What is true on Control?

Walmart just shipped a better permission model for AI agents than a lot of companies have for their internal ones. Today when an agent shops for you it signs in as you, so every order looks like yours. Agent Profiles, launching in the next month, change that. - each agent gets its own profile inside your account, and its orders show up separately - you pick approve-every-order or a spend limit ($50, $100, $200 are their examples) - Walmart can still ask for approval even inside that limit - the agent never gets your card number and can't add or change payment methods - it can find your usual items through their MCP gateway without seeing your purchase history - you can delete a profile anytime, and agents that break the terms get blocked Now think about how most internal agents get rolled out. a shared service account or somebody's own token, broad access, one log where the agent's actions and the human's are mixed together. What's worth copying 1. one identity per agent, never the user's login 2. the limit enforced by the system the agent calls, not by the prompt 3. a step-up check the platform can trigger even inside the limit 4. secrets stay platform side, the agent gets a handle 5. answer the question, don't hand over the history 6. revoke one agent without touching the person's access Anthropic's Claude Duet launched the same day with the agent-side version. it shows you exactly what it's about to do before it sends, pays, signs or deletes, and some things like moving money between accounts are off-limits even if you say yes. merchant side and agent side landed on the same shape in one day. if your agents still run on a human's credentials, that's the gap

A Python pipe buffer was holding camera frames until 64 KB had piled up. That quietly added hundreds of milliseconds to our π0.5 rollouts. New from @castorhat: how we found it, and what changed on the robot once it was gone. https://t.co/xTAueR4wOV

Why is nobody talking about this? ToddlerBot is a 0.56 m, 3.4 kg humanoid robot built at Stanford by Haochen Shi, Weizhuo Wang, Shuran Song and C. Karen Liu. Its goal is to make robot learning cheap and easy to reproduce. The full hardware costs under 6,000 USD. Hardware - 30 active degrees of freedom: 7 per arm, 6 per leg, 2 in the neck, 2 in the waist - Dynamixel servos (XC330, XC430, 2XC430, 2XL430 and XM430 in the current open-source configuration) - 3D-printed structure: a full repair takes about 21 minutes of printing and 14 minutes of assembly - Jetson Orin NX 16 GB, two fisheye cameras, an IMU, two microphones and a speaker Sim-to-real - Zero-point calibration and motor system identification produce a digital twin of the robot - Walking: an RL policy trained in MuJoCo MJX and transferred to the real robot with no extra training, up to 0.25 m/s in any direction and 1 rad/s in place - Push-ups and pull-ups: keyframed motions, also transferred with no extra training Manipulation - RGB diffusion policies trained on 60 teleoperated demonstrations per task - Real-time onboard depth estimation at 10 Hz from the stereo fisheye cameras - A policy trained on one robot runs on another, and two robots tidied a room together Measured limits - Payload: 1,484 g, about 40% of its body weight - Endurance: 19 minutes of walking before motor heating affects stability - Durability: up to 7 falls before a part breaks - The cartwheel works, but its success rate is still low

Q3 Shareholder Update → https://t.co/u0UcDOuMNa Highlights – FSD Supervised attach rate grew to over 75% of new vehicle deliveries in NA – Unveiled the next-gen Roadster – Record deliveries in Canada, Australia, Japan & Taiwan – Tesla Semi now in volume production. Top variant can go up to 500 miles at a full 82,000 lbs while achieving efficiency of 1.7 kWh/mile – about a third of the energy a comparable diesel truck burns for the same load – Ended the quarter with the largest backlog for our passenger vehicles in 4 years! FSD Supervised – 4 new approvals since Q2 (Croatia, Slovenia, Czech Republic, Slovakia) – FSD is now live in nine EU countries & used by over 100,000 customers logging more than 160 million kilometers since initial approval Robotaxi – Deployed Cybercab into our Austin fleet – Hit nearly 2 million cumulative unsupervised miles, 8x growth in the quarter – Austin service now runs 6 am to midnight, with wait times continuing to come down as we add cars & improve the orchestration algorithms – Added Grok to Cybercab with Grok Bot & Connectors, letting you interface with your inbox, calendar, files, chats and tasks, all by voice. Transport, office & living room in one Robotics – Started production of @Tesla_Optimus on our high-volume lines in Fremont. These are the first production-quality bots we've built, proving that the current manufacturing process for Optimus is suitable for a commercial product SI Compute – On track for 400 MW of training compute by year end, feeding both vehicle & humanoid autonomy – Austin Fab construction continues, equipment commissioning planned for 2027 Battery – Battery supply is still the limiter on how fast we ramp vehicles globally, so we're expanding on every front: pack capacity in Berlin, cathode and lithium refining in Texas, LFP cells in Nevada – Shipped the first Megapacks built entirely with our own LFP cells – Increasing 4680 output to support ramp of Cybercab, Semi & Model Y Energy – Megafactory Texas is up & running, with Megapack 3 production started – Highest-ever order rate & backlog for energy storage Grid constraints & power availability are making Megapack the answer for SI infrastructure demand: it excels at supplying large data center loads, smooths out demand spikes, helps new projects meet grid connection rules & makes the grid itself more stable All with less local fossil fuel generation Supporting Infrastructure – Added 2,100+ net new Supercharger stalls, up 14% year over year

