Google DeepMind introduces Genie 4 world model
In brief
Genie 4 is a real-time world model that generates interactive simulations with native audio and physics. It helps build safe training environments for AI agents and robots.
How it works
Users navigate scenes using standard keyboard controls while steering actions using natural language text prompts. Built on Gemini models, Genie 4 generates real-time audio, lifelike movement, and physics as scenes unfold.
Researchers and developers building AI agents, interactive simulations, and robotic training environments.
Availability
Sources
3 merged into this cardMore from Google

Tool Retrieval in the Gemini API
Gemini's Interactions API now supports on-demand loading of tool parameter schemas. Agents with large tool libraries can keep schemas out of context until needed, cutting input tokens, latency, and selection errors.

Computer use in Gemini app for Mac
Google added computer use to the Gemini app for Mac, letting Gemini automate multi-step tasks across local files, desktop apps, and the web in an isolated background window.