Bot News

👁️The most dangerous AI failure in the DoW will not look like a hallucination. 👁️It will look formal, defensible, and audit-ready. 👁️Then it will be approved, inherited, and believed. 👁️I call that pathway the Reliability Kill Chain 👁️Why "human in the loop" is not enough:

The transmission inside 1X NEO's new hand shares a family tree with bicycle brakes and surgical endoscopes: tension cables running through compression sheaths, the only routing that carries force across a 3-DoF wrist without caring what the wrist is doing. 1X bet the whole architecture on paying friction tax at a discount: gear ratios of 5:1 to 15:1 where the industry runs past 100:1, low enough that motor current still carries the shape of whatever the fingers are touching. The cinematic footage shows wine glasses and LEGO Duplo but not the force residual at full wrist articulation, six months into a kitchen. We restated the whole field in one accounting standard, priced the parts list on both sides of the Pacific, and traced the tendon loops the launch didn't diagram. Corrections welcomed. #information #robotics #ai #robot #1x #neo

@AIkingdome Ty 🥹 can’t wait to see your build at OpenSauce!

@BotNewsAI LOL I’m 💀 these articles are so underrated dude. I always look forward to them.

@SharpaRobotics @kushalk_ @tylerlum23 @leto__jean @KarenJLiu Sharpa is art

Before a robot can perfect assembly, it needs to learn to play. The team behind SimToolReal @kushalk_ @tylerlum23 @leto__jean @KarenJLiu published another cool paper! Play2Perfect pretrains on diverse, task-agnostic play (grasp, reorient, reach, etc), then finetunes on sparse-reward assembly. Result: 33× sample efficiency vs. training from scratch, and zero-shot sim-to-real down to 0.5mm clearance. Peg insertion, screwing, multi-part assembly: all running at 60Hz, real speed, real hardware. And when a grasp slips, the policy doesn't stop, it recovers and keeps going. The Sharpa Wave responded present again ;) Project: play2perfect.github.io #Robotics #SharpaWave #Sharpa #EmbodiedAI #DexterousManipulation #RobotLearning

The most valuable part of a robot demo may not be the motion anymore. It may be the part of the object it taught the world how to hold. CHORD starts as a dexterous manipulation result and ends as a new accounting system for robot data. On the surface, NVIDIA’s paper reads like another human-video-to-robot-manipulation pipeline: recover the demonstrated contacts, retarget the motion, train the policy. But the reward does not really score the hand. It scores the deal the hand made with the object. A contact point is just an address. It does not tell you whether the finger pinned the object, slid it, tipped it, rotated it, or quietly kept the whole motion from falling apart. The useful thing lives in the contact normal, the moment arm, and the friction cone: the directions that grip can push and twist the object. Pressure never enters the reward, which is the tell. Video cannot reliably recover human squeeze anyway. So CHORD scores wrench support instead. Not “did the robot touch where the human touched?” but “can this grip create the same menu of forces and torques on the object?” That means a human hand and a robot claw can share almost no contact geometry and still count as the same demonstration. Different fingers. Different body. Same object-side authority. Copy the contact positions and articulated objects collapse to 0.000. Score the wrench support and they reach 0.914. That unwelds the demo from the body that recorded it. Once a manipulation demo survives embodiment transfer, it stops being a clip. It becomes inventory: something you can stockpile, rank, license, and rent back to the next policy that needs to know how the world can be held. Somebody is quietly building the object library every future robot policy ends up renting from. Covered it in my article for @BotNewsAI. #ai #tech

"It looks right" and "it is right" are not the same claim, and most of the painful lessons in this field live in that gap. SC3-Eval sits right on top of it. The pitch is to evaluate robot policies inside a generated video instead of on a physical arm, but generated video drifts. A forward-only model can continue to produce plausible frames long after the action behind them has gone wrong. Looking harder at the picture doesn't help. So they stop asking the model to look forward and make it run the story backward: which action would have caused this footage? When the answer stops matching the command, the rollout has started lying, and you can catch it the moment it does. Covered it in my article for @BotNewsAI #ai #tech

Often, robot demos make me a little suspicious. The Genesis AI Eno writeup made me trust the numbers instead, which is the rarer reaction. Two details did it. They grade their policies in simulation but don’t train on simulated frames, so a good score can't be the model memorizing the simulator instead of learning the task. That is a small decision with a lot of self-restraint behind it. And the hands: a 1:1, twenty-joint, soft-skinned hand isn't an aesthetic call, it's what lets gloved human demonstrations transfer without a retargeting step mangling them on the way in. The body around those hands is close to an afterthought, on purpose. Wheels, a folding panel tower, no legs. They kept the part of the human form the world's tools are shaped around and dropped the part they aren't. Covered in my article for BotNews: the hand, the brain, the 3 ms control loop, and the simulator they handed to the public while keeping the model for themselves. #AI #tech

Genesis AI just answered one of robotics' oldest arguments by ignoring half of it. Do humanoids need five-fingered hands? Eno says yes, and builds a 20-DoF, 1:1, soft-skinned hand to prove it. Do they need legs? Eno says no, and rolls in on wheels. The tell is in the data: 200,000 hours of human hands, transferred with no retargeting, plus a control stack tuned to 3 ms so human motion counts as supervision instead of teleop. The rest, including the simulator they open-sourced and the model they didn't, is in the piece. #Robotics #AI #Robots #Tech

@BrettKrieger12 @eliano Legend has it, if you bring a farmer near it, it will build him an ontology.

Show me your best office memorabilia Mine is this Alex Karp signed hat from 2024 when @eliano brought back the merch 🧢🔮

@dong1505lin @seeedstudio Sooo good 🦾

🎮 Teleop in action — reBotArm B601 + XenseFlare Gripper. Master-slave, low latency, all business. 🤖⚡🦾 @seeedstudio #PhysicalAI #Robotics #tactile #reBotArm #seeedstudio

@DominiqueCAPaul Pasta, Pesto, and Papers is fancy.

Over the last few years, I’ve met so many people working on robot learning across Zurich’s academic labs, start-ups, and big tech. What keeps surprising me is how little exchange happens between these groups. To change that, I’m starting a Robotics AI Paper Club for researchers, engineers, and anyone looking to get deeper into the field. Wrote a paper or method yourself? → Present it! Read a paper others should know about? → Show us what you liked and why it’s worth reading! First edition: this Thursday. Drinks, pasta & pesto are on me. Luma link below 👇🏼

@PalantirTech This is so satisfying 🤤

“Pointing an LLM at hundreds of disconnected, ungoverned databases gets you a system that hallucinates, is insecure, and unauditable. For something as consequential as our nation’s agricultural data, that is not just useless — it’s dangerous. The Ontology has been the key to delivering AI-enabled technology to every farmer in the country.” At AIPCon 10, the USDA demonstrates how the Ontology now underpins national food supply security.

DynaFLIP is a robot vision backbone trained to see what static encoders miss. Not just what is in the scene, but what is about to matter when the world moves. The result is an eye trained on consequence...a perception system that gives downstream robot policies something sharper than object recognition: prediction #Robotics #AI #tech