Google has shipped a new Gemini desktop app update that moves its Computer Use functionality into a new testing phase. The app now includes a switch between Chat and Tasks, with trusted testers beginning to receive access to Tasks mode. TestingCatalog does not yet have access to the mode itself.
One notable detail is that Tasks, like regular Chat, includes an entry point to Gemini Live. This suggests users could eventually operate Computer Use tasks through real-time voice, asking Gemini to work with their laptop while maintaining a live conversation. Google also released Gemini 3.8 Live on September 15. The new real-time audio model offers asynchronous function calling and support for carrying out tasks during dialogue, making it a natural fit for this experience.
Computer Use settings are also becoming more granular. A new menu lets users configure allowed and disallowed apps, providing control over which applications Gemini can operate. The previously spotted option to start a Gemini project directly from a folder has also become more prominent and appears to be entering trusted testing.
Together, these additions show how Google is positioning the Gemini desktop app as more than a standalone chat client. The Windows app only launched publicly earlier this month, while Google has already been expanding Gemini toward cross-app task execution and background workflows. A production rollout of these Computer Use features could still take weeks or longer, depending on testing.
Separately, rumors around Gemini 4 continue. Some testers have reported responses apparently associated with a Gemini 4 Pro checkpoint while using Gemini 3.8 Flash, although the exact model identity remains unclear. TestingCatalog has previously spotted references to the Gemini 4 family, but it remains unclear which checkpoint Google ultimately plans to release under that name.
Editorial notes
- Google recently announced the Gemini app for Windows in September as well.
- Google announced Gemini 3.8 Live and 3.8 Live Extended Thinking on September 15, describing voice tasks and asynchronous function calls.
