Mitshell Ramos

@raulb4s and @mbrq_13 testing teleop with HandUMI at the @0xnonhuman lab in Peru 🇵🇪, 7,250 km away from SF. This is part of the tests to make sure the IK works correctly and that the data collected with HandUMI feels like teleoperated data, but much cheaper. The complete software will be open sourced in the coming days! Data collection, teleop in sim and in real, data postprocessing, etc. Stay tuned! Want to collaborate on HandUMI or build your own? Join our Discord: discord.gg/V47FuUkFA

Why do people keep collecting data with teleoperation when a bimanual robot setup costs more than $10k? Isn't there a solution that gives you the same data quality without the robot? At @robonet_, we want to build the Internet of Robotics. As part of that mission, we built HandUMI, a hand-worn data collection device for bimanual arms with parallel-jaw grippers. Specs per unit: - 276.5 grams - $110.68 - Encoder-precision gripper aperture - Integrated wrist camera - Tracking with the VR headset of your choice (Pico/Quest) - More than 5 grippers supported (Piper, Trossen, ARX, Soft gripper, Dream gripper) The best part: all the hardware is open source! Thanks @fdotinc for the hardware lab and the space to make this possible. ft. @alvax64 @leoperzz @raulb4s @mbrq_13 @BryanBRstds @Aryan_Mangla_ , and the rest of the @0xnonhuman team.

Starting with the fundamentals Prototype Version 0 AI, Software, Hardware A small team, 9 months Designed and assembled in Paris at @UMA_Robots

Fable 5 is back.

@Rush26agarwal Let's talk!!

If you have ever worked around blue collar industries in the following regions, DM me! - Southeast Asia: Indonesia, Vietnam, Philippines, Thailand, Cambodia - Latin America: Brazil, Mexico, Colombia, Peru, Argentina, Guatemala - Middle East and North Africa: Egypt, Morocco, Jordan, Tunisia, Saudi Arabia, UAE - Sub-Saharan Africa: Nigeria, Kenya, South Africa, Ghana, Ethiopia - Eastern Europe: Poland, Romania, Bulgaria - Balkans: Serbia, Bosnia and Herzegovina, North Macedonia - Southern Europe: Portugal, Spain, Greece - Western/Northern Europe: Germany, France, United Kingdom

Robots are the bottleneck in scaling robotics, and learning from human video promises to solve it. But how can chaotic human data ever measure up to sanitized, lab-made teleoperation data? Introducing Do as I Do: establishing a much needed correspondence between human videos and dexterous robot data. Some fun insights below: 🧵

New work with @nvidia: evaluating robot policies entirely inside a world model. The policy acts, the model imagines the consequences, and the imagined evals predict real-world results. 🧵 real vs world-model rollout side by side📷

It was an incredible experience to be part of the competition on ICRA 2026 in Vienna and engage with the robotics community. I truly enjoyed the opportunity to learn from the competition, connect with people, and see the latest advances in robotics

We won 1st place in Logistics Picking track at the #ICRA2026 Vienna Site of What Bimanuals Can Do 2026 @WBCDCompetition It focused on whole-body humanoid logistics picking task The journey and experience was just amazing! @leoperzz @autobrik @raulb4s @mbrq_13 @ubillus83797

How does test-time scaling impact robots? We find that larger models, more thinking, and more context help significantly for some prompts but not others. Like LLMs, we can also train a router to for a better performance/latency tradeoff! Paper: jadee-dao.github.io/direct/

The Demis Hassabis HUGE* Conversation (in full) 00:00 What is the hardest problem AI has already solved? 12:30 What is the cutting edge of drug discovery with AI? 21:53 Why did Demis say he “would have left AI in the lab longer”? 43:09 How should militaries use AI? 50:13 What can humans do that AI won't? 58:17 What does Demis Hassabis want his legacy to be? (And 1:04:40 Can I beat Demis at Jenga?) Recorded March 5, 2026 in London.

Interesting...👀

What didn’t exist when you needed it and why haven’t you built it yet? 🤔

@Tancrededib Hey 👀

I’m hiring someone who: - has taste - loves people - enjoys LDN & SF - wants to shape the future DMs are open

Usually, we expect more diverse data >> less diverse data. Cross-embodiment transfer seems to benefit from paired data across embodiments, more so than increasing diversity. Webpage & code: data-analogies.github.io Paper: arxiv.org/abs/2603.06450

Researchers trained a humanoid robot to play tennis using only 5 hours of motion capture data The robot can now sustain multi-shot rallies with human players, hitting balls traveling >15 m/s with a ~90% success rate AlphaGo for every sport is coming

Asimov (@tryasimov) pays households and businesses worldwide to record their daily routines, generating thousands of hours a day of diverse human movement data to train humanoid robots. They've built a global network, along with the full stack, from proprietary collection hardware to annotation tooling, and are already providing data to the largest robotics companies in the world. Congrats on the launch, @lyemningthou and Anshul! ycombinator.com/launches/PeH-a…

Foundation models are getting "smarter," but we’re still stuck in the "demo era." A smooth video doesn't mean a robot is ready for the real world. How is the industry tackling this "Validation Gap"? 🧵 This is gonna be a long one ❗️❗️ [Save this so you can find it when you need it]

I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then: - the human iterates on the prompt (.md) - the AI agent iterates on the training code (.py) The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc. github.com/karpathy/autor… Part code, part sci-fi, and a pinch of psychosis :)

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow. Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes. As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now. It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.