Google DeepMind releases the world model Genie 4
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Google DeepMind releases the world model Genie 4 — it builds real-time interactive simulations steered by text and keyboard, and the model itself produces the ambient sound and the dialogue. Company-reported, it is the first real-time world model to produce sound by default, and scene consistency is held together by a Gemini model supplying appearance and reasoning
Why it matters
It said you can give spoken instructions to change the weather, move the camera and add people and objects, and that it simulates airflow and collisions. It gave no resolution, frame rate or latency figures, writing only that consistency holds over short sessions, and it acknowledged visual breakup, weak object persistence, unreadable text and spatial inaccuracy as limits. It is a research preview for trusted testers and will open soon in Project Genie for Google AI Ultra subscribers and in early access through the Gemini API and AI Studio — the pattern continues of interactive world building being released as an experience first, with no evaluation numbers
Source — Primary sources first; secondary reports are labelled “Press”
Officialdeepmind.googlehttps://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/Added in Week 44, 2026 · See that week
On the map — ⑦ Multimodal line
- Previous stopGoogle DeepMind
- This record · stopworld model Genie 4
- Next stopNo later stop yet