Generalist retweeted
.@GeneralistAI CEO @peteflorence has been watching robot arms make the same kind of mistake: halfway through a task, they meander off to the side in a way they shouldn’t.
With a weak base model, he said, fixing it feels like playing Whac-A-Mole; every failure you patch makes room for the next one.
But that has changed as the base models have gotten stronger. Now, Pete recalled, you only have to give a “very small amount of guidance” on what not to do, and “it just won’t do it again.”
"If you're not touching and moving the world and you're a robot, what are you doing?"
@peteflorence is co-founder and CEO of @GeneralistAI, a company building general-purpose intelligence for the physical world through robotics foundation models. In mid-August, Generalist released Gen-1.5, its latest model, which Anthropic researcher Sholto Douglas has described as a "GPT-3 moment for robotics".
Florence's central claim is that dexterity, touching and manipulating the physical world, is the robotics equivalent of coding for language models: a broad capability with the potential to create a self-improvement loop in which robots build robots.
(2:24) GEN-1.5 and one-shot learning
(10:53) Dexterity in robotics
(27:38) Generalist’s founding thesis and what sets it apart
(32:17) Protecting simplicity
(42:15) Balancing general intelligence with commercial deployment
(50:52) Geopolitics, safety, and alignment
(1:03:37) Book recommendations
Generalist retweeted
Last week @willknight came by and got a preview of one-shot prompting and we had some fun improvisational moments with the robot. Thanks Will for helping capture the moment.
I'm usually wary about talk of "the ChatGPT moment for robots" because language is less complex than the physical world. After visiting @GeneralistAI, though, where I saw their robots perform impressive manipulation with just a prompt, I think you can see it happening in a limited way. (Thanks to @peteflorence and co for having me!) wired.com/story/generalist-a…
Generalist retweeted
Good question thanks Ani. Here's a video that gives a sense of the answer here about the effect of prompting:
- in the first part, the model is just babbling with no prompt in context
- at the end, we add a prompt for taking money out of a pouch (generalizing to the wallet)
Replying to @peteflorence @andyzengineer
Very cool work, Pete! I'm curious if you've tried an extreme version of this: no in-context example at all; just place objects in front of the robot and see if it can infer the task.
I suspect this will have non-trivial success rates, which would also allow you to figure out how much of the benefit is actually coming from the prompt (rather than pure zero-shot task inference + capability).
I remember Russ showed something like this in his Stanford talk on LBMs last year:
youtu.be/TN1M6vg4CsQ?si=-8J-…
We started planning yesterday’s @generalistai GEN-1.5 announcement about 3 weeks ago. Two weeks ago, already feeling whiplash from new results, I asked ChatGPT to create this image to share in our internal meme channel.
🤖 Made with AI
During a recent visit to Generalist AI, I watched a robotic arm improvise and use a banana as a tool. wired.com/story/generalist-a…
RT @felixwyw: At 10:06pm on Aug 3, I watched a robot do something I thought was years away.
We were working on few-gradient learning with…
This quoted post is unavailable.
Generalist retweeted
Most robot demos are scripted.
Generalist's GEN-1 is not.
> GEN-1 was doing a task
> Mid-task, an extra object was thrown into the bin
> GEN-1 quickly adapted to the new environment
> Still completed the task smoothly
This is the difference between a scripted policy (seen in viral launch videos) and a real foundation model.
GEN-1 was trained on 500,000 hours of proprietary, real-world dexterous manipulation data.
It has NEVER seen that exact scenario before.
This was the coolest demo at @AutomateShow
@GeneralistAI @FlexivRobotics
Generalist retweeted
These are the kinds of tasks that felt impossible to automate just a few years ago. and here they are showing it live
That's one of the coolest robotics demos! 😮💨
@GeneralistAI showed GEN-1 handling box folding and screw packing during @AutomateShow.
The boxes are cardboard with real variability: creasing, deformation, different configurations. GEN-1 retries when things go wrong. It adapts mid-task.
This is a jump from GEN-0, shown 3 months ago during GTC. GEN-0 handled rigid, predictable boxes. GEN-1 handles deformable ones with chaotic behavior.
The scaling is straightforward. GEN-1 trained on 500,000 hours of proprietary, real-world dexterous manipulation data.
Scaling laws are working. More high-quality real-world data leads to better physics understanding, better retry behavior, better generalization.
And the time to get a working demo is shrinking drastically.
They're not even at scale yet. They're just starting to see what happens when you pre-train on massive amounts of actual robot data.
~~
♻️ Join the weekly robotics newsletter, and never miss any news → ziegler.substack.com
Generalist retweeted
Replying to @GeneralistAI
@GeneralistAI mogging controls based robotics at Automate 2026 in Chicago
Generalist CEO @peteflorence says robotics models are in a transition period similar to the step change between GPT-2 and GPT-3.
They're "starting to cross over into levels of performance where these things are commercially viable for a number of different applications."
"We think this is a crossover point where we have a general model starting to be able to hit levels of reliability, speed, and improvisational intelligence where we can start to get these things out there."
"Very much like — you take a GPT-2-level model, you scale it to a GPT-3-level model, and certain types of commercial applications start to become viable."
Happy Monday. On today's show:
- @Will4Planet (Planet)
- @Dambisamoyo (U.K. House of Lords)
- @DrSamuelBHume (Stematic Labs)
- @Dkirtley (Helion)
- @peteflorence (Generalist AI)
- @marvinvonhagen (Interaction)
- @jordanbramble (Antares)
See you on the stream.
WWDC, Jobs Up Stocks Down, VC Horror Stories, Cars and Planes nitter.cf/i/broadcasts/1lJQRRjYN…
Generalist retweeted
Today marks the end of my first full week @GeneralistAI
Last Monday, I was given a challenge: use our GEN-1 model to teach a robot a task of my choosing, using the same no-code platform our customers use.
I picked the ball-and-vase magic trick. It was one of my favorites as a kid, and it felt like the right mix of fun and surprisingly hard.
A few days later, GEN-1 pulled it off. I left Friday having watched the robot nail it 14 times in a row. What’s wild is that even 4 months ago, if you told me you could go from idea to on-robot skill in a couple of days, I probably wouldn’t have believed you.
Really excited to be building with an incredible team. Can’t wait to see what week two brings 🤖
Generalist retweeted
Replying to @GeneralistAI
We’ll see a fully robot-maintanined data center go live within the next 12 months, by Generalist and a startup.
Infra is about to change faster than most people expect.
Generalist retweeted
Meanwhile as people are oohing and ahhing at some janky teleoperated robots, Generalist, a team of people from OpenAI, Boston Dynamics and Google DeepMind are building truly intelligent robot systems that learn on the spot and can do much more complicated tasks.
Replying to @GeneralistAI
2/ The point isn’t any one demo.
It’s that for the first time in robotics, through scaling laws, our models are beginning to reach new levels of reliability, speed, and intelligent improvisation never seen before, across many tasks.
Generalist retweeted
We need to move past a world where every handful of months, everybody releases a few demos from their latest model or paper. People want to see more from GEN-1, more on this soon.





















