The OpenAI Sora 2 team (Bill Peebles, Thomas Dimson, Rohan Sahai) discuss how they compressed filmmaking from months to days, enabling anyone to create compelling video. Bill, who invented the diffusion transformer that powers Sora and most video generation models, explains how space-time tokens enable object permanence and physics understanding in AI-generated video, and why Sora 2 represents a leap for video. Thomas and Rohan share how they're intentionally designing the Sora product against mindless scrolling, optimizing for creative inspiration, and building the infrastructure for IP holders to participate in a new creator economy. The conversation goes beyond video generation into the team’s vision for world simulators that could one day run scientific experiments, their perspective on co-evolving society alongside technology, and how digital simulations in alternate realities may become the future of knowledge work.

Hosted by: Konstantine Buhler and Sonya Huang, Sequoia Capital

00:00 Introduction
02:57 Understanding Diffusion Transformers
06:06 Advancements from Sora 1 to Sora 2
08:48 Building a World Simulator
10:44 Data Selection and Training
12:48 Exploring the Future of AI and Physics
17:09 The Journey of Sora's Product Development
23:27 User Engagement and Creation
25:08 Ranking Algorithms and Social Impact
30:33 Preventing Mindless Scrolling
33:23 API Use Cases and Future Vision
34:32 Exploring AI in Gaming
35:01 Creative Potential of AI in Gaming
35:34 Innovative Gaming Concepts
37:40 AI's Role in Creative Filmmaking
39:00 Future of AI in Filmmaking
39:35 Empowering Creators with AI
42:16 Monetizing AI Creations
43:53 The Future of AI-Generated Content
49:03 AI and the Multiverse
50:34 Existential Questions in AI
51:18 Theoretical Limits of AI
51:57 Lightning Round