Generalist's banner
Generalist's profile picture

Generalist

@GeneralistAI • 26,091 subscribers

Generalist is an AI robotics company building general intelligence for the physical world and making it useful to everyone.

Shorts

When a Lego brick gets unexpectedly stuck on the fingertips, the model uses the other hand to remove them.

When a Lego brick gets unexpectedly stuck on the fingertips, the model uses the other hand to remove them.

20,912 views

We've been heads-down building. The robots have gotten pretty good. We'll be sharing a brief update soon.

We've been heads-down building. The robots have gotten pretty good. We'll be sharing a brief update soon.

11,901 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

Introducing GEN-1.5, a one-shot learner. It can learn new tasks in a few seconds. Show it what to do, and it generalizes. This capability emerged from pretraining on physical data at scale, as a step towards our mission of building general intelligence for the physical world.
3:32
GeneralistAI's profile picture

Introducing GEN-1.5, a one-shot learner. It can learn new tasks in a few seconds. Show it what to do, and it generalizes. This capability emerged from pretraining on physical data at scale, as a step towards our mission of building general intelligence for the physical world.

Generalist

3,442,483 views • 2 months ago

GEN-1 plays the 🐚 shell game, trained on just 1 hr of robot data. It also generalizes to unseen objects, like berkay 's car keys. Physical AI models should be capable of benchmark tasks like this one. It's interesting for the all the reasons Rhoda AI calls out -- requires visual memory, and the model must track the cups from the very start, at high frame rates. Interestingly, GEN-1 appears to exhibit a degree of "active perception." It's subtle; the hands can sometimes appear to "follow" the cups, using its own movements to help attend to where it thinks the object should be. Read more about GEN-1 in our blog post in the comments below ↓
0:47
GeneralistAI's profile picture

GEN-1 plays the 🐚 shell game, trained on just 1 hr of robot data. It also generalizes to unseen objects, like berkay 's car keys. Physical AI models should be capable of benchmark tasks like this one. It's interesting for the all the reasons Rhoda AI calls out -- requires visual memory, and the model must track the cups from the very start, at high frame rates. Interestingly, GEN-1 appears to exhibit a degree of "active perception." It's subtle; the hands can sometimes appear to "follow" the cups, using its own movements to help attend to where it thinks the object should be. Read more about GEN-1 in our blog post in the comments below ↓

Generalist

864,333 views • 6 months ago

Why create robot intelligence for just one hand, when we could have it learn from many? GEN-1, our latest embodied foundation model, now supports a broad range of end effectors from 5-finger hands, to specialized tools, and everything in between.
2:09
GeneralistAI's profile picture

Why create robot intelligence for just one hand, when we could have it learn from many? GEN-1, our latest embodied foundation model, now supports a broad range of end effectors from 5-finger hands, to specialized tools, and everything in between.

Generalist

307,048 views • 3 months ago

GEN-1.5 packs a bottle into a box, then packs another bottle into a box, then another bottle, then another one, then another... Read more about GEN-1.5 in our blog post in the comments below.
4:18
GeneralistAI's profile picture

GEN-1.5 packs a bottle into a box, then packs another bottle into a box, then another bottle, then another one, then another... Read more about GEN-1.5 in our blog post in the comments below.

Generalist

49,156 views • 20 days ago

Robot puts a ring on it GEN-1.5 puts an O-ring on a hydraulic rod gland, then takes the ring off, then puts the ring back on, then takes the ring off, then ring on, ring off, ring on... Read more about GEN-1.5 in our blog post in the comments below.
3:57
GeneralistAI's profile picture

Robot puts a ring on it GEN-1.5 puts an O-ring on a hydraulic rod gland, then takes the ring off, then puts the ring back on, then takes the ring off, then ring on, ring off, ring on... Read more about GEN-1.5 in our blog post in the comments below.

