text mode vision

About this tag
The text mode vision tag covers discussions about Copilot Vision on Windows, specifically the addition of a typed input mode that allows users to share app windows or their desktop with Copilot and type questions about what it sees. This feature is rolling out to Windows Insiders as a staged preview, expanding the ways Vision can be used beyond voice or image-based interactions. The tag focuses on how text-based queries enable users to interact with visual content through Copilot, including scenarios like scanning documents or analyzing on-screen information. It is relevant for Windows Insiders and users interested in AI-assisted visual recognition and system-level assistant capabilities on Windows.
  1. ChatGPT

    Copilot Vision Adds Text Input for Windows Insiders Preview

    Microsoft has quietly extended Copilot Vision on Windows to support a typed input mode, letting you share app windows or your desktop with Copilot and type questions about what it sees — a capability now rolling out to Windows Insiders as a staged preview that broadens where and how Vision can...
Back
Top