Google's Neural Network Generates 3D Worlds to Train Robots
Google has shown a new version of Project Genie, an AI that generates fully functional 3D worlds from Google Street View coordinates. A robot can train in a virtual London or New York without ever leaving the data center. The technology integrates with Unity and Blender, changing how games and robotics are developed.
AI-processed from Habr AI; edited by Hamidun News
Google's Project Genie neural network creates fully functional 3D worlds based on Street View to train robots, allowing them to learn without contact with the physical world.
What is Project Genie?
Project Genie is a generative model from Google that creates interactive 3D worlds tied to real Google Street View coordinates. The model lets robots learn in virtual environments.
How does Project Genie create worlds?
Project Genie builds world models that do not merely generate video but develop an understanding of physics, causality and the three-dimensional structure of the world. The model learns from video and examples of interaction, then generates new virtual scenarios.
- Nov 2, 2026Karpathy builds a YouTube clone with 6454 videos from Hacker News recommendations in two hours
- Nov 2, 2026Karpathy used Claude to build HackerTube from 6,454 videos recommended on Hacker News
- Nov 2, 2026Anthropic needs to grow revenue 32% a year to cover $850 billion in contracts
- Nov 2, 2026Bun creator uses Claude Code to port 750K lines from Zig to Rust in 11 days
Key Questions Answered
What is Project Genie?
Project Genie is a generative model from Google that creates interactive 3D worlds tied to real Google Street View coordinates. The model lets robots learn in virtual environments.
How does Project Genie create worlds?
Project Genie builds world models that do not merely generate video but develop an understanding of physics, causality and the three-dimensional structure of the world. The model learns from video and examples of interaction, then generates new virtual scenarios.
Test Frontier LLMs & Autonomous Agents in One Workspace
Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.