Genie
See how promptable interactive environments differ from ordinary generated video or hand-authored game levels.
Interactive world model
A playable environment emerges from learned rules, not a hand-authored game level.
What people can do
Start from the practical surface before reading sources and boundaries.
See how promptable interactive environments differ from ordinary generated video or hand-authored game levels.
A playable environment emerges from learned rules, not a hand-authored game level.
Real-time playable worlds, promptable environments, Street View-grounded scenes, and agent evaluation.
Scene explainer
The page starts with the experience, then moves toward source-backed details.
01First impression
Genie 3 is positioned as a frontier world model for generating and navigating interactive environments from prompts.
02Capability
Directly frames the output as an interactive world rather than a fixed video clip.
03Boundary
Access is still gated through the experimental Project Genie rollout and is not a broadly open developer platform.
Genie 3 is an experimental interactive world-model preview, not a generally available developer API or productized 3D asset tool.
Release signals
The company profile stays stable. These short signals explain what changed and point back to sources.
Google connected Project Genie to Street View-grounded scenes and tied the rollout to eligible Google AI Ultra subscribers instead of positioning it as a broad public API launch.
ResearchGoogle DeepMind presented Genie 3 as an interactive world-model frontier rather than a fixed clip-generation model.
FAQ
Use these notes to keep model comments grounded in official sources and careful category boundaries.
The site tracks systems that model environments, actions, spatial structure, or persistent simulated state. Pure text chatbots and ordinary video generators are only included when they provide a clear bridge toward interactive or physical world modeling.
Video models are included only when they help explain the path from generated clips to controllable spaces, physics-aware prediction, or agent-ready simulation. The site keeps that distinction explicit so video generation is not overstated as a finished world simulator.
Primary sources carry the most weight: official product pages, research posts, papers, documentation, code repositories, and company announcements. Secondary media can be referenced, but it stays labeled as reported or adjacent unless independently confirmed.
Useful comments add source links, corrections, release-status notes, comparison questions, or concrete reader context. Comments are public immediately, so readers should avoid private information and unsupported promotional claims.
Discussion
Add source-backed corrections, questions, or notes for this page.
No comments yet. Start with a source note or a question for future coverage.