X algorithm myths vs the actual code
Each myth verdict cites the 2026 repo (xai-org/x-algorithm @ 0bfc279) or the frozen 2023 repo (twitter/the-algorithm @ c54bec0). 'Absent from open code' ≠ proven absent from production — withheld crates (params, visibility filtering, Grox prompts) could hide behavior. We say so every time; that's the difference between this site and the folklore.
"One reply is worth 150 likes"
The 13.5-vs-0.5 reply/like ratio (27×, sometimes misquoted as 150×) comes from the 2023 twitter/the-algorithm heavy-rank…
GONE from the 2026 open code"Your TweepCred / PageRank score caps your reach"
TweepCred (the PageRank-style author score with the famous follower/following penalty) exists only in the 2023 repo. The…
NO RULE IN THE CODE"The algorithm nukes posts with external links"
There is no link-detection or link-penalty term anywhere in the open 2026 scoring path — in plain words: nobody wrote a …
MECHANICALLY WEAKENED by the 2026 design"Engagement pods / early-boost groups beat the algorithm"
Phoenix predicts per-viewer engagement probabilities from each viewer's own history — candidates never see each other's …
PARTLY REAL, WRONG MECHANISM"You must get engagement in the first 30/60 minutes or the post dies"
There is no hand-coded freshness decay in the 2026 ranker. Post age enters as a learned feature bucketed in 60-minute st…
NO HASHTAG FEATURE in the 2026 ranker"Hashtags boost your reach"
The ranking model's inputs are ID-hash embeddings, engagement history, surface, and post age. Post text (including hasht…
DISCOUNTED IN CODE"Post 10+ times a day for maximum growth"
The author-diversity decay multiplies your Nth-best post in each viewer's session by (1−floor)×decay^N+floor — your own …
IMPOSSIBLE with what's public"Tool X scores your draft with X's real algorithm"
Two hard blockers, from the code: (1) every 2026 weight lives in an unpublished params service; (2) the released mini-Ph…