DeepMind unveils Genie 4 world model promising more realistic physics and humans
DeepMind's Genie 4 adds audio and more realistic physics
New model
Google DeepMind has unveiled Genie 4, a world model that improves on Genie 3 with more realistic physics, human movement and native audio, and which the company plans to offer to developers and consumers.
DeepMind says world models are a key element in the march toward artificial general intelligence, generating interactive environments frame by frame in real time without pre-rendered assets or programmed interactive elements.
Genie 4 uses Gemini 3.8 Flash as a guiding agent to break down goals and evaluate each output frame, which DeepMind says keeps simulations on track across changing environments, though it notes worlds still only remain consistent for a couple of minutes before they forget how things started.
The model is the first DeepMind world model with native audio, including ambient background sounds, prompt-specified audio elements and interactive dialog that adapts as the simulation changes.
DeepMind says Genie 4 handles aerodynamics and collisions better and that people in simulations should look less uncanny, with more natural movement and responses.
Access will start expanding soon with no specific timeline, and Google plans to roll it out for developers via the Gemini API and AI Studio, with pricing not yet available.
Consumers will get access in phases through Google's most expensive AI Ultra plans, which start at $100 per month, handled through Project Genie, with a waitlist for early access.
From the source
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.