This is game engine 2.0. Some day, all the complexity of UE5 will be absorbed by a data-driven blob of attention weights. Those weights take as input game controller commands and directly animate a spacetime chunk of pixels.
Agrim and I were close friends and coauthors back at Stanford Vision Lab. So great to see him at the frontier of such cool research! Congrats!
Introducing Genie 3, our state-of-the-art world model that generates interactive worlds from text, enabling real-time interaction at 24 fps with minutes-long consistency at 720p. 🧵👇
Aug 5, 2025 · 3:03 PM UTC


































