Google’s next Genie AI model generates more realistic experiences
Google announced Genie 4, the latest version of its generative world model for creating interactive experiences with AI. Key improvements include more realistic worlds, real-time updates via natural language prompts, audio generation capabilities, and extended experience length of up to two minutes (doubled from the previous one-minute limit). The model uses Gemini 3.8 Flash for enhanced simulations. Google positions Genie 4 as useful for filmmaker pre-visualization, game prototyping, and robot training scenarios.
Key points
- Genie 4 generates more realistic, interactive AI experiences controllable via natural language.
- Extended to 2-minute experiences; now includes audio generation.
- Designed for filmmaking, game design, and robotics training applications.
Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. The Verge did the reporting; read the original for the full story.
Read the full story at The Verge
