DeepMind unveils Genie 4 world model promising more realistic physics and humans
Summary
Google DeepMind introduced Genie 4, a world model that generates interactive virtual environments in real time. The company says it improves on physics, human movement, and audio, but environments remain consistent for only a few minutes, and Google has not announced a release date or pricing for developer access.Key Facts
- Genie 4 generates virtual environments frame by frame as users explore them.
- DeepMind says Gemini 3.8 Flash helps Genie 4 interpret goals and keep simulations on track.
- Users can change elements such as weather and camera position while a simulation runs.
- DeepMind says Genie 4 better simulates physics, including aerodynamics and collisions, and produces more natural human movement.
- Genie 4 is DeepMind’s first world model with built-in audio generation, including ambient sounds and interactive dialog.
- DeepMind says its world models remain an active research project, and Genie 4 worlds retain consistency for only a couple of minutes.
- Google plans to offer Genie 4 to developers through the Gemini API and AI Studio, but has not announced pricing or a release date.
- Consumer access will roll out in phases through Google’s AI Ultra plans, which start at $100 per month.
Read the Full Article
This is a fact-based summary from The Actual News. Click below to read the complete story directly from the original source.
