The way we create and explore virtual worlds is evolving at lightning speed. From hackathon prototypes to cutting-edge AI research, developers and companies are experimenting with technologies that turn imaginations into immersive, explorable environments. Recently, builders and researchers alike have proven just how far AI-generated worlds can reach: from robotic simulations and interactive museums to infinite AI landscapes.
The first World Labs Hackathon (WL-HACK 01) brought together 70 hackers in San Francisco to try out Marble, a platform for building interactive worlds. In just 3.5 hours, 32 teams created an impressive array of projects spanning AR/VR interfaces, games, art experiences, and real estate tools.
Best projects included:
- Museum of the World – Visitors can step inside famous paintings, from Van Gogh’s bedroom to worlds inspired by Vermeer and Matisse.
- Jar of Marbles – A semantic interface for organizing marble worlds into collections, navigable via computer vision gesture controls.
- Virtual Augmented Room – a robotics simulation where the robot uses LiDAR technology to explore a marble environment, creating semantic maps and annotating its surroundings in real time.
The hackathon highlighted the creativity and potential of global AI-based models, demonstrating how quickly innovative ideas can take shape when builders have the right tools.
Google is also moving forward Interactive AI worlds with Project Geniea beta prototype is now available to Google AI Ultra subscribers in the United States. Powered by Genie 3, Nano Banana Pro and Gemini, Project Genie enables users to create, explore and remix AI-generated worlds in real-time.
Unlike static 3D shots, Project Genie creates the environment dynamically as users move around, simulating physics, interactions, and environmental changes. Sessions are currently limited (mostly around 60 seconds in early testing), but worlds can be remixed, explored in curated galleries, or recreated for new experiences.
Project Genie offers three main capabilities:
- World Drawing: Create worlds from text or uploaded images, and preview them with Nano Banana Pro to adjust style and perspective.
- Explore the World: Move through the world from a first-person or third-person perspective while the AI shows the path forward in real-time.
- Remix the world: Transform existing worlds with new prompts or create entirely new experiences, then export explorations as videos.
Although still beta, Google emphasizes responsible development, noting occasional input lag, limited session duration, and some inconsistencies with physics or character behavior.
