Patrick retweeted
ULTIMATE BOTS SEASON 2 IS HERE. 🤖🏆
4 teams. 6 events. $100K on the line.
Teams will earn points across 3 disciplines:
🥊 Martial arts
💃 Dancing
🏁 Obstacle course
Season 2 hits F1 Austin → TwitchCon → IEEE Humanoids → CES → Big Game Weekend → NVIDIA GTC.
Captains + teams announced soon.
Follow for reveals, ticket drops & live streams.
Patrick retweeted
We did incredible engineering to do something incredibly stupid. Last night at @sushitrash's show at @ChaseCenter, our humanoid raised a middle finger to Joji and all of San Francisco — in front of 15,000 people.
In 4 hours, we fixed a broken robot hand, designed and manufactured hand mount, retargeted my motion from video using Ultimate Bots Studio and deployed with the latest NVIDIA machine learning policy live on stage.
For over a year we've been putting humanoid robots into the most unpredictable environments there are — live crowds, every week — with zero injuries or significant accidents. I'm proud to work with @_patrickrose and @emerson who have the engineering depth and the audacity to take impossible projects and deliver them.
Some may say it's not serious or complex enough, a waste of time. I believe an important part of integrating robots into society is making them part of our social norms — teaching them how friends may talk to each other, not a sterile idea of the world. Most people only meet robots through headlines, and fear grows in that distance. Seeing a humanoid live — dancing, fighting, flipping you off — turns that fear into curiosity. That's why we put them in front of crowds and hand them over at our events and hackathons, where anyone can train one themselves the way they want. I'm happy every time someone walks out as a friend of the robots.
San Francisco is the craziest city in the world and I love it. It's the only city where you can meet people and build projects this audacious. We love you San Francisco, and FUCK YOU!
Patrick retweeted
Training robots just got TikTok easy.
Ultimate Bots Studio lets you make dances, gestures, full motion flows in 3 easy steps:
1) Upload a video → create a motion
2) Stitch motions → build a dance
3) Export to robot and share with community
Try it -> link in the comments
Patrick retweeted
How do we train robots today? What’s changed so that anyone can teach them new moves?
This is what @DDobas broke down on the @TEDTalks stage today.
We’re moving from complex robotics pipelines to something much more intuitive: show the robot a move, and it learns.
The full talk drops in the coming weeks. For now, here are a few backstage moments from the UFB team in Vancouver, having way too much fun with it.
Thanks @bilawalsidhu for giving us the stage!
Patrick retweeted
what the Fuck arxiv.org/html/2603.21852v2
Patrick retweeted
New League. New Website.
Your favorite world-famous humanoid fights are entering the next phase.
We’re launching the next generation of humanoid sports - the UFB Fighting League.
Now’s your chance to get involved.
Visit UFB.GG and join as a Pilot, Ghost, or Team Manager.
Patrick retweeted
Yesterday we held the UFB Ghost Trials at @CalHacks Hack Nights — hands-on trials where students learned to retarget motions from videos, train motion imitation policies (BeyondMimic) in mjlab, then competed in sim + real robot deployments!
This is about making advanced humanoid training accessible to students everywhere — not just labs. Top teams impressed, making progress towards permanent placement in the league. Congrats to team Molt, Justin and Alice, for taking the win 🚀🤖
Shoutout to @kevin_zakka (creator of mjlab — the backbone of our sim training) and massive props to @UFBots tech team: @emerson @_patrickrose and @DDobas for powering this and pushing the frontier forward!
Video of sim showdowns, real deployments, and winners below 👇
Patrick retweeted
Happy to have led the workshops at UFB Ghost Trials — covering video motion retargeting, training BeyondMimic in mjlab, latest papers like Sonic/BFM-Zero, plus team support, sim evals & real-robot deployments.
Thrilled seeing more students get hands-on with humanoid training! 🚀🤖
Yesterday we held the UFB Ghost Trials at @CalHacks Hack Nights — hands-on trials where students learned to retarget motions from videos, train motion imitation policies (BeyondMimic) in mjlab, then competed in sim + real robot deployments!
This is about making advanced humanoid training accessible to students everywhere — not just labs. Top teams impressed, making progress towards permanent placement in the league. Congrats to team Molt, Justin and Alice, for taking the win 🚀🤖
Shoutout to @kevin_zakka (creator of mjlab — the backbone of our sim training) and massive props to @UFBots tech team: @emerson @_patrickrose and @DDobas for powering this and pushing the frontier forward!
Video of sim showdowns, real deployments, and winners below 👇
Patrick retweeted
Last week, we ran 8 humanoid robots live at DJ Wukong’s Chinese New Year show.
5 on stage. 3 with VIPs.
I ran the full pipeline, from mocap to sim to real deployment.
Here’s what worked (and what didn’t).
Patrick retweeted
UFB Laboratory xitter.cf/i/broadcasts/1yNGabqqz…
Patrick retweeted
When you see the solution to AGI you will find that it was in fact so straightforward as to be obvious, and that it could have been developed decades ago
Patrick retweeted
(Low quality opinion post / feel free to skip)
Now that AGI isn't cool anymore, I'd like to register the opposing position.
- AGI is coming in 2026, more likely than not
- LLMs are big memorization/interpolation machines, incapable of doing scientific discoveries and working on OOD concepts efficiently. They're not sufficient for AGI. My prediction stands regardless.
- Something akin to GPT-6, while not AGI, will automate human R&D to such extent AGI would quickly follow. Precisely, AGI will happen in, at most, 6 months after the public launch of a model as capable as we'd expect GPT-6 to be.
- Not being able to use current AI to speed up any coding work, no matter how OOD it is, is skill issue (no shots fired)
- Multiple paths are converging to AGI, quickly, and the only ones who do not see this are these focusing on LLMs specifically, which are, in fact, NOT converging to AGI. Focus on "which capabilities computers are unlocking" and "how much this is augmenting our own productivity", and the relevant feedback loop becomes much clearer.
Patrick retweeted
Santiago@svpino21 Sep 2025United States
United StatesConnected via United States App StoreAccount-level information, not a live location or per-post device.
Over the last 10 years, I’ve learned something:
Every single person claiming that “Python is slow” tends to be a newcomer with no experience building software. They are usually dropouts of a bad JavaScript bootcamp.
More importantly, if you think that Python isn’t a “production-capable” language, you are definitely too early in your career.
Patrick retweeted
Thanks for bringing this teleop lens to life, this was so much fun and it worked flawlessly on #Spectacles!
@_patrickrose @vitl2907 @ArthurZBaney @vincent_trasto @SnapAR
What it feels to be a robot? 🤖 Dozens of people tried it this weekend at @LAHacks
🕶️ #Spectacles let you teleport into me 😯
🤓 While I learn, you can help me do stuff.
We also collect good training data this way.
And the best part, everyone had fun! Look at these happy faces ☺️
Human-robot interaction: looking bright 🤩
Thanks @LAHacks and @SnapAR team for having me!



























