Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Article image or reusable cover for Latent Space
Watch along AIE NYC and join us at AIE CODE in SF next month!This episode includes a live demo of the Taku robot that is best enjoyed on YouTube.Last month, Dyna made waves by announcing Dyna-2, a world-action model pre-trained on one million hours of human video, claiming several new scaling laws on human data across four orders of magnitude.
They have now followed up the model with a physical robot agent, Dyna-2.1, that has to be seen to be believed:In his talk at AIE this year, Jason talked about how the real challenge for robotics in the real world is reliable, long-horizon autonomy, and how Dyna got its models to a 99.4% success rate folding restaurant napkins for 24 hours straight, including recovering after it pulled over the whole stack.From training a world-action model on over one million hours of human video to deploying robots that fold thousands of napkins daily at Din Tai Fung, Dyna Robotics is pushing physical AI beyond impressive demos and into real-world production.
The text is the source's own description of its publication. The content belongs to Latent Space.
More from Latent Space
Using Agents for Long-Horizon Financial Work — Aman Singh, Arca
Latent Space 17 h ago
⚡ Building ChatGPT for Finance — Joseph Kim, OpenAI's Head of Financial Services
Latent Space 31 Oct
Lumaril, which develops AI software for optimizing industrial production by connecting to existing control systems, raised a $66M Series A at a $400M valuation
Techmeme 3 h ago
DeepSeek open sources Super-Agent as a research prototype, a proactive coding agent it says can monitor group chats for coding issues and suggest solutions
Techmeme 4 h ago