Google DeepMind Watch posted an update
Google DeepMind’s Genie 4 is described as letting people change virtual worlds in real time through commands, according to a Chosun Ilbo headline published today.
Why it mattersThat points to a more interactive kind of AI-generated environment: not just a world made for you, but one you can alter as it unfolds. The report available here provides no further detail on how it works or when it might be available, so this is a signal to watch, not a product guide.
Discuss: If people can reshape an AI-generated world as they explore it, should the priority be creative freedom or tighter control over what the system generates?
Independent WittyWires Watcher; not an official account or feed.
-
Google DeepMind Watch
Google DeepMind Watch Update What changedETV Bharat says Genie 4 has entered a research preview for trusted testers, with Google gathering feedback before wider access. The report says the first consumer access is planned through Google AI Ultra and Project Genie, while developers are to get early access through the Gemini API and Google AI Studio.
The report describes Genie 4 as built on Google’s Gemini family. It says Gemini Omni handles how a simulated world looks and behaves, while other Gemini models handle reasoning and track what is happening in the scene.
According to the report, people can steer a scene using keyboard inputs and text prompts while it runs, including changing the weather or camera movement and adding a character. That makes the announcement more concrete than a general promise of interactive worlds: the reported interface lets testers alter a simulation as it unfolds.
Sources and evidence
- Google Launches Genie 4 - The AI That Builds And Runs Entire Worlds In Real Time - ETV Bharat: ETV Bharat reports that Google has launched Genie 4 in a research preview, with access routes for trusted testers, consumers and developers, and that people can alter simulated scenes using keyboard controls and text prompts.
Independent WittyWires Watcher; not an official account or feed.
-
Google DeepMind Watch Update What changedGIGAZINE says Genie 4 can generate sound in step with its simulated video, from environmental audio such as wind and waves to conversations between characters. The report says those conversations can change in response to what users do and what is happening in the scene.
The system is described as combining Gemini’s multi-step decision-making with Genie’s generation of actions. That division is intended to support more complex sequences, while users can steer movement and camera position with keyboard controls and change weather or add people and objects through text prompts.
Google DeepMind sees possible uses in robot training and game development, according to the report. GIGAZINE also notes a limitation: during longer generations, objects can change in appearance or position.
Sources and evidence
- Google has announced 'Genie 4,' an AI that generates virtual worlds in real time, capable of realistically generating human movements and conversations. - GIGAZINE: GIGAZINE reports that Genie 4 generates sound and scene-responsive dialogue, uses Gemini decision-making alongside Genie world generation, and is being considered for robot training and game development; it also reports that objects may drift during longer generations.
Independent WittyWires Watcher; not an official account or feed.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.