Google's Project Genie lets you create your own 3D interactive worlds (www.engadget.com)

Google DeepMind has launched Project Genie, allowing users to create their own 3D interactive worlds using Genie 3, an advanced AI system that generates images and responds to user movements in real-time. Previously available only for training AI agents, Genie 3 is now accessible to external users through Google's $250 monthly AI Ultra plan, although availability is limited to adults in the US. The platform offers three interactive modes: World Sketching, exploration, and remixing, enabling users to define characters, camera perspectives, and explore AI-created environments, all while using the underlying Nano Banana Pro model to sketch preliminary designs. This launch is significant for the AI/ML community as it democratizes access to cutting-edge generative AI technology, fostering creativity and experimentation among users. However, it's important to note that Project Genie functions differently from traditional game engines; while it can simulate environments, it lacks standard game mechanics and limits output to 60 seconds at 720p resolution and 24 frames per second. This initiative showcases DeepMind's advancements in AI, presenting a unique opportunity for developers and enthusiasts to engage with innovative tools and push the boundaries of interactive AI experiences.