IT Home, October 17: On October 15, OpenAI updated the ChatGPT extension for Chrome (version 1.26.1005.11759). ChatGPT can now read multiple open tabs in the Chrome browser and use the content from these webpages to answer questions, organize information, or complete cross-tab tasks. This feature is available to all users, regardless of whether they have a paid subscription.
After a user invokes the browser in chat, ChatGPT can use the currently open webpage as context—for example, to compare multiple product pages, summarize multiple documents, or analyze work files.
IT Home, citing a blog post, reports that this update also introduces enhanced "action" capabilities. In Work mode, ChatGPT is no longer limited to reading web pages—it can, with authorization, control tabs to help users fill out forms, send messages, download files, and organize and group tabs.
Since the extension runs within the user’s standard browser configuration, it can reuse the user’s existing login sessions on websites, enabling seamless assistance with workflows in scenarios such as Gmail, LinkedIn, Salesforce, or enterprise internal tools.
However, this convenience comes with greater permission requirements. After installing or enabling related features, Chrome may require the extension to read and modify website data, access page debugging tools, manage tabs and downloads, and even read bookmarks, browsing history, or display notifications.
OpenAI states that these permissions are necessary for ChatGPT to operate a browser, but users can still control its access scope through site-by-site authorization, allowlists, blocklists, and other methods.
By default, ChatGPT requests confirmation before accessing any new website, allowing users to choose “Allow Once,” “Always Allow for This Site,” “Always Allow for All Sites,” or to deny access. Among these, “Always Allow for All Sites” is flagged by OpenAI as a higher-risk option; browsing history and file uploads and downloads also require separate authorization.