Project Genie is a new initiative from Google DeepMind that allows users to create and explore interactive worlds using its Genie 3 model. This prototype is currently available to Google AI Ultra subscribers aged 18 and older in the U.S. The core features of Project Genie include world sketching, exploration, and remixing. Users can design their environments using text prompts and images, navigate through them in real-time, and modify existing worlds for new experiences. The goal is to enable a more immersive interaction with AI-generated environments. Genie 3 stands out because it simulates dynamic worlds rather than static 3D environments. As users move through these worlds, the system generates paths and interactions in real-time, making the experience more engaging. However, the technology is still in an experimental phase, with known limitations such as the realism of generated worlds, control over characters, and a restriction on world generation time to 60 seconds. The project reflects Google’s commitment to responsible AI development. They acknowledge areas for improvement, including the fidelity of visual representations and the latency issues with character control. While some features announced previously, like promptable events, are not yet included, the focus is on gathering user feedback to enhance future iterations. Access to Project Genie will expand to more users beyond the initial rollout, aiming to explore its potential across AI research and creative applications.