computer use

muse web browser manual control muse agent users a laptop with a large pointer arrow

Muse Agent Users to Gain Manual Control Over the Muse Web Browser

Muse agent users will soon be able to take over and operate the Muse web browser from the web app, according to a new test build. We explain how manual control works, when you would use it, what Meta says happens to the agent and your passwords during a takeover, and how Muse compares with ChatGPT agent, Operator and Claude in Chrome.

Read more
muse agent dedicated vm tab voice mode widget a desktop monitor with a tab strip

Muse Agent Adds Dedicated VM Tab and Updated Voice Mode Widget

A new Muse web build adds a dedicated tab for watching the agent’s cloud computer screen and turns voice mode into a phone-call style widget, and a second clip shows browser takeover on the way. We explain each change, compare Muse with ChatGPT agent and Operator, and separate what Meta has confirmed from what has only been seen in builds.

Read more
gemini task mode desktop gemini live computer use a open laptop with a tilted screen panel

Gemini Desktop Task Mode to Support Gemini Live and Computer Use Settings

Google’s Gemini desktop app now has a switch between Chat and Tasks, and trusted testers are starting to receive Gemini Task mode, the home of its computer use agent. Tasks carries a Gemini Live entry point, hinting at voice-controlled computer use on top of the new Gemini 3.8 Live model, and a new settings menu lets users choose allowed and disallowed apps. This article covers what TestingCatalog found, five weeks of computer use traces, the Drive backup and large-folder problem, Windows and Workspace admin controls, and what businesses should decide before rollout.

Read more
CHAT