Facebook will let you customize your feed algorithm using AI

Meta has introduced a new feature called 'Your Algorithm' that gives users direct control over what content appears in their Facebook feed and Reels. Rather than relying solely on Meta's automated recommendation engine, users can now manually add or remove topics they want to see more or less of, and the system adjusts recommendations immediately after each interaction.

The feature works by letting users mark specific topics as 'interested' or 'not interested,' which feeds back into Meta's underlying recommendation models. This gives users a more transparent and hands-on way to shape their content experience, addressing long-standing complaints that social media feeds feel opaque and difficult to control.

From an AI perspective, this is a notable shift toward user-in-the-loop recommendation systems. Instead of treating the algorithm as a black box, Meta is surfacing the controls and letting human preferences directly influence model outputs. This approach could improve user satisfaction and trust, though it also raises questions about how much manual curation users will actually engage with over time.

The broader industry trend here is toward greater algorithmic transparency and user agency. Several platforms have been experimenting with similar controls, and Meta's move signals that AI-powered personalization is evolving from a purely automated process to one that incorporates explicit user intent as a first-class input.

This page provides an editorial summary based on publicly available information. It is not a republished article. Use the source link below for the original report.