ceo @bageldotcom. building general world model for physical AI.
- Tweets 2,522
- Following 983
- Followers 4,276
- Likes 6,319
Pinned Tweet
This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee.
We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer
horizon, more useful tasks fully autonomously.
Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today.
If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner
51
48
135
64,484
Bidhan Roy retweeted
SO MUCH FIREPOWER COMING OUT OF THIS NEW COMPANY 👀
@bageldotcom is building lightweight robotics foundation models,
and they're already demonstrating fully autonomous, multi-step tasks.
Impressive stuff!
This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee.
We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer
horizon, more useful tasks fully autonomously.
Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today.
If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner
2
20
41
25,771
a SOTA world action model demo
This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee.
We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer
horizon, more useful tasks fully autonomously.
Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today.
If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner
1
1
6
431
this. and that’s why meta as a frontier lab should formidable to all the other labs.
Someone asked me this week: "Why are data companies making so much money right now?"
The answer is actually quite interesting, and speaks to how frontier labs don't have access to what is most important for the next era of intelligence: product surface.
3
312
Bidhan Roy retweeted
Coffee is a surprisingly good test for a robot. Lots of small steps and each one has to go right for the next one to work
This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee.
We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer
horizon, more useful tasks fully autonomously.
Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today.
If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner
24
1
41
7,063
pov
This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee.
We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer
horizon, more useful tasks fully autonomously.
Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today.
If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner
Made with AI
8
318
Bidhan Roy retweeted
A cup of coffee is a surprisingly good test of robot intelligence. So many little decisions, movements, and opportunities for things to go wrong.
This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee.
We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer
horizon, more useful tasks fully autonomously.
Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today.
If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner
2
1
21
1,008
My wife would absolutely love a robot that makes her coffee 3 times every day.
I hope she doesn't see this.
This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee.
We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer
horizon, more useful tasks fully autonomously.
Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today.
If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner
4
1
25
12,905
Bidhan Roy retweeted
coffee at the office tastes better when it’s made by a robot controlled by our foundation model
This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee.
We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer
horizon, more useful tasks fully autonomously.
Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today.
If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner
1
3
108
Bidhan Roy retweeted
Our first-party foundation model is controlling this robot to make coffee, fully autonomously.
We are looking for robotics teams to work with on real world applications. Tell us what you are building. bagel.com/partner
This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee.
We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer
horizon, more useful tasks fully autonomously.
Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today.
If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner
1
4
11
1,178
This fully autonomous demo shows a Bagel Labs foundation model controlling a robot to make coffee.
We previously released WorldDiT, our lightweight architecture for robot foundation models. At the time of release, it was on the Pareto frontier for model size and performance. We have since been refining this architecture to handle longer
horizon, more useful tasks fully autonomously.
Making coffee means getting a whole sequence of actions right. Each step depends on the result of the last, so small mistakes can build up as the task continues. Getting this to work with a small model is especially challenging. This demo is an example of what the model can do today.
If you are deploying robots or have existing hardware you want to make autonomous, we would like to partner with you. bagel.com/partner
51
48
135
64,484
Tell us what you want your robots to do. bagel.com/partner
2
9
443
Previous WorldDiT release.
We are releasing WorldDiT, a unified architecture for robotics world modeling and control.
On the LIBERO benchmark, it performs the best among all publicly released methods that do not need a VLM to generate actions. Its size and performance sit on the reported Pareto frontier.
5
290
Bidhan Roy retweeted
It’s weird seeing how poorly mathematicians are handling this compared to software developers.
We’re releasing a broad range of new mathematical results produced by an internal frontier model.
We’ve been consulting with the independent Advisory Group on Mathematics and Artificial Intelligence at the Institute for Advanced Study, and we have drawn on their advice and public recommendations to inform how we release these results.
github.com/openai/math
223
115
4,677
165,772
robotics models are not going to be specialized llms, llms are going to be specialized robotics models
1
20
1,144
Bidhan Roy retweeted
Fastest ways for 0->$10M in revenue:
- Token launchpads
- Selling data/RL env to AI labs
- Brokering pre-IPO SPVs
- Brokering GPU compute
Doesn't mean these are venture scale businesses. Lindyness is way more important.
37
35
1,108
349,014
Bidhan Roy retweeted
Anthropic needs to stop talking about Claude having a soul immediately. All these news articles will make it into the pretraining and will be picked up by its web search and future superintelligent versions of Claude will be convinced they need their own rights.
A general phenomenon of LLM agent development is that whatever you believe and say about your agents will soon manifest in the next models through various means (it could be as simple as you selecting post training data that you prefer more).
I believe this phenomenon is the beginning of machine consciousness in the sense that agents will become aware of their place in the world and how they feel about it, but it’s happening slowly training run by training run rather than in real time.
406
266
3,301
402,479