X (Twitter) Algorithm Explained 2026: How For You Ranks Posts
X (formerly Twitter) runs on an open-source algorithm — one of the few major social platforms where you can actually read the code that determines what gets seen and what gets buried. The system uses machine learning models to score every post based on predicted engagement, author reputation, and content signals. This guide breaks down exactly how the algorithm works, what ranking signals matter most, and actionable strategies to increase your reach based on how the system actually operates under the hood. > **TL;DR:** X's For You feed pulls ~1,500 candidate posts per session, scores each one with a neural network called Heavy Ranker, and ranks on replies, bookmarks, and author reputation — not follower count. Engagement in the first 30–60 minutes is the single biggest distribution lever. External links are actively suppressed; keep them out of your main post.
