After 5 years at Wayve working out how to make a SOTA ML model drive cars, I’ve started a startup with Oliver Cameron & an amazing team. Like Wayve, it’s an applied algorithmic problem at the bleeding edge of ML. Can’t wait to share much more soon. For now, we’re hiring!

Today, we are delighted to welcome Odyssey to Air Street Capital. Oliver Cameron, Jeff Hawke and team are powering breakthrough AI-first visual storytelling to create blockbusters of the future.

The next frontier for visual generative models is to learn from the physical world. We've been pioneering exactly this at Odyssey. We're building a vast dataset of real-world places, all captured in incredibly high-fidelity 3D with a custom hardware device. Read on for more!

Big Odyssey news! We’re unveiling Explorer, a generative world model. Explorer transforms text or an image into a realized, detailed 3D world. I'm also incredibly excited that Edwin Catmull, the legendary Pixar founder, is joining our board & investing. Read on for more...

Today is a big day at Odyssey. We're sharing Explorer, our first generative world model. We think world models are the next frontier for AI, enabling wonderful new things. To help shape this, Ed Catmull, the iconic founder of Pixar, is joining our board and investing.

Ed Catmull (Pixar founder) just joined Odyssey's board as they reveal their first 3D breakthrough: Instantly turning any 2D image into an editable 3D world. World Labs isn't alone anymore. Here's the TL;DR without the hype 🧵

We’ve been busy building the next frontier of AI: generative worlds at Odyssey. It’s great to be able to share our work publicly (including testing in production settings), and welcome Edwin Catmull to our board!

We then reconstruct all captured 3D data into a gaussian splat. This means our generative world models learn from a rich & varied source of 3D. This dataset is growing so fast, with real-world data now captured in both California & Eastern Europe. Our goal is every continent.

We’re getting ready to share a glimpse of something totally new, all powered by a real-time model. We can't wait to hear what you think. See you on May 28th ✨

Introducing interactive video from Odyssey—video you can watch and interact with, imagined by AI in real-time. Give it a try for free today on (almost) any device, and let us know what you think. We think it's pretty cool!

Wow. Since launch 24 hours ago, we’ve served 85,000 streams of interactive video across the world. And it’s only accelerating! What’s wild is our model generated 250 million(!) video frames to meet the demand. Blown away by the excitement, TY. Let’s make more magic together ❤️

"People think of us as a world simulator." - Oliver Cameron, co-founder of Odyssey "We want to question our assumptions, like multiplayer, states and scripting - stuff that's integral to games today." "How should these things work? Let's make them model native." "Maybe

Most AI labs are focused on achieving superintelligence. We’re building something different: superimagination ✨