Microsoft has introduced Copilot Vision, a cutting-edge feature of its AI-driven assistant, now available for free within the Edge browser. This feature, announced by Microsoft AI CEO Mustafa Suleyman on Bluesky, empowers the assistant to ‘see’ and understand the content displayed on a user’s screen.
Copilot Vision delivers what Microsoft calls a ‘conversational experience’. By clicking the microphone icon, users can provide voice commands, allowing Copilot to interpret on-screen content and offer tailored responses or guidance. For instance, users can request step-by-step instructions while exploring a recipe or seek an analysis of a job listing to prepare for a personalized interview. However, Microsoft advises against relying on AI for critical document preparation, such as resumes.
Currently, full system integration of Copilot Vision is exclusive to Copilot Pro subscribers. These subscribers can leverage Vision not only in the Edge browser but also across platforms like Photoshop, video editing software, and even games like Minecraft.
Edge users can still access Vision’s basic capabilities. After registering through a dedicated link on Microsoft’s website, users can initiate a Vision session by clicking the microphone icon within the browser. A sound and a change in the browser’s color scheme signal the session’s commencement. Microsoft assures that during the process, only Copilot’s responses are recorded, with no screenshots, content, or voice commands being collected. To conclude the session, users can either end it manually or close the browser. However, users should note that the feature may not function on all websites.
Yorum Yap