EXPLORINEER
en

US — TechCrunch

Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering

AI2 min read

Google DeepMind has released Genie 4, a research preview of its newest world model. A world model is AI that creates interactive, simulated worlds that users can explore and change.

What happened

Google DeepMind released Genie 4 in research preview on Tuesday. Users can type prompts while a simulation is running to change the scene. The model also makes real-time audio that fits the world, including music, background sounds, and interactive dialogue.

Key facts

  • Genie 4 can keep a scene consistent for up to two minutes, double the limit of its predecessor, Genie 3.
  • Genie 3 was released as a research preview a little over a year ago.
  • Users can make edits in real time, such as changing the weather, changing the camera angle, or adding people or objects.
  • Genie 4 is available now to trusted testers. In the coming weeks, it will roll out to Google AI Ultra subscribers.

A crowded field

Other companies are also building world models. Runway released its second world model, GWM Worlds 2, a couple of months before Genie 4. The industry is also starting to combine. AMD is acquiring World Labs, Amazon is in talks to buy Decart, and Rivian bought Third Dimension to test self-driving cars in simulation.

Why it matters

World models could help people test ideas before they happen in the real world. For example, Google showed how Gemini, its AI model, can break a robot task into steps that Genie 4 simulates. Trusted testers also see a use in making films, where fast ideas and storyboards matter. Google says the product is still early, and it has not yet solved problems like objects drifting over time and inaccurate audio or unreadable text.

What to watch

  • Whether Genie 4 rolls out to Google AI Ultra subscribers in Project Genie, as planned in the coming weeks.
  • Whether early access partners of the Gemini API and Google AI Studio start building with it.
  • Whether Google fixes drifting details, audio accuracy, and legible in-world text.
  • Whether Gemini Omni can turn simulated prototypes into finished creative assets.

Glossary

Genie 4
Google DeepMind's newest world model. It makes interactive, simulated worlds that users can change while they run.
world model
An AI system that builds a simulated world and predicts how it changes, so people can explore or test in it.
Gemini
Google's AI model. In this story, it plans steps and checks frames while Genie creates the visuals.
Project Genie
Google's AI tool for making interactive worlds from text or image prompts.
Google AI Studio
Google's tool for developers to try and build with its AI models.

Same story, different eyes

Ad

Add 150 words. Learn 10 a day.

Dicter word books send only the words you learn to your review notes.

More in this topic

AIThe Verge

VisionQuest is what happens when AI really goes rogue

Marvel's VisionQuest follows the synthezoid Vision as he explores what it means to be a person, living alongside AI beings created by Tony Stark. The series engages with real-world debates about whether thinking machines should be seen as people and whether AI poses an existential danger. It also points to how aggressively Silicon Valley has used science fiction imagery to market its AI products.

AI전자신문

Adobe Expands AI Partnership with London Heathrow to Deliver Personalized Passenger Services

Adobe is expanding its partnership with Heathrow Airport to use AI-driven personalization and digital customer experience tools for more than 84.5 million annual passengers. Heathrow will adopt Adobe CX Enterprise on its official website, which receives over 50 million visits a year, and the two companies will work to make Heathrow's official content easier to find on major AI platforms such as ChatGPT, Gemini, Microsoft Copilot, and Perplexity. The companies also plan to track how Heathrow content is cited and surfaced in AI search and improve areas with poor information accessibility.

AIThe Register

A whopping 3% of boardroom execs spy productivity and costs savings from AI

Gartner researchers say three-quarters of corporate board members expect AI to boost productivity and cut costs, but only three percent of organizations have hit those targets. The analyst firm also reported that 38 percent of companies are over budget on AI spending, and 85 percent plan to spend even more next year. Gartner advises focusing AI on the work that matters most, with HR helping leaders agree on priorities.