Google DeepMind unveils Genie 2, a model that can generate 3D worlds from a single prompt image, playable by humans or AI agents using keyboard and mouse inputs (Kyle Wiggers/TechCrunch)

Kyle Wiggers / TechCrunch:
Google DeepMind unveils Genie 2, a model that can generate 3D worlds from a single prompt image, playable by humans or AI agents using keyboard and mouse inputs  —  DeepMind, Google’s AI research org, has unveiled a model that can generate an “endless” variety of playable 3D worlds.