Trending
Prev Story
Next Story

DeepMind's Genie 4 world model adds audio and more realistic people to simulations

Ars Technica •
October 27, 2026 • 04:00 PM
1
1 reads 0 reactions

Genie 4 will roll out to developers and Google AI Ultra subscribers soon.

DeepMind's Genie 4 world model adds audio and more realistic people to simulations

Last year, Google DeepMind sent gaming stocks tumbling with the reveal of its Genie 3 world model . Since then, world models have become a major focus of AI labs around the world, but Google isn’t resting on its laurels. Researchers have been hard at work on an updated model that improves on Genie 3 in almost every way. And if you pay Google enough money, you might actually get to use Genie 4 before too long.

It’s easy to look at the output of Genie 4 and see a video game, which is why Genie 3 caused so much consternation in the gaming industry. DeepMind doesn’t think about it that way, though. According to Google , world models are a key element in the march toward artificial general intelligence (AGI). A world model creates a virtual world, but it doesn’t require pre-rendering environments or programming interactive elements. You simply tell the model what you want, and it generates the experience frame by frame in real time as you explore it.

DeepMind says this technology could create infinite training environments for physical robots or unlock new avenues of rapid prototyping for creative fields. Of course, that requires the model to accurately simulate what you want. Genie 4 has several improvements that make its simulations more useful, and that’s thanks in part to Google’s updated Gemini models.

When you prompt a world into existence in Genie 4, it leverages Gemini 3.8 Flash as a guiding agent to break down goals and evaluate each output frame. This helps keep the simulation on track, letting you move through varying environments without losing the original context. However, DeepMind notes that Genie 4 worlds still only remain consistent for a couple of minutes before they forget how things started.

Like Genie 3, the new version supports changing the parameters midstream. You can change the weather, add elements, or move the camera, and Gemini will help steer the simulation with each update. This is similar to the way reasoning models generate additional internal prompts to zero in on the right output tokens.

Prev Swipe Story Next

Same Story from Other Publications

Compare how 3 other independent news outlets reported on this story.

3 Publications
The Verge
3d ago
Google DeepMind’s new AI model gives robots improved dexterity.

Google DeepMind’s new AI model gives robots improved dexterity.

With Gemini Robotics 2.5, robots can “perform significantly more tasks with greater performance and dexterity,” according to Carolina Parada, DeepMind’s head of robotics. The model lets robots combine a “number” of skills, including “advanced tool use, complex manipulation of deformables, and handling delicate objects with finesse,” Parada says. [Link: Gemini Robotics 2.5: Accelerating Physical Intelligence | https://deepmind.google/blog/gemini-robotics-2-5-accelerates-real-world-physical-intelligence/ | Google DeepMind]

#mind #google #deepmind
Compare →
The Next Web (TNW)
1d ago
Google DeepMind’s AI agents formally verify Signal encryption code

Google DeepMind’s AI agents formally verify Signal encryption code

“A long distance to go”: DeepMind’s AI verified Signal encryption code in four weeks, but only for one-to-one chats, not Signal’s apps.

#mind #google #deepmind
Compare →
Wired
1d ago
Google DeepMind Staff Tap the UK Government to Escalate Their Unionization Fight

Google DeepMind Staff Tap the UK Government to Escalate Their Unionization Fight

After initial talks stalled, workers at Google DeepMind are trying to bypass company management in their bid to unionize.

#google #deepmind
Compare →

Related Stories

Technology
Build #2611