Genie 3: A New Frontier for World Models with Jack Parker-Holder & Shlomi Fruchter
EPISODE 743
|
AUGUST
19,
2025
Watch
Follow
Share
About this Episode
Today, we're joined by Jack Parker-Holder and Shlomi Fruchter, researchers at Google DeepMind, to discuss the recent release of Genie 3, a model capable of generating “playable” virtual worlds. We dig into the evolution of the Genie project and review the current model’s scaled-up capabilities, including creating real-time, interactive, and high-resolution environments. Jack and Shlomi share their perspectives on what defines a world model, the model's architecture, and key technical challenges and breakthroughs, including Genie 3’s visual memory and ability to handle “promptable world events.” Jack, Shlomi, and Sam share their favorite Genie 3 demos, and discuss its potential as a dynamic training environment for embodied AI agents. Finally, we will explore future directions for Genie research.
About the Guests
Jack Parker-Holder
Google DeepMind
Shlomi Fruchter
Google DeepMind
Resources
- Genie 3: A new frontier for world models
- Genie 2: A large-scale foundation world model
- Genie: Generative Interactive Environments paper
- A generalist AI agent for 3D virtual environments
- RT-1: Robotics Transformer for Real-World Control at Scale
- MaskGIT
- Human-Timescale Adaptation in an Open-Ended Task Space
- Google Duplex: An AI System for Accomplishing Real-World Tasks Over the Phone
- Veo models
- Imagen
- Playable Environments: Video Manipulation in Space and Time
- Dyna, an integrated architecture for learning, planning, and reacting
- Recurrent World Models Facilitate Policy Evolution
- World Models
- Diffusion Models Are Real-Time Game Engines
- Dream to Control: Learning Behaviors by Latent Imagination
- Mastering Atari with Discrete World Models
- Mastering Diverse Domains through World Models
- Genie: Generative Interactive Environments with Ashley Edwards - #696
