Google DeepMind Blog
1. Introducing computer use in Gemini 3.5 Flash
Gemini 3.5 Flash 内置的计算机操作功能使开发者能够构建自动化智能体，支持浏览器、移动和桌面任务，并包含安全措施。 (score: 0.85)
Google DeepMind announces that computer use is now a built-in tool in Gemini 3.5 Flash, enabling developers to build agents that can see, reason, and take action across browser, mobile, and desktop environments. The integration improves performance for long-horizon and enterprise automation tasks, with safety measures including adversarial training and optional enterprise safeguards for prompt injection mitigation.
- Computer use is integrated natively into Gemini 3.5 Flash, improving agentic task performance.
- It enables agents to interact across browser, mobile, and desktop platforms.
- Safety measures include adversarial training and enterprise safeguards for prompt injection.
- Available via Gemini API and Gemini Enterprise Agent Platform.
- Use cases include continuous software testing and knowledge work automation.