YouTube Rolls Out AI-Powered Custom Feeds for Personalized Recommendations
YouTube is announcing a new feature called custom feeds that lets users describe, in their own words, the kinds of videos they want recommended to them. Users type a description into a prompt box on YouTube, whether they want a feed dedicated to a particular interest or something more specific, such as video podcasts for a 30-minute train commute or relaxing commentary videos to unwind with.
The prompt-based feature leverages Google's Gemini AI model to build the feed, which is then pinned to the top of the YouTube home page in its own tab. Because feed creation is AI-powered, users can share detailed instructions about what the feed should feature or exclude and what content to prioritize. The move follows similar efforts by Bluesky, Meta's Threads, Instagram, X, and Spotify, all of which now offer tools that let users build their own algorithms.
YouTube says custom feeds will help users better explore the more than 20 billion videos hosted on its platform. Emily Moxley, VP of Product Management for Viewer AI, notes that users are always one search away from a treasure trove of topics. The new feeds do not replace YouTube's main recommendation feed; instead, users can easily hop between whichever feed best suits their needs.