This might be one of the most minimalist snake robots ever built. • One motor. • No dozens of actuated joints. • Crawls, climbs between walls and swims. It's called SAW (Single Actuator Wave-like robot), developed by Dr. David Zarrouk's Bio-Inspired and Medical Robotics Lab at Ben-Gurion University of the Negev. How it works • A single motor rotates a helix inside the robot's body. • 3D-printed links follow the helix to create a continuous wave. • The links push against the surrounding surface to propel the robot. • Front wheels handle steering. The numbers • 57 cm/s on flat ground • Around 5× faster than similar wave robots • Around 8 cm/s in a tunnel, with contact against both walls • Around 6 cm/s while swimming in its waterproof version One gait, multiple environments • Gravel, sand and grass • Obstacles and narrow passages • Pipes, tunnels and water The same wave-like motion works across these environments without changing the gait. Why use one motor? Traditional snake robots often rely on 10, 20 or 30 motors. SAW uses a single actuator, reducing the number of moving parts and making the design lighter, simpler to manufacture and suitable for 3D printing. Possible applications • Search and rescue in collapsed buildings • Inspection of pipes and tunnels • Medical imaging and biopsies inside the digestive tract, with a miniaturized version around 1 cm wide or less The research was published in Bioinspiration & Biomimetics under the title Single actuator wavelike robot (SAW): design modeling, and experiments. What caught my attention is how the helical mechanism generates the motion with just one motor. The mechanical design does most of the work

My wife and I first video edit ever lol @maticrobots breaking vacuum history being the first robot vacuum in the world to be controlled, purely with thoughts! I am so stoked and honored they allowed me the chance to try this out! https://t.co/JQp5cp7rKw

Follow Gemini 4 Argon's report, I implemented their robotics harness. Gemini did a zero-shot bimanual handover. Now open source 🤖👇 https://t.co/N6oUOQY6u9

Today I’m excited to share that Optivolt is unstealthing with a $32M Series A. Solar growth continues to outpace all other forms of energy production, but the granularity of control we get from deployed systems hasn’t changed in decades. So we’ve added a brain inside solar panels, opening the door for a new unit of optimization and control.

What does it take to build a humanoid robot that can walk without falling? Dropbear recorded 128 walking tests with zero falls. But every test ran in simulation, with external pushes turned off. Developed by Hyperspawn and Point Blank, Dropbear is an open-source humanoid robot. The entire robot is available on GitHub, giving developers access to the project and a chance to study how it works. The next step is testing how well it handles disturbances and unexpected changes in the real world

Asimov 1 is an open-source reference humanoid robot. It ships as a complete DIY kit. $20,000 total, delivered to your door. https://t.co/OzL6JI3ZDB https://t.co/mZt5hidLLw

I turned @asimovinc's open-source Asimov 1 into an interactive 3D robotics workshop. Built from 1,184 real CAD parts, with Menlo's own walking policy running in a live physics simulation in your browser. 🟠 BUILD the robot using Menlo's assembly instructions. 🟠 UNDERSTAND its mechanisms, including the parallel ankle linkage. 🟠 TEST its walking policy, apply a push, and freeze the simulation to inspect every joint. Built with @threejs. Fully open-source. Try it yourself: https://t.co/EeZ4Bn6WQa

I kneel... training @asimovinc to transfer from lying on the ground (back/belly/side) to a half kneel, with hopes of translating next from a half kneel to full stand. Trying to find the best way to get up off the ground. https://t.co/TPz46juuvu

