Gemini Gains Direct Control Over macOS Tasks
Google has officially rolled out a new "computer use" capability for its Gemini application on macOS. This update enables the AI to perform multi-step tasks by interacting directly with a user's local files, desktop applications, and web browser, effectively allowing the AI to operate the computer on the user's behalf.
Enhancing Workflow Efficiency
According to Google, this feature is designed to assist users in automating complex or repetitive tasks. Potential use cases highlighted by the company include:
- Streamlining administrative workflows
- Filling out complex digital forms
- Assisting in the creation of presentation slides
- Organizing and listing items for sale across various platforms
User Control and Transparency
To address privacy and security concerns, Google has implemented granular controls. Users retain the authority to decide exactly which applications Gemini is permitted to access. Furthermore, the company has introduced a live preview mechanism; as Gemini executes tasks, it operates within a dedicated background window, allowing users to monitor the AI's actions in real-time within the chat interface.
This feature is currently being deployed to users in the United States and is available exclusively in English. The introduction of this capability marks a significant step in Google's strategy to integrate its AI more deeply into the desktop environment, arriving as the broader industry continues to push for more autonomous AI agents capable of navigating traditional software interfaces.
Source: The Verge. Rewritten and translated for PromptsFA.
