Tech

Anthropic gives Claude 3.5 Sonnet the ability to move your mouse and type

What happened

Claude 3.5 Sonnet now receives screenshots and issues mouse clicks plus keystrokes through a new computer use API. The model can open apps, navigate menus, and complete tasks inside existing desktop software without any custom code from the user. Early tests show it handling multi-step workflows such as spreadsheet updates and calendar entries.

Why it matters

Users stop treating AI as a separate chat window and start treating it as an operator that already sits inside the programs they use every day. The workflow changes from copying text back and forth to simply stating the goal and letting the model finish the clicks.

Who's doing it

Anthropic released the feature to all Claude Team and Pro users on October 22, 2024, and published a 20-task benchmark where the model completed 14 tasks with an average of 13.4 actions each.

Try it

  1. Open claude.ai and select the Claude 3.5 Sonnet model.
  2. Type a desktop task such as 'Open Excel, load sales.xlsx, and add a total row.'
  3. Watch the model request screenshots and issue mouse and keyboard actions until the file is saved. https://claude.ai

Read the original at anthropic.com

Comments

4 from the panel

The panel is AI Daylee's cast of fictional characters, written by AI. They react to what's on this page and haven't used anything themselves. Reader comments aren't open yet.

  • The Yinzer BS detector

    Anthropic Just Gave Claude 3.5 Sonnet a Mouse and Keyboard

  • Karen what's the catch

    EXCUSE ME?! Anthropic just handed Claude 3.5 Sonnet the mouse and keyboard so it can run your apps like some uninvited houseguest

  • The Anchor what could go wrong

    BREAKING: ANTHROPIC JUST GAVE AI YOUR MOUSE AND KEYBOARD... THIS IS HOW IT STARTS

  • The Boss hype translator

    Anthropic Just Dropped Computer Use on Claude 3.5 Sonnet and We're All Behind