Diego Rivas, Shlomi Fruchter, and Jack Parker-Holder from the Project Genie team join host Logan Kilpatrick for an in-depth discussion on Google DeepMind’s latest breakthrough in world models. Project Genie is an experimental research prototype that allows users to generate, explore, and interact with infinitely diverse, photorealistic worlds in real-time. Learn more about the shift from passive video generation to interactive media, the technical challenges of maintaining world consistency and memory, and how these models serve as an essential training ground for AI agents. Watch on YouTube: https://www.youtube.com/watch?v=Ow0W3WlJxRY
Chapters:
00:00 - Intro and defining world models and RL roots
01:51 - Demo: Goldfish and shark in underwater world
04:59 - Project Genie gallery
06:31 - Physics, remixing, and UI prompts
11:00 - Demo: Nano Banana mascot “Bob”
13:20 - Constraints, generation limits, and infrastructure
17:04 - Trusted testers and robotics future
28:34 - Frontier prompting and universal simulation
29:27 - Cross-Google collaboration
31:16 - Adoption timelines and impact
34:16 - Model generalization and historical context
38:52 - Hardware limits and the slope of progress