
RT @stash_pomichter: have been super impressed with taerim and tiantian’s ability to get robust policies running on real use cases. massi…

The open-source framework for agentic robotics. Program atoms, not bits. Join: discord.gg/dimos

RT @stash_pomichter: have been super impressed with taerim and tiantian’s ability to get robust policies running on real use cases. massi…

Would you let a robot give you a tattoo? He did. @stash_pomichter had an awesome San Francisco robot party to celebrate new office with a ton of robots.

TATBOT come get real tattoos from our robot running dimOS
Tatbot's new rig: a UFACTORY xArm 7 running DimOS, tattooing the Dimensional logo on silicone skin. See it live tonight at the Dimensional Office Warming in San Francisco. luma.com/dimens-uphr

NYTimes covered our robots taking over SF and the subsequent restraining orders we had to take out against some passionate community members. Fun read. nytimes.com/2026/10/27/techn…

We're hosting another Physical AI Hack this weekend, November 7–8 at @fdotinc in San Francisco. This time, we're partnering with @dreamlabs_ai and their new world action model, Dream-1, which can do tasks zero-shot. @livekit @nvidia @huggingface @dimensionalos @enact_labs are joining us too. @livekit is the real-time layer: connect your robot to human operators and cloud models with ultra low latency, then give it a voice agent so you can talk to it. You'll get LiveKit credits for real-time streaming and voice agents. Other technical partners: @_lightcompany @mirdainsystems @SGhashghaei @spcxstarship Prizes: 1st place: $2,000 + a Metal Arm + credits 2nd place: $1000 + a Maker Arm + credits 3rd place: $500 + a Reachy Mini + credits Sign Up: luma.com/pah There are two tracks: Hill climb (New Track): This is a new format where everyone works to improve the model's accuracy on the same task. We'll announce the task soon and provide the props. You'll climb the leaderboard through fine-tuning, DAgger and a System 2 agent harness around Dream-1, using LiveKit and Dimensional OS. Creative (Zero shot): Build the most creative project you can with Dream-1, LiveKit and Dimensional OS.

Introducing CandyBench: a new frontier eval in applied robotics we got 7 robots to give out 3057 halloween candies and graded them on performance here's what happened:

come play with some robots and meet our residents! 🚀🦾
We’re filling Warehouse 1 with 1000 people come through and see some robots this Friday luma.com/dimens-uphr

🇺🇸 A San Francisco startup is PAYING $20 an hour for people to WALK its robot dogs 🦮 The company needs humans to guide the 33-pound robots through city streets to collect real-world data. The machines still overheat or stall, forcing walkers to haul them back. AI agents can’t handle the hardware alone yet. Turns out robots need dog walkers before they can replace them 😅 Writer: Lucas

@nytimes didn’t eviscerate us 🎉 One week of data collection, 4 death threats, and 1 restraining order. Overall comments are supportive but clear most unprepared for robot augmentation of human labor at scale. Thanks @kashhill for the coverage nytimes.com/2026/10/27/techn…

Decided to share some of our internal experiments off of the Argon + Astra hype. Much work to do! More soon.
Has Argon solved robot manipulation? Or do the demos fail as task complexity scales We benchmark Argon, Astra, etc on complex manipulation tasks on real hardware + 1000 simulation runs Can they one shot complex tasks? Or is a physical harness and tools via dimOS still needed?

SAVE THE DATE (November 7th) Come join us for a workshop where you will learn how to control a robot dog with the force alone, no touching! (along with a lil computer called an ESP32) There will be an even bigger game based event later and if you want to participate, you will need an ESP 32 and the knowledge of how to control the robot This robot dog was granted to us by @dimensionalos who is building opensource operating system for our robotic future! Link is in the next tweet

dimOS in the wild
I controlled a Robot with my RayBan Meta Connected my @Meta glasses to my Robot Arm so it can interact with objects > Glasses detect objects > Robot interacts with them Here’s how you can vibecode hardware too:

Last call to apply to the dimensional residency 🦾🚀
OPEN CALL TO ROBOT DEPLOYERS. T-7 to our residency kickoff. Get hyped. Last chance to apply. Free robots, warehouse space, compute, software support, and connections to customers across data centers, agriculture, construction, manufacturing, real estate, more

this is so cool! agents can now string together models into skills, like this one built with @dimensionalos
Took me a while to get @dimensionalos agentic robot control working reliably for this task. It’s very stable now! RGB-D (@RealSenseai) and YOLO detects objects. GraspGenX produces the grasp pose which is executed via path planning and some heuristics.

anyone interested in trying @huggingface Microduck in this sim playground before it arrives ? Has all the policies + agentic runtime + YOLO object detection + playground. Comment and I'll share the link

Took me a while to get @dimensionalos agentic robot control working reliably for this task. It’s very stable now! RGB-D (@RealSenseai) and YOLO detects objects. GraspGenX produces the grasp pose which is executed via path planning and some heuristics.