Drift v1.0.24 is live!
for robotics engineers tired of re-explaining their project to agents every command.
Shipped:
🧠 Project context - drop a DRIFT.md or SKILLS.md, it's used on every step
🤖 MuJoCo + Gazebo, end-to-end - URDF, MJCF, plugins, launch, debug, run, train
⚙️ Multi-step builds that hold context - robot -> world -> sim -> tune, one prompt
The best founders I admire are unreasonable people.
Unreasonable about the problem.
Unreasonable about the timeline.
Unreasonable about what's possible.
Reasonable people adjust to the world.
Unreasonable ones refuse to.
Last one month at San Francisco was one of those very fast and full of learning month ever in my life. And honestly, it was one of those months that sets the tone for everything after!
And the most fun part was that here in San Francisco, nobody was asking whether robots or AI agents would work anymore.
That question is already so behind.
The only question I hear in SF is how fast can we convert our vision into reality and that's exactly the kind of place @godrift_ai needs to be 🚀
The worst career advice I ever got was to have a backup plan
A backup plan is just a slower way of quitting.
If you have an exit, you'll use it.
Burn the boats or don't start.
Drift v1.0.24 is live!
for robotics engineers tired of re-explaining their project to agents every command.
Shipped:
🧠 Project context - drop a DRIFT.md or SKILLS.md, it's used on every step
🤖 MuJoCo + Gazebo, end-to-end - URDF, MJCF, plugins, launch, debug, run, train
⚙️ Multi-step builds that hold context - robot -> world -> sim -> tune, one prompt
I want to offer some unsolicited advice to computer vision researchers jumping into robotics. Don't focus too much on VLMs, VLAs etc. That's fine, but the real action is at the sensorimotor level. Most of the open problems in robotics are in manipulation, which is about hand-object interaction, and contacts and forces are central. Proprioception and tactile sensing are as important as vision. Don't get seduced by cherry-picked demos. You can't do robotics without doing robotics.
@cyber_razz the credibility problem isn't the hypocrisy. it's that they probably know better than anyone that a coordinated pause won't happen. which makes you wonder what the ask is really for
@unusual_whales the company closest to the frontier calling for a pause is either the most credible warning or the most effective moat depending on how cynical you are
@cb_doge space-based solar has been theoretically viable for decades. what's actually different now that makes this a near-term conversation and not a sci-fi one.
Got a chance to sit down with @Scobleizer
for dinner yesterday - shared how at @godrift_ai
we are solving general purpose robotics through the ACTUAL bottleneck.
So happy to share our story with him.
Truly a gem of a person in valley to get advice from :)
Good morning AI and robot fans. (Which really are the same thing).
Did you miss how big a day yesterday was in AI? https://t.co/8L5xphk0qQ didn't.
You saw this coming, didn't you? @cixliv did.
While I got you, I am not paid by @TownAI (a new system that watches everything I do and helps us) but it was the big winner of yesterday for me. And that's saying something, because yesterday was so huge.
And last night had dinner with @Sanjil, who is building a new agentic simulator and infrastructure for people to take robots to the next level.
It'll be out in a couple of months, but he educated me a lot on just how hard it is to get robots from doing a few tasks, like these Unitree robots are doing, as impressive as the tasks are, to being truly generalized where it can do thousands, or even millions of tasks.
Better ways to teach robots to do a lot more than dance coming soon.
Robotics is a long game. If you're in it for a quick exit you're in the wrong field.
I’m here because the problem is genuinely hard and that's the only reason i need.