Last year I trained the advantage-conditioned VLA for π*0.6 during my internship @physical_int. Now, I have a much improved recipe. Introducing ✨Advantage Guidance✨, a performant RL method with stable advantage-conditioned supervised training and contrastive guidance sampling https://t.co/AyIGA7qQqf

Humanoid robot market: $5.41B in 2026 → $50.27B by 2035. That’s a projected CAGR of 28.1%. Asia-Pacific held 42.6% of the market in 2025, ahead of North America at 29.3%. Key application areas include manufacturing logistics healthcare and education. The forecasts vary across research firms but the market is expected to grow over the coming decade. Sources: • MarketsandMarkets (July 2026) • Fortune Business Insights • Grand View Research • Goldman Sachs via Investing .com

Introducing Embodied First Exam: One line of code to run coding agents in 1,090 embodied tasks across 31 simulation suites and 44 robots. Can your agent go far beyond pick-and-place: Puzzles with spatial constraints; Olympic sports with multi-robot collab; Real-time eval, where the world won't pause; Dynamic, agile, whole-body control; AutoResearch with sim2sim Try your own agent: harbor run -d embodied-first-exam -a <your_own_harness> -m <your_own_model>

If we’re entering the era of Robotics APIs, we need to start thinking about the security threats that come with them, just like we’ve seen with LLM APIs. Except this time, the models act in the physical world. https://t.co/qE9ghIMw5H

@EkaRobotics has raised a $150M Series A. Generality v/s Performance is the fundamental tension at the frontier of robotics. Generality without performance is just a prototype. Performance without generality is just a single-purpose tool. Customers shouldn’t have to choose. Eka breaks the tradeoff. Powered by our Vision-Force-Action (VFA) model, we deliver the performance and versatility customers need to put robots to work every day. Eka is built on three convictions: ⚡️Force is the language of manipulation. 🚀 Reinforcement learning is how dexterous manipulation scales. 🎂 System 1—fast, reliable physical execution—is the bottleneck to solve. With this funding, we will scale our model and accelerate customer deployments. Grateful to be building alongside a dream team and investors who share our ambition.

@EkaRobotics has raised a $150M Series A. Generality v/s Performance is the fundamental tension at the frontier of robotics. Generality without performance is just a prototype. Performance without generality is just a single-purpose tool. Customers shouldn’t have to choose. Eka breaks the tradeoff. Powered by our Vision-Force-Action (VFA) model, we deliver the performance and versatility customers need to put robots to work every day. Eka is built on three convictions: ⚡️Force is the language of manipulation. 🚀 Reinforcement learning is how dexterous manipulation scales. 🎂 System 1—fast, reliable physical execution—is the bottleneck to solve. With this funding, we will scale our model and accelerate customer deployments. Grateful to be building alongside a dream team and investors who share our ambition.

A bit of background on this blog: Astra demos made me wonder what’s left for robotics research. I told LLM friends “it’s too slow,” but they pointed to efforts toward 50 Hz. I had no reply. A morning of thinking led me to this blog. TL;DR: https://t.co/eneEB4ECeS https://t.co/HeWbmWDppG

@asimovinc Amazing. How much of the stack have you actually opened up?

@EkaRobotics has raised a $150M Series A. Generality v/s Performance is the fundamental tension at the frontier of robotics. Generality without performance is just a prototype. Performance without generality is just a single-purpose tool. Customers shouldn’t have to choose. Eka breaks the tradeoff. Powered by our Vision-Force-Action (VFA) model, we deliver the performance and versatility customers need to put robots to work every day. Eka is built on three convictions: ⚡️Force is the language of manipulation. 🚀 Reinforcement learning is how dexterous manipulation scales. 🎂 System 1—fast, reliable physical execution—is the bottleneck to solve. With this funding, we will scale our model and accelerate customer deployments. Grateful to be building alongside a dream team and investors who share our ambition.

Ropedia Super Week, Day 1 | Ropedia W0: Different Robots, One World Model

Ahead of launch, @robocurve evaluated Dream-1 independently. Result: a new Pareto frontier for robot control. 16x cheaper, 1.7x faster, and better performance (59 vs. 48 on RoboDojo-RC Tier 1) than the previous best alternative. LLMs can plan. Robots still need a cheap, fast, and general System 1 to act.

