Leak: DeepMind's Genie 4 is a real-time world model with native audio and type-to-edit scenes
rohanpaul_ai · x · 2026-10-28
Unverified details circulating about Google DeepMind's Genie 4, billed as its first real-time world model with native audio — generating ambient sound, music and live dialogue from characters that react to users and in-world events.
Key points:
- Users can rewrite a running simulation by typing: change weather, move the camera, add people, with Gemini fitting each edit to the scene while keeping it coherent.
- Gemini 3.8 Flash reportedly acts as an in-loop director, splitting goals into steps and checking incoming frames; Gemini 4 Argon allegedly used the loop to simulate Apptronik's Apollo humanoid playing checkers.
- Access: trusted testers first, then Google AI Ultra subscribers and early Gemini API partners.
More from Models
- OpenAI opens Decisions API beta: up to 10x faster decisions than GPT-6 Luna — OpenAIDevs · 2026-10-28
- Open-Weight AI Security Research Stalls as $80 Fine-Tuning Undoes Safety Interventions — Miles_Brundage · 2026-10-28
- Socher's Recursive Unveils Flint: 125+ tok/s Local Coding Model Built by Automated Research — jeffclune · 2026-10-28
- Liquid AI releases LFM3: six instances spanning text, audio, vision, omni — FinancialAd1961 · 2026-10-28
- Qwen3.8 Flash on a single DGX Spark gets up to 62.7% faster code generation in new update — EAccelerate_42 · 2026-10-28
- Arena co-founder: US still leads frontier AI, but China is winning open models and driving down cost — JaynitMakwana · 2026-10-28