Expired80% confidenceFactExact time
In 2024, Google DeepMind's Genie series can generate interactive 2D/3D game environments from a single image alone.
4
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
7/10/2026
First Seen
Valid until: 10/8/2026(expired)
Sources
MIRA: An Analysis of a Multiplayer Interactive World Model Built on Rocket League
hackernewshackernews7/9/2026
Related Claims
UnverifiedGoogle DeepMind's Genie 1 is based on a Latent Action Model learned unsupervised from internet videos, enabling it to automatically discover virtual controllers from sequences of video frames without any action annotations.70% similarUnverifiedOpus 5 is capable of generating a complete 3D interactive virtual world application in one shot, involving browser-side 3D rendering technologies such as WebGL and Three.js.68% similarUnverifiedFable 5.1 can directly output runnable 3D game scenes, shaders, and complete menu interfaces.64% similarUnverifiedAlibaba's AutoNavi released the general-purpose world model World Studio and opened it for testing, unifying interactive video generation and 3DGS scene generation on the same platform, with output saveable as video and 3DGS files.64% similarUnverifiedGenie 2 extends to 3D scenes, generating 3D worlds with consistent physical laws that support multi-perspective interaction from a single image alone, at real-time generation speed.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/418945API
curl https://kongchang.com/api/v1/knowledge/claims/418945MCP
get_claim(id=418945)