Tag
Google DeepMind announced Genie 4 alongside an upgraded Project Genie experience in the browser, enabling mid-session prompt steering, synchronized audio, a natural-language world-building agent, and a community gallery for exploring and remixing worlds.
Google DeepMind 发布 Genie 4,一个面向创作者、游戏开发者和 AI 研究者的实时世界模型,可根据文本提示生成可交互探索的动态世界,并生成音频、模拟物理运动,目前开放研究预览候补名单。
Google DeepMind 发布 Genie 4 世界模型,利用 Gemini 3.8 Flash 作为引导智能体,在物理模拟、人物表现和音频支持上较 Genie 3 全面提升,可实时生成可交互的虚拟世界。DeepMind 认为世界模型是通往 AGI 的关键一步,可用于机器人训练环境与创意原型设计。
Practical tips for setting up a Genie AI-powered natural language query tool for sales/pipeline data, emphasizing that curated example SQL and metadata are more effective than free-text instructions.
Databricks introduces Agent Mode API for Genie Agent, providing a new interface for building and managing AI agents on the platform.
Google's Genie 3 can generate a playable open world from a text prompt or image, but it's currently rough with low framerate and bugs, sparking debate on whether it threatens traditional game development or will plateau as a demo.
Google DeepMind integrates Street View data into its Genie world model, allowing interactive simulation of real-world streets for applications in robotics, autonomous driving, and user experiences.