An AI lab advancing intelligence through world models
San Francisco
Joined November 2024
- Tweets839
- Following66
- Followers6.5K
- Likes1.4K
Pinned Tweet
Today we're unveiling SKY 00-1, the first Engineering World Model towards Autonomous Manufacturing.
LLMs are great at information retrieval and code, however, the physical world involves geometric and spatial understanding. Designing complex physical objects requires long-horizon planning and latent reasoning, which LLMs weren't built for.
We stacked SKY-001 against the top frontier LLMs (GPT-6 Astra, Fable 5.1 etc) and we found that our model is 100x faster and 150x cheaper in CAD and BIM while having higher precision.
As a compositional visual world model, SKY-001 lets you "dream" a design before you build it. It explores many designs in parallel, breaks each one down into its smallest components, and reassembles them in 3D, ready to open in CAD tools like Autodesk Fusion.
With applications in several industries, SKY-001 is the first step to reimagining engineering firms.
👉 Join the frontier with us and visit our website for early access (link in comments).
Introducing SKY-001, the first Engineering World Model.
On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested:
-> 51-125x faster
- > 150-210x cheaper
-> Higher IOU than all frontier models
SKY-001 lets you dream a physical object before you build it.
18 months of work. Built by the team out of Maluuba's deep learning lab (acq. by @MSRResearch).
The first ‘AI General Engineer’ will be the backbone for Autonomous Manufacturing.
Skyfall AI retweeted
Grateful to be tackling some of the hardest problems in AI with such an incredible team. Couldn't ask for a better group of people to build with.
Meet the world-class research team behind SKY-001, the first Engineering World Model.
Solving complex design and engineering problems in the physical world is orders of magnitudes more difficult than LLM agents using next token prediction. Our team at @skyfallai decided to take a different path than everyone else out there in order to achieve the research breakthrough.
Last week, we shared how SKY-001 stacks up against frontier LLMs, showing the clear advantage World Models have on complex real-world tasks like engineering design.
Here is a sneak peek video where you can learn directly from the researchers about what makes our approach unique, what training and data collection paradigms were used, and why we believe World Models are the next frontier in AI.
I’m incredibly proud to work alongside this team.
Meet the Research Team behind SKY-001 💙
Sign up for the waitlist if you haven't yet: skyfall.ai/sky-001
Meet the world-class research team behind SKY-001, the first Engineering World Model.
Solving complex design and engineering problems in the physical world is orders of magnitudes more difficult than LLM agents using next token prediction. Our team at @skyfallai decided to take a different path than everyone else out there in order to achieve the research breakthrough.
Last week, we shared how SKY-001 stacks up against frontier LLMs, showing the clear advantage World Models have on complex real-world tasks like engineering design.
Here is a sneak peek video where you can learn directly from the researchers about what makes our approach unique, what training and data collection paradigms were used, and why we believe World Models are the next frontier in AI.
I’m incredibly proud to work alongside this team.
Full technical breakdown in our blog: skyfall.ai/blog
Skyfall AI retweeted
World models are moving out of robotics and video and into engineering software.
SKY-001 from @skyfallai turns a text prompt or a 2D sketch into a full CAD build sequence that opens directly in Autodesk Fusion.
hear directly from the research team behind SKY-001"
Speed separates them, with each case taking 3.9 seconds versus 199 seconds for GPT-6 Astra.
SKY-001 gets there by planning visually instead of through repeated LLM calls, first splitting an object into sub-assemblies and individual parts.
A construction world model then predicts the ordered sketches and 3D solid states that build each part, which LLM-made shapes usually lack.
🤝 Paid partnership
Meet the world-class research team behind SKY-001, the first Engineering World Model.
Solving complex design and engineering problems in the physical world is orders of magnitudes more difficult than LLM agents using next token prediction. Our team at @skyfallai decided to take a different path than everyone else out there in order to achieve the research breakthrough.
Last week, we shared how SKY-001 stacks up against frontier LLMs, showing the clear advantage World Models have on complex real-world tasks like engineering design.
