The popular search engine service provider, Google has commenced the rolling out access to Project Genius – which is a new experimental experience that allows users to generate and explore playable AI-created worlds.

Google Launching Project Genie 3

Yes we are talking about Genie 3 which is featured as a general-purpose world model capable of producing diverse, interactive environments in real time.

So far it’s access is limited to AI Ultra subscribers in the US aged 18 and above, but they have planned a wider availability in the coming future.

When it comes to the Project Genie, it is built on the idea of a world model, unlike the traditional AI systems that operate within narrowly defined environments, a world model attempts to simulate how an environment behaves, how it changes over time, and how user actions affect it.

Basically, these kind of models are a key step towards building systems that can handle the complexity and unpredictability of the real world, which is central to its long-term AGI ambitions, as per the information provided by Google DeepMind.

Project Genie – Opening The Doors To AI-generated Playable Worlds

Coming to its usage, the Project Genie commence with a simple but flexible setup where users are prompted to describe the world they want to create, including how they wish to explore it.

It’s movement options range from walking and driving to flying or riding, where users can choose between first-person or third-person perspectives.

After this they are asked to define their character, which can be a person, an animal, an object, or something more abstract.

It appears that project Genie generates a preview image through a process Google calls World Sketching before entering the world.

For the creation of preview, Genie uses Nano Banana Pro which allows users to fine-tune the look of their environment before committing to it.

Once users ger satisfied they can create the world itself, although sessions are currently limited to 60 seconds at a time.

This generated environments run at 720p resolution, with interaction rates of around 20 to 24 frames per second.

When the users start moving through the environment, Genie 3 generates the path ahead in real time, adapting the world based on their actions.

This system simulates physics and interactions with what it calls breakthrough consistency, although it also acknowledges clear limitations according to the Google.

Please note these generated worlds may not always look fully true to life, may not strictly follow prompts, and may sometimes behave inconsistently with real-world physics.

Besides this, the character control can also feel less precise, having occasional latency during interaction.

Besides all this, Project Genie also comes with a Remix Worlds feature which allows users to build on existing worlds by reusing and modifying prompts.

In simple words, users can explore curated worlds through a gallery or they can even use a randomiser for inspiration, then remix those ideas into new interpretations.

All these walkthroughs can be recorded, with videos available for download.

When it comes the Project Genie, it is an important research tool that will help it better understand how people interact with world models across AI research and generative media, Google said.

For the usage, the company sees practical applications in areas such as robotics, animation, fiction, and even the exploration of historical or inaccessible locations beyond entertainment.

We can see that Project Genie offers an early glimpse into how interactive, AI-generated worlds could play a role in the future of intelligent systems as it is still in the experimental stage.