Demis Hassabis indicated that Google's Veo 3 could be adapted for video games in response to a user inquiry on X. World models, distinct from video generation models, allow simulation of real-world dynamics but Veo 3 is currently focused on video and audio synthesis. Google is working on a multimodal model, Gemini 2.5 Pro, aiming to incorporate aspects of human brain simulations. DeepMind's Genie 2 can generate countless playable worlds and Google is forming a team for AI models to simulate real-world environments.
Veo 3, which is still in public preview, can create video as well as audio to go along with clips - anything from speech to soundtracks.
World models simulate the dynamics of a real-world environment, allowing agents to predict how the world will evolve in response to their actions.
Collection
[
|
...
]