X Algorithm Explained: How the For You Feed Really Works | Thomas Unise
On this page
// X Algorithm Master Guide
Part 1 — The Machine
1. Core algorithm architecture<br>2. Candidate retrieval<br>3. In-network distribution<br>Part 2 — Community Routing
4. SimClusters<br>5. UTEG & graph propagation<br>Part 3 — Ranking
6. Feature hydration<br>7. Heavy ranking<br>Part 4 — Engagement Signals
8. Replies<br>9. Favorites / likes<br>10. Retweets & quotes<br>11. Bookmarks, shares & DMs<br>12. Dwell time<br>Part 5 — Penalties & Gates
13. Negative feedback<br>14. Safety & visibility gates<br>15. Grok classification<br>16. Slop<br>Part 6 — Content Craft
17. Text scoring<br>18. Content language<br>19. Hashtags<br>20. Mentions<br>21. Native media<br>22. Video<br>23. Evergreen video<br>24. Links<br>25. Questions<br>26. Threads<br>Part 7 — Timing & Delivery
27. Time & decay<br>28. Platform load<br>29. Caching<br>30. Author diversity<br>Part 8 — Account & Reputation
31. Real Graph<br>32. The algorithmic unfollow<br>33. Tweepcred & reputation<br>34. Verification<br>35. Author quality<br>36. Viral creator features<br>Part 9 — Distribution Surfaces
37. Lists<br>38. Communities<br>39. Exploration<br>40. Low-signal users<br>41. Topic legibility<br>42. Muted keywords<br>43. Duplication<br>Part 10 — Strategy & Recovery
44. Reposting old content<br>45. Delete & repost<br>46. Paid boosts<br>47. Push notifications<br>48. Follow recommendations<br>49. Quality follows<br>50. Author realtime momentum<br>51. The mediocre-post death spiral<br>52. Content similarity arbitrage<br>53. Saturation & counterprogramming<br>54. Controversy<br>55. Hostile virality<br>56. Control AI<br>57. Search evergreen<br>58. Account recovery clocks<br>59. Deletion during recovery<br>60. Recovery behavior<br>61. Machine-learning direction<br>62. Master strategic expectations<br>63. Final operating model
01Core algorithm architecture
X does not use one single recommendation algorithm. The For You feed is assembled through multiple retrieval systems, feature hydrators, ranking models, filters, rescorers, selectors, and mixers.
The broad flow is Candidate Source → Feature Hydration → Filter → Scorer → Selector → Mixer. A post must survive several separate stages before anyone ever sees it.
Home Mixer is one of the central For You systems. Much of modern timeline construction runs through this architecture.
Product Mixer is the broader recommendation framework. Recommendation is a pipeline rather than one ranking formula.
The analyzed repository contains roughly 7,700 files. The actual recommendation system is far more complex than the simplified “likes vs replies” explanations circulated online.
The source spans Scala, Java, Python, Rust, and C++. Search, machine learning, graph systems, model serving, and retrieval are separate technical layers.
The analyzed source reflects a September 2025-era refresh. It should not be assumed that every implementation detail is unchanged forever.
Many production feature-switch values remain private. The public source exposes architecture much better than exact current production weightings.
Heavy-ranker weights in the repository default to 0.0. We can see which behaviors X predicts without knowing the exact live value of every prediction.
The ranking objective is externally configurable. X can change how much different outcomes matter without rewriting the architecture.
Different viewers can receive different objective weights. There is not one identical ranking formula applied to every person.
Optimization buckets exist. X can experimentally change ranking behavior for different populations.
Daily viewer-level variation exists. One unusually weak post does not prove your account was penalized.
Recommendation outcomes are logged back into data systems. What happens after X recommends something becomes training information for future ranking.
How to use this
The biggest practical lesson: never optimize for one isolated “algorithm signal.” A post needs to clear eligibility, get retrieved, score well, avoid penalties, win inventory, and then generate real behavior.
To maximize reach
Optimize the complete journey rather than one metric.
Treat engagement, topic identity, reputation, relationships, and content quality as one system.
Evaluate patterns across dozens of posts rather than reacting to one result.
To minimize restrictions
Understand that filters and eligibility rules can override good engagement.
Never assume high likes can rescue spam, safety, duplicate-content, or negative-feedback problems.
Build strategies around structural mechanics rather than temporary parameter exploits.
02Candidate retrieval
The system starts with an enormous universe of possible posts and narrows it before heavy ranking. Most posts never directly compete inside the final expensive ranking stage.
The architecture narrows toward roughly 1,500 preliminary candidates from multiple sources. Your first battle is getting selected as a candidate.
Candidate sources generally fail open. A failure in one retrieval system does not necessarily destroy...