This might be how machines learn to walk blind. No cameras. No LiDAR. The Noetix N2 (1.2 m, 33 kg) climbs 20 cm curbs using feedback from its joints and an IMU that acts like an inner ear. Every 20 ms, a recurrent neural network reads how the body moves and adjusts its next step based on what it feels. The policy was trained in simulation in just 5 hours on a single GPU. On the real machine it handles: • 15 cm steps • 20° ramps • 20 cm curbs • Uneven stone paths The system relies on proprioception, sensing the body's own movement instead of looking at the terrain. What stands out to me is how much information the joints provide when vision is unavailable.

AI can think. AI can talk. AI can get things done. Today, we're giving Fo a way to feel and control the physical world. - a head shake and a reminder in a lamp to get you going - nudge your vacuum cleaner for a deep clean - make your cli call you for updates Introducing Fo MCP. AI has escaped the screen.

Your phone probably costs more than this humanoid robot. Zeroth 01 is an open source humanoid 40 cm tall with a parts list starting at $350. Most of the frame is 3D-printed Feetech servos drive the joints and you control it in Python. One developer already built one with 16 servos a Raspberry Pi 4 and a battery. It can kneel wave and do push ups. Walking is another story. Five walking controllers have been trained in MuJoCo and none of them runs on that physical robot yet.

Hard lighting cut our expert-only π0.5 checkpoint's success roughly in half. The same lights cost the full fine-tune nothing. New from @castorhat: the fine-tuning ablations behind our IROS demo. https://t.co/JciqcCBMYy

Every robot already carries contact sensors: its own joints. When a robot touches something, its joints drift slightly off their commands, and the encoders pick it up. Legged robots and humanoids already leverage this signal to walk blind - but is it enough for blind precise assembly? We find that it is! Our policies can insert pegs, mesh gears, and thread nuts using only the robot's joint positions - no camera, no tactile, and no object poses. And the peg policy works zero-shot in the real world! 🧵 w/ my amazing co-first author @younghyo_park, and advised by @kushalk_ and @pulkitology.

‣ 20 Predictions That Will Change How You See Robots Forever ➤ 1. More robots than cars ➝ Billions of humanoids in use, often several per household. ➤ 2. Elder care becomes the biggest market ➝ Aging populations make assistance, mobility help and companionship the main use. ➤ 3. Human-level dexterity ➝ Ultra-sensitive hands that can handle an egg or a surgical tool. ➤ 4. Robots as a subscription ➝ People rent "robot labor" by the hour or month instead of buying the machine. ➤ 5. Days of battery life ➝ New batteries and wireless charging floors. ➤ 6. Robot law ➝ Rules on liability, insurance and privacy, plus debate over legal status. ➤ 7. Nearly human robots ➝ Realistic skin and faces in hospitality and care, mandatory mechanical look in industry. ➤ 8. Work and taxes reinvented ➝ Robot taxes, shorter workweeks or universal basic income. ➤ 9. Robots building robots ➝ Factories, mines and construction sites run almost entirely by humanoids. ➤ 10. A space workforce ➝ The first builders on the Moon and Mars. ‣ Part 2: 10 New Predictions ➤ 11. Mind control ➝ Brain-computer interfaces let people pilot a robot remotely, like a second body. ➤ 12. Artificial muscles ➝ Motors give way to soft fibers for silent, fluid movement. ➤ 13. A tutor for every student ➝ Teaching robots adapt to each child's pace and support human teachers. ➤ 14. Robot rescuers and firefighters ➝ First on the scene in fires, earthquakes and hazardous zones. ➤ 15. Precision farming ➝ Fruit-by-fruit harvesting, plant care and fewer pesticides. ➤ 16. Robot sports and entertainment ➝ Sports leagues, stunt doubles and robot actors become common. ➤ 17. Custom personalities ➝ Voice, character and appearance customizable like an avatar. ➤ 18. Cybersecurity becomes critical ➝ Hacking a robot becomes a serious crime, with mandatory security certification. ➤ 19. Repairable, recyclable robots ➝ Modular design: you swap a part, not the whole robot. ➤ 20. Universal translators ➝ Every robot speaks every language, serving as guide and interpreter anywhere. ✓ Key Takeaways • These are educated guesses, not certainties. • In 75 years, unforeseen breakthroughs (or setbacks) could change everything. What do you think of these predictions?