Generalist

53,759 views • 22 days ago

Introducing GEN-1. Our latest milestone in scaling robot learning. We believe it to be the first general-purpose AI model to master simple physical tasks. 99% success rates, 3x faster speeds, adapts in real time to unexpected scenarios, w/ only 1 hour of robot data. More🧵👇
3:21
GeneralistAI's profile picture

Introducing GEN-1. Our latest milestone in scaling robot learning. We believe it to be the first general-purpose AI model to master simple physical tasks. 99% success rates, 3x faster speeds, adapts in real time to unexpected scenarios, w/ only 1 hour of robot data. More🧵👇

Generalist

389,657 views • 6 months ago

GEN-1.5, our latest embodied foundation model, can learn new tasks prompted with 3 - 12 seconds of a single demonstration, no gradient updates or fine-tuning. It generalizes prompts to new situations, recovers from mistakes, and improvises new strategies to reach the same goal.
0:23
GeneralistAI's profile picture

GEN-1.5, our latest embodied foundation model, can learn new tasks prompted with 3 - 12 seconds of a single demonstration, no gradient updates or fine-tuning. It generalizes prompts to new situations, recovers from mistakes, and improvises new strategies to reach the same goal.

Generalist

137,424 views • 2 months ago

How many pucks could a puck bot pack if a puck bot could pack pucks? 🏒 12 hockey pucks is a tight fit in this container – watch the model fix the arrangement when pucks get stuck or misplaced. GEN-1.5 doesn't just puck around. Read more about it in our blog post and sign up for the waitlist in the comments below.
3:45
GeneralistAI's profile picture

How many pucks could a puck bot pack if a puck bot could pack pucks? 🏒 12 hockey pucks is a tight fit in this container – watch the model fix the arrangement when pucks get stuck or misplaced. GEN-1.5 doesn't just puck around. Read more about it in our blog post and sign up for the waitlist in the comments below.

Generalist

17,022 views • 8 days ago

Introducing GEN-0, our latest 10B+ foundation model for robots ⏱️ built on Harmonic Reasoning, new architecture that can think & act seamlessly 📈 strong scaling laws: more pretraining & model size = better 🌍 unprecedented corpus of 270,000+ hrs of dexterous data Read more 👇
0:48
GeneralistAI's profile picture

Introducing GEN-0, our latest 10B+ foundation model for robots ⏱️ built on Harmonic Reasoning, new architecture that can think & act seamlessly 📈 strong scaling laws: more pretraining & model size = better 🌍 unprecedented corpus of 270,000+ hrs of dexterous data Read more 👇

Generalist

501,309 views • 11 months ago

This is GEN-1 putting paper bills into a wallet. Paper has always been deceptively hard for robots. Thin, deformable, and unforgiving—it bends, folds, and slips. Not precise, you miss. Too much force, you crumple. Easy for humans. But for robots, it’s a full-stack challenge.
0:36
GeneralistAI's profile picture

This is GEN-1 putting paper bills into a wallet. Paper has always been deceptively hard for robots. Thin, deformable, and unforgiving—it bends, folds, and slips. Not precise, you miss. Too much force, you crumple. Easy for humans. But for robots, it’s a full-stack challenge.

Generalist

222,584 views • 6 months ago

We've improved how GEN-1 learns to adapt to new actuators and new robots at the lowest level, with up to 10-20x gains on internal benchmarks. This significantly boosts performance on high-precision tasks like disassembling parts from a NIST board. Read more about GEN-1 in our blog posts in the comments below.
3:24
GeneralistAI's profile picture

We've improved how GEN-1 learns to adapt to new actuators and new robots at the lowest level, with up to 10-20x gains on internal benchmarks. This significantly boosts performance on high-precision tasks like disassembling parts from a NIST board. Read more about GEN-1 in our blog posts in the comments below.

