谷歌 Genie 4 模型增強交互式 AI 世界的真實感
谷歌宣布 genie 4，一款生成更真實交互式世界的 AI 模型，新增音訊功能，基於 gemini 3.8 flash。這可能有助於電影製片人、遊戲開發者和機器人訓練師。
google has unveiled its genie 4 world model, designed to generate interactive experiences using ai. the new model boasts four key updates: enhanced realism, real-time updates via natural language prompts, audio generation, and longer simulation times of up to two minutes, compared to one minute for its predecessor, genie 3. genie 4 utilizes gemini 3.8 flash to enhance its simulations. google is positioning genie 4 as a tool for various applications, including pre-visualization for filmmakers, game idea prototyping, and creating training scenarios for robots. however, the company notes that as simulations run longer, details and object permanence may shift over time. genie 4 is set to be available soon for google ai ultra subscribers, with a waitlist currently open for those interested in trying it out in project genie.