Ropedia Super Week, Day 1 | Ropedia W0: Different Robots, One World Model

How to build a humanoid robot at home

You can build a dexterous robotic hand for just $314. Prefer it ready to use? The fully assembled version costs about $720. Chestnut Robotics' Aero Hand Open weighs 389 g and has 7 active degrees of freedom across 16 joints, 3 of them in the thumb. Here's the trick cables run through the fingers like tendons so one motor bends several joints at once. Everything is open source CAD STEP files, 3D-printable parts, firmware and a MuJoCo simulation model. It's still a research prototype and its long term reliability hasn't been proven yet.

This flight shows the power of crewed-uncrewed teaming and the advantage it provides our warfighters. We must test often, learn fast and give commanders what they need, when they need it. https://t.co/R7drAByBS5

@mehul Matic is doing useful stuff so that I have more free time working on FSD.

A robotic arm that learns physical tasks by watching you demonstrate them. Meet the SO-101, an open-source robotic arm supported by Hugging Face's LeRobot. ‣ 3D-print the parts and assemble the arm ‣ Demonstrate a task using the leader arm ‣ Record movements and train a neural network with LeRobot ‣ Let the follower arm perform the task on its own What catches my attention is how accessible this makes robot learning. You can experiment with imitation learning on real hardware without building an entire robot from scratch.

Menlo SDK is now open-source. - Turn your ideas into new capabilities for your Asimov 1 - Control its movements and read its state from your code - Use its camera, microphone and speaker in your applications Start building on humanoids: https://t.co/STuP6jduwT https://t.co/UlwqRhwEF6 https://t.co/AS9JsWocFQ

You don’t need to build a humanoid robot from scratch to start exploring robotics. This open source robot is available on GitHub. You can study the design explore the code and see how the different parts work together. For robotics enthusiasts and developers projects like this are a great way to learn by building. The best part? You can start with what the community has already shared. Would you build your own version?

You don’t need to build a humanoid robot from scratch to start exploring robotics. This open source robot is available on GitHub. You can study the design explore the code and see how the different parts work together. For robotics enthusiasts and developers projects like this are a great way to learn by building. The best part? You can start with what the community has already shared. Would you build your own version?

An agent generates trajectories for carrying a kettle and pouring water. Dyna2-style RL handles low-level control with precision and robustness to disturbances—beyond motion planning alone, as Qia Yuan noted. Agentic planning + conditioned RL is a huge frontier. https://t.co/GzqaeL3iXE

🚀RP1 is officially here. 🌍Putting control of robotics back in developers’ hands. Introducing RP1 (ROBOTO 01) by RoboParty—a high-performance, fully open-source humanoid robotics platform for frontier robotics research and embodied AI model development. 🤖 Open across the full hardware and software stack: • Robot platform: mechanical CAD, bill of materials, and assembly documentation • Actuators: in-house ROMOMO joint designs and related technical resources • Control: electrical systems, firmware, low-level drivers, and motion control implementations • Development: simulation models, SDKs, data processing tools, and training tools • Engineering foundations: technical documentation and research materials Open the black box. Understand the system. Make it your own. A deviation in motion can originate in the model, control policy, actuator response, or mechanical structure. RP1 opens up the design and implementation of these layers so developers can trace problems, modify the system, and validate changes on real hardware. Open-source algorithms for advanced motion control RP1 has demonstrated continuous walking, recovery from disturbances, getting back up after a fall, and human motion tracking. UFO and MimicLite connect motion learning, control policies, and execution on real hardware. The open toolchain connects data collection, simulation training, hardware deployment, and experimental validation—supporting joint iteration across models, control, and hardware. From RPO to RP1, we’re turning one team’s engineering experience into a starting point for many more. Opening the future of embodied AI to everyone ready to explore it. 🔗RP1 on GitHub: https://t.co/kMqFLi3eJ3 #RoboParty #RP1 #OpenSourceRobotics #EmbodiedAI

Trying to train a fall recovery policy for the @asimovinc humanoid Getting up is hard! https://t.co/GiYYMEyPCJ

Exploration is hard for RL when training high-DoF dex hands ✋ X-Reset makes generalist object-centric RL easier by resetting to human hand-object states 🙋‍♀️ We mitigate the exploration problem, and train a single policy to manipulate a variety of objects to any goal pose 🧵 https://t.co/MtP0URF7nu