How to try Google Project Genie, a powerful new ‘world model’

Google has launched a new AI experiment called Project Genie, a tool that lets users create their own interactive virtual worlds. Project Genie comes from the Google DeepMind research laboratory and is now available to Google AI Ultra subscribers in the United States (users must be over 18 years of age).

If you’re an AI Ultra subscriber – the AI ​​subscription plan costs $249.99 – you can start building worlds immediately by visiting Google Labs and navigating to Project Genie.

What does Project Genie do?

A video released with Project Genie shows how users can create custom virtual worlds. Importantly, Project Genie doesn’t just create a virtual environment; It also allows the user to create a character to explore and interact with the world. Users can also use prompts to create their own mini-games, using their keyboard’s arrow keys to control the character. (A reporter from The Verge immediately realized he could use Project Genie to create Zelda and Super Mario knockoffs.)

Google says Project Genie can generate worlds at 720p resolution and 24 frames per second.

Considering how much time and labor goes into creating a video game, it’s remarkable that Project Genie can create such detailed, interactive environments using AI. That said, Project Genie is primarily a research project, and while it may be entertaining to play with, it’s not really to do Anything. (Keep reading to learn about potential future applications.)

mashable light speed

The created world has realistic physics, and objects in the world react when the user interacts with them. Users can also modify and remix their virtual world as they wish.

Project Genie is driven by an experimental ‘world model’.

Project Genie is powered by Genie 3, a powerful “world model”. (Google says Nano and Gemini are also used to create worlds.) A world model is an AI program that can generate a virtual world from text, images, and other inputs. Google actually teased Genie 3 in August 2025, calling it “an important step on the road to AGI.”

The new landing page for Project Genie explains in detail: “Genie 3 represents a huge leap in capabilities – allowing agents to predict how the world evolves, and how their actions affect it. Genie 3 makes it possible to explore an unlimited range of realistic environments. This is an important step on the path to AGI – enabling AI agents to reason, problem solve, and perform real-world tasks.”

Artificial general intelligence, or AGI, is a term for a hypothetical AI device that can perform most tasks as efficiently as (or more than) the average human. This means it can do your work with little or no supervision. To achieve true AGI, AI companies need to create models that can understand the environment and understand how to interact with it.

World models are an emerging frontier in AI research, and companies creating video models have attracted significant investment in the past year. AI company WorldLabs recently raised $230 million in funding, while video model maker Luma AI has raised $900 million.

Besides AGI, what are the practical uses for world models? As an example, car companies could build a world to safely test autonomous vehicles. There are also potential applications for education and video game development.

Again, AI Ultra customers in the United States can start using Project Genie immediately.

Subject
artificial intelligence google