Here is a sneak peek video where you can learn directly from the researchers about what makes our approach unique, what training and data collection paradigms were used, and why we believe World Models are the next frontier in AI.
I’m incredibly proud to work alongside this team.
Here's a side-by-side comparison for BIM 👇
Which domain should we take it to next?
Get early access: skyfall.ai/sky-001
Our vision at @skyfallai is to make intelligence as affordable and ubiquitous as electricity.
With SKY-001, we're one step closer to that mission. Here's a side-by-side comparison of how fast our World Models are compared to frontier LLMs in CAD. LLMs are too slow so we had to 10x the video speed gosh 😂.
Electricity became ubiquitous because it was both cheap and fast enough to be woven into every tool and process without a second thought. When engineering design generation becomes 1000x faster, it transforms into a real-time utility for the entire human race.
Full technical breakdown in our blog: skyfall.ai/blog
We launched the first Engineering World Model, SKY-001, this week and it already outperforms all the frontier LLMs in CAD and BIM in speed, cost and precision.
Here’s an example of how our model compares to OpenAI’s Astra, Anthropic’s Fable 5.1 and Google’s Gemini 4.
These results did not happen by accident. Read our technical blog to find out how we built SKY-001 (🔗 below).
Sign up for early access: skyfall.ai/sky-001
Blog: skyfall.ai/blog/introducing-…
👉 Generate your own game now for @arcprize.
The @skyfallai team has created a AI generator that makes ARC-AGI-3 styled games end to end with no human involvement
All games in this repo have a formal spec, solver trajectories, per level budgets and multiple layout seeds. We also have a bundled browser player to go through these games.
The generator comes up with ideas (follows a design vocabulary), creates detailed specs that are then implemented and verified (by a second agent) in multiple iterations and finally packaged in the format above.
You can run this generator locally to create any number of original games to help train/evaluate your agent.
We have taken some inspiration from @tufalabs re-arc-3 to create this generator. Please feel free to try this out, share your feedback, and contribute on this to help the @arcprize community.
Repo: github.com/Skyfall-Research/…
We took a contrarian approach in research, and we're glad we did. The results beat our own expectations.
SKY-001 outperforms all frontier LLMs such as GPT-6 Astra, Gemini 3.8 Flash, and Opus 5.5 in both CAD and BIM. It's a big step forward for world models proving how such AI systems can reinvent manufacturing firms.
Next, we're excited to bring it to more domains such as PCB Design, Aerospace Engineering, Computer Use Agents and many more.
Join the waitlist now for early access: skyfall.ai/sky-001
Here is how SKY-001 beats prompt-based methods step-by-step:
Stage 1: Parallel Explorations Through World Modeling
Stage 2: Recursive Diffusion-Based 3D Decomposition
Stage 3: Multi-step 2D to 3D Latent Action World Model
Stage 4: 3D Construction World Model
Check out our full blog post for all the technical details! 🧵
Blog: skyfall.ai/blog/introducing-…
Website: skyfall.ai/sky-001
👉 Sign up for early access now: skyfall.ai/sky-001
While designing complex physical objects via CAD, frontier LLMs try to brute-force engineering through text tokens and inevitably buckle under compounding error pile-up.
SKY-001 operates as a true spatial World Model. It plans directly in the 3D space, recursively breaking complex designs down to the smallest part, then re-assembling everything while keeping every step globally consistent.
That’s how it leaves GPT-6 Astra, Gemini 4 Argon, and Claude Fable 5.1 behind on complex CAD workflows.
Here’s a side-by-side look at a Jaguar E-type sports car and a Ducati Cafe Racer:
Skyfall AI retweeted
What if Al could design an entire machine, down to its smallest components, at a fraction of the time and cost?
@skyfallai unveiled SKY-001, the first engineering world model, designed to tackle complex engineering tasks with remarkable speed and precision. A major step towards Al that doesn't just generate ideas, but helps turn them into reality🔥
🤝 Paid partnership
Introducing SKY-001, the first Engineering World Model.
On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested:
-> 51-125x faster
- > 150-210x cheaper
-> Higher IOU than all frontier models
SKY-001 lets you dream a physical object before you build it.
