a real-to-sim-to-real future where Atlas could train a robot for any new environment in minutes using just 5 photos from your phone: "One is this notion of fully in-context learning. Maybe I've got a robotics foundation model, then I can demonstrate the robot once how a task should be performed, and that's enough for the robot to figure out." "Another version is real to sim to real. Maybe I've got my pre-trained robotics foundation model, but I want to adapt it to this particular environment, like this studio, this table, moving this microphone around." "There's a version where you could come in here and take just a couple casual videos with your phone or a couple images with your phone, use Atlas to reconstruct the space, and now stage all kinds of robotics interactions in this studio space." "If you could lower the barrier to doing that, you could do it in five minutes to take five photos, upload it to Atlas, have it generate a simulation, maybe describe in natural language what kind of task you want the robot to do, have an agent go build that simulation for you, RL fine-tune your general purpose robotics foundation model, and now you've got a robot maybe in the span of a couple minutes that could come in and is perfectly adapted to this space." World Labs

MTS

25,204 views • 26 days ago

Explore where physical AI is headed next with the people shaping it. On Feb. 10 at 9 a.m. PT, join Ming‑Yu, Vice President of Research at NVIDIA, and Chubby♨️ from Superintelligence, for a conversation on how NVIDIA Cosmos reframes AI for a world of robots, AVs, and vision-driven systems. We'll dig into: ✅ Cosmos' origins and designing models for the physical world ✅ The scientific ideas and architectures behind Cosmos and its open models ✅ How open, reasoning-capable physical AI is changing how teams prototype, deploy, and iterate ✅ What a future of AI systems that understand space, time, and causality could unlock If you’re thinking into real‑world AI, this is the conversation to catch ➡️

Explore where physical AI is headed next with the people shaping it. On Feb. 10 at 9 a.m. PT, join Ming‑Yu, Vice President of Research at NVIDIA, and Chubby♨️ from Superintelligence, for a conversation on how NVIDIA Cosmos reframes AI for a world of robots, AVs, and vision-driven systems. We'll dig into: ✅ Cosmos' origins and designing models for the physical world ✅ The scientific ideas and architectures behind Cosmos and its open models ✅ How open, reasoning-capable physical AI is changing how teams prototype, deploy, and iterate ✅ What a future of AI systems that understand space, time, and causality could unlock If you’re thinking into real‑world AI, this is the conversation to catch ➡️

NVIDIA AI Developer

26,468 views • 7 months ago

Breaking news: Cosmos 3 is here. They are attempting to do something completely new 🤯 Why is Physical AI much harder than building a chatbot? Understanding the world is not enough, robots need to predict it and act inside it. That's the idea behind NVIDIA Cosmos 3: → Reasoning model understands what's happening from video, images, text, and actions. → World model generates future states of the environment. → Action model generates the actions needed to achieve a goal. Previous systems often stitched these capabilities together using separate models. Cosmos 3 combines them into a single architecture with two components: ▪️ Reasoner Tower Analyzes observations and builds an understanding of objects, motion, interactions, and physical context. ▪️ Generator Tower Uses that understanding to generate future videos and action sequences that obey physical constraints. So Cosmos 3 moves from: Perception → Model A Prediction → Model B Actions → Model C to: Perception + Prediction + Actions → One unified system. The goal is to make robots, autonomous vehicles, and smart environments better at answering three questions: 1. What is happening? 2. What will happen next? 3. What should I do? That's a big shift from today's AI, which mostly focuses on generating text. And check the benchmarks! Physical AI needs to generate decisions that survive contact with the real world. 🚗🤖

Breaking news: Cosmos 3 is here. They are attempting to do something completely new 🤯 Why is Physical AI much harder than building a chatbot? Understanding the world is not enough, robots need to predict it and act inside it. That's the idea behind NVIDIA Cosmos 3: → Reasoning model understands what's happening from video, images, text, and actions. → World model generates future states of the environment. → Action model generates the actions needed to achieve a goal. Previous systems often stitched these capabilities together using separate models. Cosmos 3 combines them into a single architecture with two components: ▪️ Reasoner Tower Analyzes observations and builds an understanding of objects, motion, interactions, and physical context. ▪️ Generator Tower Uses that understanding to generate future videos and action sequences that obey physical constraints. So Cosmos 3 moves from: Perception → Model A Prediction → Model B Actions → Model C to: Perception + Prediction + Actions → One unified system. The goal is to make robots, autonomous vehicles, and smart environments better at answering three questions: 1. What is happening? 2. What will happen next? 3. What should I do? That's a big shift from today's AI, which mostly focuses on generating text. And check the benchmarks! Physical AI needs to generate decisions that survive contact with the real world. 🚗🤖

Turing Post

13,836 views • 3 months ago

everyone is using GPT-6 Astra to make games... i had it build me a robot prototyper i type what robot i want, and it builds the whole thing and tells me how to make it real one prompt: "prototype me a full Microduck" it designed every part, checked nothing crashes into itself when it moves, did the motor maths so the thing can actually stand up, and handed me the parts list with prices and the step by step assembly not a render, a robot i can build this weekend every piece is ready to send straight to a 3D printer, and the motors and screws come with prices and where to buy them took me 45 minutes and 5 prompts to build (burnt all my limits) process below

everyone is using GPT-6 Astra to make games... i had it build me a robot prototyper i type what robot i want, and it builds the whole thing and tells me how to make it real one prompt: "prototype me a full Microduck" it designed every part, checked nothing crashes into itself when it moves, did the motor maths so the thing can actually stand up, and handed me the parts list with prices and the step by step assembly not a render, a robot i can build this weekend every piece is ready to send straight to a 3D printer, and the motors and screws come with prices and where to buy them took me 45 minutes and 5 prompts to build (burnt all my limits) process below

Ronin

58,670 views • 21 days ago

Honor is building the first phone that also includes an AI robot. It's a robot in the sense that the pop-up camera acts as the AI's eyes, and if I understand correctly, it allows a continuously active AI companion to work as an assistant. Interesting, but probably more of a gimmick. However, personal AI companions are coming.

Honor is building the first phone that also includes an AI robot. It's a robot in the sense that the pop-up camera acts as the AI's eyes, and if I understand correctly, it allows a continuously active AI companion to work as an assistant. Interesting, but probably more of a gimmick. However, personal AI companions are coming.

Chubby♨️

201,603 views • 7 months ago

Nirvarnic CEO Suzanne Gildert asks: what if we put a robot in a feedback loop with a quantum computer? No training. No reward. Just perception shaping a quantum wavefunction and collapse deciding the next move. “It might be something like a proto spark of experience.” This has never been tried in a scientific setting, until now. It won't prove consciousness, but it might signal that something else is happening. And finally enable AI in the physical world.

Nirvarnic CEO Suzanne Gildert asks: what if we put a robot in a feedback loop with a quantum computer? No training. No reward. Just perception shaping a quantum wavefunction and collapse deciding the next move. “It might be something like a proto spark of experience.” This has never been tried in a scientific setting, until now. It won't prove consciousness, but it might signal that something else is happening. And finally enable AI in the physical world.

vitrupo

97,241 views • 1 year ago