a16z Discusses Atlas World Model With World Labs

a16z posted about a 43-minute YouTube video featuring World Labs co-founders Fei-Fei Li, Justin Johnson, Ben Mildenhall and a16z general partner Martin Casado. The discussion covers Atlas, described as a world model for spatial intelligence built on new view prediction. It contrasts this with LLMs using next token prediction and video models using next frame prediction, noting Atlas as the first to unify pixel generation. The linked video is titled Why World Models Could Change Robotics, 3D, and Creativity.