Google DeepMind unveiled Genie 4, its new real-time world simulation engine
Google DeepMind announced Genie 4, the fourth generation of its model for simulating interactive worlds generated in real time. The version is natively multimodal: it produces graphics and audio simultaneously, including ambient sounds, music and dialogue that adapt to the action. It adds improved physics with aerodynamics and collisions, and lets users control the scene with keyboard shortcuts and natural-language instructions. It integrates with the Gemini family and targets uses in robotics, film, video games and photojournalism.
In 40 seconds
- Genie 4 is natively multimodal: it generates graphics and sound simultaneously, with music and dialogue that adapt to the action.
- It adds improved physics with aerodynamics and collisions for more believable movement and reactions.
- Users can move through the world with the keyboard and change the scene instantly using natural language.
Read the full story at La Nación
IASummary generated by artificial intelligence from a story by La Nación. It may contain errors: the original source prevails.
Comments
Be respectful. Comments reported by several people are hidden until a moderator reviews them.
You do not need an account to read, only to comment. Sign in with a code sent to your email or with your Google account. We only show the name you choose, never your email.