Tags: Max subscription

Anthropic announced that its Claude AI can now control a MacOS computer, allowing it to perform tasks such as opening files, scrolling, clicking, and using apps like Google Calendar or Slack. The capability is limited to Claude Pro and Claude Max subscribers, requires permission before each action, and includes safety safeguards to block prompt injections and other vulnerabilities. Users are advised not to use the feature with apps that handle sensitive data. The new function works with Anthropic's Dispatch service, enabling task delegation from a phone and supporting morning briefings or test runs. Lire la suite

Anthropic introduced Cowork, a new tool that brings the capabilities of Claude Code to a broader audience through a simple folder‑based interface. Integrated into the Claude Desktop app, Cowork lets users designate a folder for the AI to read and modify files, with instructions given via the regular chat window. The feature is currently in a research preview and is limited to Max subscribers, though a waitlist exists for other plans. Anthropic highlighted use cases such as assembling expense reports from receipt photos and warned users about potential risks like prompt injection and ambiguous commands. Lire la suite

Anthropic has introduced a web version of its Claude Code AI coding assistant, featuring a new sandbox that limits file system and network permissions to specific folders and servers. The network isolation works through a Unix domain socket linked to an external proxy that enforces domain restrictions and asks users for confirmation on new requests. Users can customize proxy rules, allowing the agent to fetch npm packages from approved sources without unrestricted internet access. While the changes reduce approval steps and improve security against prompt injection, Anthropic notes that developers must still prioritize code review to catch potential mistakes. Lire la suite