This Animation Startup Wants to Make It Easier to Tell Open-Ended Stories
The current wave of generative AI animation often feels like a magic trick that only works once. You type a prompt, a video appears, and if you don’t like the result (maybe your feet are all wobbly, which is a common problem with generations of AI), your only real option is to try a different prompt. This “black box” approach is exactly what Cartwheel, a new 3D animation startup, is trying to dismantle.
Andrew Carr and Jonathan Jarvis, two veterans from OpenAI and Google respectively, founded the company, which is working to build a future where AI handles the technical chore of animation while leaving the creative soul to the artist.
I spoke with Carr and Jarvis about launching their company, defining “taste” with AI, and the technical and creative challenges of animation in 2026.
What sets Cartwheel apart
According to the founders, one of the biggest obstacles in this field is that 3D motion data is remarkably sparse compared to the endless oceans of text and images available online on which AI models are trained.
“If you look at all the big tech companies, they’ve built their models on written language, audio, image, [and] “We knew it was going to be difficult, but it turns out to be more difficult than we thought, probably by a factor of 10 or 100, to get this data.”
Learn more: Generative AI in gaming is here, but it faces resistance from players and developers
While other tech giants focus on generating the final pixels, Cartwheel has spent years mapping how humans actually move. Their models are designed to understand the nuances of a performance so that a simple 2D video of a person dancing in their backyard can be translated into an accurate and realistic 3D skeleton.
This shift from flat images to 3D assets is what gives animators the control they lacked in the AI era.
Cartwheel has spent years tackling the difficult task of mapping how humans actually move.
Preventing AI “sameness”
Cartwheel executives said they view AI’s “sameness” as the result of a lack of control. If everyone uses the same generator to produce a video, the results might eventually start to look similar.
“The output of our system is designed so that people can edit it. It’s designed so that people can touch it and manipulate it, and we don’t want someone to type something and then have it go to a finished animation. That’s not the goal. It’s boring, who’s going to watch that?'” Carr says.
“The fact that it’s very easy for people to access and modify it totally eliminates the similarity problem,” he said. “You put him on different characters, you put him in different environments, you change his appearance, you push the performance, you pull the performance, and in that sense [sameness] becomes a non-issue. »
Carr and Jarvis said the solution is to provide a “control layer” where the AI output is just the starting point. By generating 3D data instead of flat video, the creator can change the lighting, move the camera, or adjust a character’s pose after the AI has done its initial work, making the technology a sophisticated powerful tool rather than a substitute for the artist.
Founder Andrew Carr said one of his main scientific hypotheses is that motion is a fundamental type of data.
The future of animation with AI
Beyond simply making animation faster and lowering the barriers to entry, the company is turning to a concept it calls “open storytelling” or “open world building.” In modern video games and social media, the demand for content has reached a scale that hand animation cannot match.
Cartwheel imagines characters that are not just programmed with a few set movements, but are powered by movement patterns that allow them to react and act in real time. It’s less about choreographing each frame and more about “rehearsing” with a digital actor who understands the intention of the scene.
Ultimately, the goal is to bridge the gap between 2D vision and 3D execution, the founders said.
“One of the main assumptions that we hope will be true over the next three years for Cartwheel is that everyone will work in 3D even if it’s written in 2D, even if the end result is just a 2D video,” Carr said.
By focusing on the “layer beneath the pixels,” Carr and Jarvis hope that as animation becomes more automated, it will also become more personal. The machine manages the biomechanics and file export, but the human has the final say on taste, timing and the heart of the story.
