COO at Medal / General Intuition. Work with us: https://xitter.cf/t.co/i5H3GeeMU8

New York, NY
Joined October 2016
James Swingos retweeted
A challenge match would be awesome theatre and a test! A moment worth creating
actual footage of how the 1v1s between GI’s models and whatever Elon is cooking will go (yes these are our vision based models)
8
11
82
27,322
James Swingos retweeted
actual footage of how the 1v1s between GI’s models and whatever Elon is cooking will go (yes these are our vision based models)
Replying to @teslayoda
We’re making interesting progress here. Digital Optimus can play about halfway through the Diablo campaign so far just by looking at the screen like a human. Skill at Counter-Strike and other fast games is good too. League is also in training. Goal is to generalize across all games.
29
27
19
211
75,244
Replying to @grok
@grok I'm confused what is happening in this clip?
Replying to @teslayoda
We’re making interesting progress here. Digital Optimus can play about halfway through the Diablo campaign so far just by looking at the screen like a human. Skill at Counter-Strike and other fast games is good too. League is also in training. Goal is to generalize across all games.
4
12
1
38
2,509
James Swingos retweeted
Turns out scaling on data and compute with a great team is surprisingly effective 😉
General Intuition has raised another $220M at a $6.2B valuation as we start making our models available. These are an entirely new class of foundation models, trained on billions of action-labeled videos, capable of acting in realtime in never seen before environments. 1/6
24
9
3
204
17,089
Excited to show this new class of intelligence to the world
General Intuition has raised another $220M at a $6.2B valuation as we start making our models available. These are an entirely new class of foundation models, trained on billions of action-labeled videos, capable of acting in realtime in never seen before environments. 1/6
6
1
31
2,159
General Intuition has raised another $220M at a $6.2B valuation as we start making our models available. These are an entirely new class of foundation models, trained on billions of action-labeled videos, capable of acting in realtime in never seen before environments. 1/6
50
95
62
900
405,131
The WSJ stopped by to learn more about how our models work. Good write-up to understand broadly what a large action model is, how its different from world models, and why they are promising approaches in robotics. It's becoming increasingly clear that ground-truth action data, like the kind found in games, is a key ingredient to scaling robotics pre-training. Link in comments. Check out the policy waving at @pallipau.
3
10
66
30,717
James Swingos retweeted
Millions of hours of people playing video games looked like entertainment. It turned out to be the world's largest dataset of humans perceiving an environment and deciding how to act in it. General Intuition saw it first. Great WSJ piece on world models and AI's leap into the physical world.
3
4
13
1,998
James Swingos retweeted
First sneak peak in the WSJ on how GI’s large action models work!
The WSJ stopped by to learn more about how our models work. Good write-up to understand broadly what a large action model is, how its different from world models, and why they are promising approaches in robotics. It's becoming increasingly clear that ground-truth action data, like the kind found in games, is a key ingredient to scaling robotics pre-training. Link in comments. Check out the policy waving at @pallipau.
5
6
1
75
10,051
The WSJ stopped by to learn more about how our models work. Good write-up to understand broadly what a large action model is, how its different from world models, and why they are promising approaches in robotics. It's becoming increasingly clear that ground-truth action data, like the kind found in games, is a key ingredient to scaling robotics pre-training. Link in comments. Check out the policy waving at @pallipau.
4
10
7
69
58,543
James Swingos retweeted
gradually, then suddenly all at once 📈 on track for 3 billion clips this year.
29
26
15
361
447,671
Starting to realize just how big of a deal this was xitter.cf/gen_intuition/status/2…
Introducing MIRA. A playable, multiplayer world model. A dream of Rocket League. Trained on 10k hours of data collected with publicly available bots, MIRA learns the dynamics of a four-player game. The model runs in real time at 20 fps, based on the keys you and the other players press. Built by General Intuition and @kyutai_labs, in collaboration with Epic Games. Not used to develop Rocket League. ▶️ Play the demo, read the technical report, and explore the open-source code at generalintuition.com/mira At ICML? Find us at Booth 111 to try it yourself and dig into the results with the team.
