Dyna Robotics on Monday introduced a new robot foundation model DYNA-2, which it says was trained on over a million hours of human video and no robot data. Today we are introducing Dyna-2, a world-action model pre-trained on one million hours of human video. DYNA-2, instead, was trained only on egocentric human video, which is footage from a person’s point of view as they interact with objects. Across 15 benchmark tasks, models trained on more human video consistently outperformed those trained on less human video. Dyna’s stated plan is to push the same approach to 10 million hours of video, which it frames as a collection problem rather than a fleet-building one.