@Grummz: So X pulls 35 posts at a time and bumps you if you appear more than once. Reading the replies, the most interesting sug…
Summary
A discussion thread on X proposes changes to the platform's feed algorithm to reduce multiple posts from the same author dominating a batch, including engagement detection and a 'tweet storm' icon.
View Cached Full Text
Cached at: 05/30/26, 06:25 PM
So X pulls 35 posts at a time and bumps you if you appear more than once. Reading the replies, the most interesting suggestions are: a) Some form of engagement detection, so that if you engage with the post, it won’t filter that poster for your next batch. b) Some sort of snooze button. Zero account penalty, but temp mutes the poster. I’d like to suggest one more thing, don’t move the post. Put a “tweet storm” or “X storm” icon next to the initial post and let users expand it to see all of the ones in that 35 batch. That way they don’t take up a full slot, and you can combine it with (a) above as an engagement signal.
Nikita Bier (@nikitabier): Just to be clear on mechanics:
The app pulls 35 posts at a time. If on one of those pulls, an author appears multiple times, they get moved to the next pull.
It’s not ideal and we’d like to find a better solution to big accounts taking up the top slots.
Similar Articles
@DeRonin_: BREAKING: X dropped the new ranking algo today. What's dead and what wins for bangers: [ what just died ]: - spam posti…
X released a new ranking algorithm that penalizes spam, reply farming, text-only posts, recycled viral templates, generic AI tool roundups, engagement bait, motivational fluff, and engagement pods; it rewards original takes from small accounts, threads with clear narrative arcs, text+media combos, contrarian takes with proof, long-form posts, responding to replies quickly, and consistent posting cadence.
@FinanceYF5: What you scroll through on X every day — the algorithm behind it has now been released on GitHub by Musk. This For You system simultaneously grabs content from people you follow and candidate posts from across the network, then uses a Grok-based transformer to predict the posts you're most likely to interact with. The black box of the information feed is being pried open…
Musk has open-sourced X's (formerly Twitter) For You recommendation algorithm on GitHub. The algorithm uses a Grok-based transformer to predict user interaction preferences.
@elonmusk: Critique of the 𝕏 algorithm is welcome. There will be monthly updates of the latest algorithm to GitHub with release n…
Elon Musk announces monthly open-source updates of the X (formerly Twitter) algorithm on GitHub with release notes, inviting critique and reminding users they can opt out of the algorithm via the Following tab.
@Xuegaogx: I probably understand the new algorithm. Now the new algorithm should recommend your tweets more to people who might interact with you. I feel that although my tweet traffic has decreased recently, the interaction rate has increased a lot. I probably understand the new algorithm. Now the …
The user observed that the new algorithm on X platform recommends tweets more to people who may interact, resulting in lower traffic but higher interaction rate.
@LinusEkenstam: I’ve been here since 2007, 19 years. I’m about to give up on X. For the third time in <12 months my account is under im…
A long-time X user (since 2007) expresses frustration over repeated algorithmic suppression of their account, claiming their reach is throttled despite being a Premium+ user and providing value. They call for more transparency from xAI and X about how the algorithm works and why certain accounts are penalized.