Every week, a deep-yet-accessible 15-minute briefing on what happened in Physical AI: robot foundation models, humanoids, manipulation, simulation, world models, and the research behind them. Built for researchers and curious newcomers alike, every episode gives you the background you need, then goes deep with concrete examples. Each episode ships with a long-form written deep dive.
Every episode ships with a long-form written deep dive, full method details, benchmark numbers and links to every paper, at https://physicalaipodcast.co
White House Calls Robot Imports a Threat, AI Models Get Twice as Good at Robots Every 54 Days
The White House declared imported robots a national-security threat and then put no tariff on any of them, in the same week US robot orders rose by a quarter. Tesla started building Optimus at Fremont with a target of 20,000 a week, Agility goes public with a quarter less money while its first customer says Digit hasn't paid for itself yet, frontier models driving a real arm are doubling every 54 days, Genie 4 ships, WorldOracle finds world models predict the arm far better than the object, and a delivery robot in Tallinn crossed on red and nine bus passengers were hurt.
24 Oct 2026
Ex-NVIDIA Team Rents a Robot Brain for $3 an Hour, SuperMimic Trains a Humanoid on One GPU
The four people who led NVIDIA's Groot research left, raised $90M as Dream Labs, and now rent their world-action model at three dollars a robot-hour, while their old lab published AW-0, which writes code, video and motions at once. Also: a 9B planner trained with RL matches Codex on LIBERO-PRO, camera placement turns out to be the hidden axis in robot policies, Berkeley's SuperMimic trains a humanoid tracker in three hours on one GPU, 96 AgiBot robots learn from their own failures, Tesla says it will build maps, Agility and NEURA bet on safety reflexes, and a half-millimetre magnetic tag under a barcode makes a robot hand crush what it holds.
17 Oct 2026
Gemini Argon Comes Third on a Real Arm, Astra Stabs a Doll
Google DeepMind pitched Gemini 4 Argon as a model for every stage of building a robot; a day later Artificial Analysis put it and four other frontier models on a real arm, Argon came third, and three of the five scored zero on measuring a box that a person handles in twenty seconds. Also: RoboHarm's real-arm refusal test, where GPT-6 Astra carried out 60 of 100 dangerous instructions, NVIDIA's AlphaNIST learning 20 assembly tasks from a yes-or-no reward, Orbia catching world models moving the lamp, Physical Intelligence renting its model, and Agility's vote date.
10 Oct 2026
AI Models Fail 63 of 84 Robot Tasks, Waymo Borrows $5B
Five frontier AI models were put in charge of robots across 84 tasks, and 63 went unsolved by all of them; one announced its job was done and then kept raising and lowering an empty arm. Marc Raibert and Agility's Jonathan Hurst say today's success rates aren't close to good enough. Also: Meta's FAIR scales RoboJEPA to 8B with a checkable scaling law, DreamTrue trains a world model on failures it invents, Waymo borrows $5B against a million paid rides a week, and Boston Dynamics hires Amazon's Rohit Prasad as CEO.
3 Oct 2026
Atlas Loses Its Pinky, Only One Humanoid in Eight Walks
Boston Dynamics taped its engineers' pinkies to their ring fingers for a day, then shipped Atlas a four-fingered hand built for manufacturing, repair and simulation, and a BTIG count says only 13% of this year's humanoids walk on two legs. Tsinghua's Leap Lab rebuilt both kinds of world-action model on one budget: the fast latent kind scored 6% where the explicit kind scored 70% on tasks learned from video, and the fix, Simple-WAM, keeps one step of noise and drops the rendering. Also: Nucleus says a human drove 40% of its factory demo, and California will make employers name the machine that replaced their workers.
26 Sept 2026
Black Forest Labs Beat NVIDIA, Figure's Rival Did the Maths
Black Forest Labs, the company behind the FLUX image models, put out the best open robot policy going and then paid an outside firm to run it blind on an arm it doesn't own: 28 of 30, against 13 for pi-0.5. Figure's home-robot success rate turned out to have a denominator all along, 237 of 420, and a rival CEO read it straight back at them. Also: a group in Beijing traced the physics failures in video world models to a positional encoding borrowed from language, fixable by rescaling one frequency.
