DeepMind Is Simulating Entire Worlds - Ready for AI Robots

DeepMind Is Simulating Entire Worlds - Ready for AI Robots

From The World, the Universe and Us by New Scientist

June 5, 2026 · 28 min

About this episode

The episode discusses Google DeepMind's advancements in simulating entire worlds for AI training.

Episode 374 Google DeepMind is simulating entire worlds using AI - that can be interacted with in real time. “World models” simulate the environment and physics of the real world. And DeepMind’s Genie 3 model allows people to create these worlds with basic image and text prompts. The idea is not just to allow people to explore these worlds, but to serve as a testbed for AI agents to learn how to interact with the world before they are deployed in humanoid robotic bodies. Could this be the next big step towards artificial general intelligence (AGI)? Joshua Howgego speaks to Jack Parker Holder, Research Director at Google DeepMind, about the latest developments. To read more about these stories, visit https://www.newscientist.com/ Learn more about your ad choices. Visit megaphone.fm/adchoices

People in this episode

Host: Joshua Howgego

Guest: Jack Parker Holder

Topics covered

  • AI
  • simulation
  • robotics
  • artificial general intelligence
  • DeepMind
  • world models

Keywords

  • DeepMind
  • AI
  • simulation
  • robotics
  • artificial general intelligence
  • world models
  • Genie 3

Mentioned in this episode

Organizations: Google DeepMind, New Scientist

More episodes of The World, the Universe and Us

Explore listener stats, chart rankings, contacts and more on the The World, the Universe and Us podcast page.