Generalist

92,977 views • 2 months ago

GEN-1.5 puts together a kit of cosmetics, then puts together another kit, then another kit, then another... We're expanding access to GEN-1.5 Sign up to get in line
7:59
GeneralistAI's profile picture

GEN-1.5 puts together a kit of cosmetics, then puts together another kit, then another kit, then another... We're expanding access to GEN-1.5 Sign up to get in line

Generalist

12,874 views • 13 days ago

Today we're excited to share a glimpse of what we're building at Generalist. As a first step towards our mission of making general-purpose robots a reality, we're pushing the frontiers of what end-to-end AI models can achieve in the real world. Here's a preview of our early results in autonomous general-purpose dexterous capabilities – fast, reactive, smooth, precise, bi-manual coordinated sensorimotor control.
2:21
GeneralistAI's profile picture

Today we're excited to share a glimpse of what we're building at Generalist. As a first step towards our mission of making general-purpose robots a reality, we're pushing the frontiers of what end-to-end AI models can achieve in the real world. Here's a preview of our early results in autonomous general-purpose dexterous capabilities – fast, reactive, smooth, precise, bi-manual coordinated sensorimotor control.

Generalist

279,070 views • 1 year ago

GEN-1 puts plushies into polybags, in a warehouse outside the lab in New Hampshire.
2:01
GeneralistAI's profile picture

GEN-1 puts plushies into polybags, in a warehouse outside the lab in New Hampshire.

Generalist

105,815 views • 6 months ago

GEN-1 delicately arranges potato chips, and lifts a heavy bag of potatoes — from a gentle touch to a strong grip. Read more about Gen-1 in our blog posts in the comments below ↓
1:15
GeneralistAI's profile picture

GEN-1 delicately arranges potato chips, and lifts a heavy bag of potatoes — from a gentle touch to a strong grip. Read more about Gen-1 in our blog posts in the comments below ↓

Generalist

91,789 views • 5 months ago

We've reduced the time it takes to go from physical prompt → robot behavior. The faster anyone can teach a robot to do something new, the easier it becomes to scale physical work. Read more about GEN-1.5 in our blog post in the comments below.
0:21
GeneralistAI's profile picture

We've reduced the time it takes to go from physical prompt → robot behavior. The faster anyone can teach a robot to do something new, the easier it becomes to scale physical work. Read more about GEN-1.5 in our blog post in the comments below.

Generalist

27,625 views • 2 months ago

GEN-1 cleans white board Read more about GEN-1 in our blog post in the comments below ↓
0:26
GeneralistAI's profile picture

GEN-1 cleans white board Read more about GEN-1 in our blog post in the comments below ↓

Generalist

64,780 views • 6 months ago

GEN-1 sorts socks and uses a touchscreen stylus. Done in collaboration with a partner on the Generalist platform. More on this soon.
1:42
GeneralistAI's profile picture

GEN-1 sorts socks and uses a touchscreen stylus. Done in collaboration with a partner on the Generalist platform. More on this soon.

Generalist

61,937 views • 6 months ago

A simple example of physical prompt steerability: same environment, different prompts, different behaviors. Thanks Jagdeep Bhatia for the suggestion. Read more about GEN-1.5 in our blog post in the comments below.
0:29
GeneralistAI's profile picture

A simple example of physical prompt steerability: same environment, different prompts, different behaviors. Thanks Jagdeep Bhatia for the suggestion. Read more about GEN-1.5 in our blog post in the comments below.

Generalist

23,586 views • 2 months ago

At Generalist, we’re working towards a future where robots can do anything. To that end, the robots build now, too. We’ve trained a robot to do one-shot assembly, constructing Legos end-to-end: no custom engineering, just pixels in → Lego copies out.
0:58
GeneralistAI's profile picture

At Generalist, we’re working towards a future where robots can do anything. To that end, the robots build now, too. We’ve trained a robot to do one-shot assembly, constructing Legos end-to-end: no custom engineering, just pixels in → Lego copies out.

Generalist

103,398 views • 1 year ago