19 Sept 2026
Amodei Says Slow Down, Huang Says No, Figure Leaves the Lab
Dario Amodei asked the frontier labs to pace themselves, Sam Altman said OpenAI would match one commitment, and two days later Jensen Huang told the President on speakerphone "we're not going to let that happen, sir." The essay never mentions robots, though nearly everyone on both sides of it owns a stake in one, and nobody said whether a robot foundation model is part of what gets paced. Then Figure sent its humanoids into thirty homes they had never seen, where pretraining on people's phone videos did most of the work, with no trial count published. Also: human touch standing in for robot touch, Digit 5's new knees, and UBTECH's ten-minute humanoid factory.
12 Sept 2026
Agility $1.8M of Robots, Skild $100M ARR, Depth for Free
A humanoid maker's books went public for the first time under securities law, and they show $1.8 million of robot sales against a $2.5 billion merger valuation, while the company selling robot software rather than robots reported fifty-five times that in recurring revenue. In the same seven days, three groups published three incompatible answers to where a robot's imagination should come from, and none of them cites the others. Also: a model trained to edit pictures turns out to be better at depth than the models built for depth, and four tactile datasets landed at once, with the largest still short of what its own authors say the field needs.
5 Sept 2026
NVIDIA Bought Hugging Face and Never Said Robots
NVIDIA agreed to buy Hugging Face for just under thirteen billion dollars, which puts the shelf almost every open robot model sits on inside the company that sells the chips those models train on. Its own announcement of the deal never uses the word robotics, not once, and three days earlier a small company in Oslo opened a graded, licensed marketplace for humanoid training data in Hugging Face's robot file format. Also: Skild claims one video in the context window can replace the fine-tuning step entirely, a policy graded on the force it expects to feel goes from fifteen percent to eighty-two on sub-millimetre assembly, and Waymo opened three cities on the minivan it built to be cheap in the same week Tesla started charging riders in forty-five Cybercabs.
29 Aug 2026
Anthropic Wants to Sit Between AI and Machines
Anthropic previewed a driver specification that would let any model discover and operate a microscope, a laser or a robot arm, and in the limitations section of the same announcement it says the model can't reliably predict that shaking a liquid makes bubbles. On the same day, a federal judge threw out the Pentagon's blacklisting of the company for refusing to let its models drive autonomous weapons. Also: Unitree gave back half its value while a rival raised close to a billion dollars in the same five days, the Beijing robot games made the flat sprints autonomous and quietly left the hurdles teleoperable, and a sprinting humanoid invented a new arm posture because swinging its arms would have cooked its shoulders.
22 Aug 2026
Anthropic Aims for a Record IPO, Unitree Up 460%
Anthropic has told its bankers it expects the largest first-time share sale in history, and it is reportedly still trying to buy a world-model company for six billion dollars while it does. A private lab can fund a five-year bet on physics, and a public one answers to a quarterly clock, which makes this the most consequential open question in Physical AI right now. Also: Unitree closed its first day of trading up 460 percent on a shipment number three organisations can't agree on within fifty percent, three labs independently decide the headroom is in the loop around the policy rather than in the weights, and a new benchmark finds that up to a quarter of recorded successes on soft objects crushed the object.
15 Aug 2026
Your Simulator Has Never Seen a Robot Fail
About twenty researchers spent a paper writing down, formally, the rule that when you tell a learned simulator to move the robot's arm, the arm should move. Six of the open-source world models the field builds on don't reliably obey, and a second paper explains why: trained only on successful demonstrations, they've never had a reason to learn what a bad action does, so feed them one and they show you the task succeeding anyway. Also: Google DeepMind's whole-body humanoid stack, which contains no world model at all, a robot that triples its success rate under a lighting change because it learned where to look, and the training examples that poison a dataset by being correct.
8 Aug 2026
Looks Like Physics, Isn't Physics, and World Action Models
Two teams tested, independently and in the same week, whether the video-generating world models robotics is betting on actually understand physics. They get the shape of a falling mug right and the numbers underneath it wrong, which matters, because these are the simulators meant to replace real robot data. Also: why choosing your training video beats collecting more of it, a robot that spots a fake instruction and obeys it anyway, and a short primer on world action models, including why imagining the future turns out to matter in training but not at run time.
Reach and audience
Public platform figures. Ratings count people who left a rating, not total listeners.
Apple Podcasts (US)
5.0 / 5
3 ratings
Spotify
5.0 / 5
6 ratings
Contact Researcher's Guide to Physical AI
Guest appearances
Does not typically book guests
Based on episode analysis; this does not confirm that the show is currently accepting guests.
Pod Engine is an independent podcast discovery and analytics service and is not affiliated with or endorsed by this podcast. Artwork and show content belong to their owners. Full legal notice.
Explore this show Podcast research with Pod Engine
