World Models Are Next: Building 5 Interactive Worlds Live with Genie 4 + Gemini
petergyang · x · 2026-10-29
Peter Yang argues world models are the next big thing after LLMs. In a new video he uses Google Genie 4 + Gemini to build 5 interactive worlds live — a kaiju attacking San Francisco, eating ramen at a Tokyo street stall, riding a dragon to storm a castle.
Beyond the graphics, he was most impressed by the live audio and interactivity, and shares his take on what this means for movies and gaming.
More from Multimodal
- NVIDIA FastGen ships major update: FLUX.2, LTX-2.5, Cosmos 3 plus four new acceleration methods — ArashVahdat · 2026-10-29
- Shading and lighting upgrade teased for AI-generated slop_eisley project — jasonkneen · 2026-10-29
- Rime launches Prism, a speech-to-speech model that kills dead air in voice agent calls — testingcatalog · 2026-10-29
- Tavus shares Griffin BTS clips showing real-time listening, room awareness and turn-taking — aftahi_ai · 2026-10-29
- Tiny Hikers Cross a Pasture as Mountains Fill the Whole Horizon — misovalko · 2026-10-29
- Darius: Fully Local ComfyUI Creative Canvas Running Multiple Image Models — neofuturist · 2026-10-29