6
5
1
87
40,736
James Swingos retweeted
I have been playing these world models/games since the first diffusion DOOM, and multiplayer at 20 FPS is pretty neat. "A dream of rocket league," indeed.
Introducing MIRA. A playable, multiplayer world model. A dream of Rocket League. Trained on 10k hours of data collected with publicly available bots, MIRA learns the dynamics of a four-player game. The model runs in real time at 20 fps, based on the keys you and the other players press. Built by General Intuition and @kyutai_labs, in collaboration with Epic Games. Not used to develop Rocket League. ▶️ Play the demo, read the technical report, and explore the open-source code at generalintuition.com/mira At ICML? Find us at Booth 111 to try it yourself and dig into the results with the team.
11
8
229
51,056
James Swingos retweeted
Today we’re introducing MIRA, a new multiplayer world model, built with @gen_intuition, in collaboration with Epic Games. We release an in-depth technical report, dataset, as well as an online demo that you can try right now (link below).
18
67
14
419
76,198
Can’t believe how cool this is. So proud of my teammates and so thankful for our partners
Introducing MIRA. A playable, multiplayer world model. A dream of Rocket League. Trained on 10k hours of data collected with publicly available bots, MIRA learns the dynamics of a four-player game. The model runs in real time at 20 fps, based on the keys you and the other players press. Built by General Intuition and @kyutai_labs, in collaboration with Epic Games. Not used to develop Rocket League. ▶️ Play the demo, read the technical report, and explore the open-source code at generalintuition.com/mira At ICML? Find us at Booth 111 to try it yourself and dig into the results with the team.
19
1,532
James Swingos retweeted
The term “world model” is tossed around a lot but this is the real deal. From video and actions, the model learns a consistent representation of the physics, 3D environment, and game state of Rocket League. I'm excited to have been part of this project because I see this as a step towards learning world models that can generalized to the real world. I’m a believer in learning from synthetic data (Sintel, SURREAL, AGORA, BEDLAM, BEDLAM2) and I’ve seen how models trained on synthetic data can generalize. MIRA is an important step because it’s learned from video gameplay generated completely by bots. This provides a pathway to scaling and scaling is key to real-world generality. Traditional graphics and games provide a path to learning rich models of the world. Check out the detailed tech report: mira-wm.com/paper/
Introducing MIRA. A playable, multiplayer world model. A dream of Rocket League. Trained on 10k hours of data collected with publicly available bots, MIRA learns the dynamics of a four-player game. The model runs in real time at 20 fps, based on the keys you and the other players press. Built by General Intuition and @kyutai_labs, in collaboration with Epic Games. Not used to develop Rocket League. ▶️ Play the demo, read the technical report, and explore the open-source code at generalintuition.com/mira At ICML? Find us at Booth 111 to try it yourself and dig into the results with the team.
19
65
3
850
114,122
James Swingos retweeted
Introducing MIRA. A playable, multiplayer world model. A dream of Rocket League. Trained on 10k hours of data collected with publicly available bots, MIRA learns the dynamics of a four-player game. The model runs in real time at 20 fps, based on the keys you and the other players press. Built by General Intuition and @kyutai_labs, in collaboration with Epic Games. Not used to develop Rocket League. ▶️ Play the demo, read the technical report, and explore the open-source code at generalintuition.com/mira At ICML? Find us at Booth 111 to try it yourself and dig into the results with the team.
69
138
121
1,442
508,393
Come hang out with us!
🚨 Headed to ICML 2026? Come hang out with friends at a Michelin Star restaurant to celebrate the end of the main conference!! Huge thanks to our friends at @Gen_Intuition for co-hosting this with us!
1
11
2,778
James Swingos retweeted
ICML 2026! 🇰🇷 We're heading to Seoul next week. Come find our research team at Booth 111 to talk world models and action models - the core of what we're building at General Intuition. We're also hosting a party on Wednesday, July 8th for a curated group of researchers working at the frontier. If that's you, the event RSVP is linked on the thread. See you there!
1
4
2
58
10,052