Anthropic's Claude Can Now Use Your Computer To Finish Tasks

Source: Slashdot

New Claude Feature: Computer Use

Anthropic is testing a new Claude feature that lets users send a request from their phone and have the AI carry it out directly on their computer—opening apps, using a browser, or editing files. The move follows the viral spread of OpenClaw earlier this year, which gained cult popularity among developers for running local, 24/7 personal workflows.

• Source: CNBC article
• Anthropic announcement: Claude blog post

How It Works

1. Send a task from a phone – Users message Claude with a request.
2. Claude processes the request – The AI agent interprets the instruction and prepares to act on the user’s computer.
3. Execution on the computer – Claude can open applications, navigate web browsers, fill in spreadsheets, and perform other actions.
4. Permission prompts – Claude always asks for permission before accessing new apps.

Demonstration

In a video released by Anthropic, a user running late for a meeting asks Claude to:

• Export a pitch deck as a PDF file.
• Attach the PDF to a meeting invite.

The video shows Claude successfully completing the task.

• Video: YouTube demonstration

Safety and Limitations

• Anthropic cautions that computer use is still early compared to Claude’s ability to code or interact with text.
• Claude can make mistakes, and while safeguards are being improved, threats are constantly evolving.
• The system includes safeguards designed to minimize risk, and Claude will always request permission before accessing new applications.

Related Feature: Dispatch

Anthropic also released Dispatch as part of Claude Cowork. Dispatch enables a continuous conversation with Claude from a phone or desktop, allowing users to assign tasks to the agent seamlessly.