18 months of work. Built by the team out of Maluuba's deep learning lab (acq. by @MSRResearch).
The first ‘AI General Engineer’ will be the backbone for Autonomous Manufacturing.
Skyfall AI retweeted
AI that can actually help design and build real objects is a big deal.
@skyfallai SKY-001 can break down complex objects, figure out how the parts fit together, and turn them into designs that work in CAD.
It also claims to be much faster and cheaper than leading AI models on CAD/BIM tasks.
Exciting to see AI moving beyond chatbots and into real-world engineering and manufacturing.
🤝 Paid partnership
Introducing SKY-001, the first Engineering World Model.
On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested:
-> 51-125x faster
- > 150-210x cheaper
-> Higher IOU than all frontier models
SKY-001 lets you dream a physical object before you build it.
18 months of work. Built by the team out of Maluuba's deep learning lab (acq. by @MSRResearch).
The first ‘AI General Engineer’ will be the backbone for Autonomous Manufacturing.
Skyfall AI retweeted
Okay, this is where the world-model argument starts to make sense.
The deep learning pioneers from Maluuba are back solving one of the biggest problems in the industry. They unveiled SKY-001, the first engineering world model.
SKY-001 isn’t just generating something that looks 3D.
It simulates different designs, breaks the object down into parts and sub-assemblies, works through the hierarchy, then rebuilds it into something that can actually open in CAD.
Plus, the results compared to frontier LLMs are hard to ignore, including claims of being 150x cheaper and faster.
That feels much closer to how real engineering work happens.
With this release, they’re also building toward autonomous manufacturing and reimagining what manufacturing firms could look like.
If this approach keeps scaling beyond CAD and BIM, the interesting question won’t be “which LLM is better?”
It’ll be whether some of these long-horizon problems should be solved with a completely different kind of model.
Introducing SKY-001, the first Engineering World Model.
On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested:
-> 51-125x faster
- > 150-210x cheaper
-> Higher IOU than all frontier models
SKY-001 lets you dream a physical object before you build it.
18 months of work. Built by the team out of Maluuba's deep learning lab (acq. by @MSRResearch).
The first ‘AI General Engineer’ will be the backbone for Autonomous Manufacturing.
Skyfall AI retweeted
This dude is a math genius.
You can use the smartest systems and humans in the world and still have issues with output. You need to understand what makes a design buildable.
🤝 Paid partnership
Introducing SKY-001, the first Engineering World Model.
On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested:
-> 51-125x faster
- > 150-210x cheaper
-> Higher IOU than all frontier models
SKY-001 lets you dream a physical object before you build it.
18 months of work. Built by the team out of Maluuba's deep learning lab (acq. by @MSRResearch).
The first ‘AI General Engineer’ will be the backbone for Autonomous Manufacturing.
Skyfall AI retweeted
Great way to explore new product concepts or compare alternatives with 3D designs!
This is an engineering world model.
You give it a text prompt or an image, and it generates a 3D assembly.
Look at the examples: it breaks a design into smaller parts, creates each part in 3D, and assembles them.
Introducing SKY-001, the first Engineering World Model.
On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested:
-> 51-125x faster
- > 150-210x cheaper
-> Higher IOU than all frontier models
SKY-001 lets you dream a physical object before you build it.
18 months of work. Built by the team out of Maluuba's deep learning lab (acq. by @MSRResearch).
The first ‘AI General Engineer’ will be the backbone for Autonomous Manufacturing.
Skyfall AI retweeted
Had the pleasure of embarking on the wild journey of Maluuba with @spisallyouneed building agents over 15 years ago before people were even talking about Siri or ML. Pumped about Sky 001, the team is cooking!
Introducing SKY-001, the first Engineering World Model.
On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested:
-> 51-125x faster
- > 150-210x cheaper
-> Higher IOU than all frontier models
SKY-001 lets you dream a physical object before you build it.
18 months of work. Built by the team out of Maluuba's deep learning lab (acq. by @MSRResearch).
The first ‘AI General Engineer’ will be the backbone for Autonomous Manufacturing.