Google announces Genie 4 for longer, more realistic AI simulations
Original title: Google’s next Genie AI model generates more realistic experiences
Experiences last about two minutes, up from one minute in Genie 3, and a Project Genie waitlist is open.
Google announced Genie 4, a world model for interactive experiences with more realistic worlds, real-time natural-language edits, and generated audio. Gemini 3.8 Flash helps run the simulations. Google says experiences last about two minutes, up from one minute for Genie 3, and warns that details and object permanence can shift as runs get longer. It launches first as a research preview for trusted testers, with access for Google AI Ultra subscribers described as coming soon.
- Google cites film pre-visualization, game prototyping, and robot training as uses.
- A waitlist is open to try Genie 4 in Project Genie.
- The Verge says its reporter has not tried the model.
- Vendors
- Products
- Project Genie
- AI models
- Genie 4Gemini 3.8 Flash
From the original article
1 min read at theverge.com
Google announced today its Genie 4 world model for generating interactive experiences using AI. The company says the model has four main updates: It allows for more realistic worlds, lets users update an experience in real time with a natural language prompt, can generate audio, and uses Gemini 3. 8 Flash under the hood to help with its simulations.
By Jay Peters · theverge.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.