X (Twitter) For You Feed Algorithm Explained

X (Twitter) For You Feed Algorithm Explained

George Eeken Blog

Introduction

𝕏 has (partly) open-sourced its new For You Feed/Timeline ranking algorithm.

The prior algorithm, Heavy Ranker (2023), has been upgraded to Phoenix (2026).

While Heavy Ranker was developed manually by Engineers who defined hundreds of features and tweaked weights to guess what you wanted, Phoenix is powered entirely by the same transformer architecture as xAI’s Grok (LLM) model, based on prior (and predicted) users’ actions.

Since January 20, 2026, the open-source code has been available on GitHub, and it’s refreshed every 4 weeks.

This publication puts an end to all guessing and speculation about why specific tweets show up in someone’s timeline and why others don’t.

So, let’s dive in and analyze how publishers Γ‘nd marketers can maximise their reach, engagement, and (marketing) exposure on 𝕏.

Or as a 𝕏-user, how to optimize your behavior to really get all the posts in your timelines you want to see and engage with.

The 𝕏 Algorithm in simple terms

The For You feed algorithm retrieves, ranks, and filters posts from two sources:

  1. In-Network (Thunder): Posts from accounts you follow
  2. Out-of-Network (Phoenix Retrieval): ML-based similarity Posts discovered from a global corpus

Both sources are combined and ranked together usingΒ Phoenix, a Grok-based transformer model (LLM-based). that predicts engagement probabilities for each post. The final score is a weighted combination of these predicted engagements.

The Algorithm has eliminated every single hand-engineered feature and most heuristics from the system. The Grok-based transformer does all the heavy lifting by understanding your engagement history (what you liked, replied to, shared, etc.) and using that to determine what content is relevant to you. Your interests in real-time. It doesn’t follow rigid rules; it learns patterns.

Instead of a single score, the model predicts multiple actions (19) and combines them into a more nuanced ranking.

Positive actions (likes, reposts, shares) have positive weights. Negative actions (block, mute, report) have negative weights, pushing down content the user would likely dislike.

The algorithm uses your last 128 posts you’ve engaged with and, based on different engagement activities (with different weights), makes predictions for each Candidate post. The higher the predicted likelihood, the higher the ranking.

The system is modular, transparent, and stable, with each post scored independently, so results are cacheable and consistent. Meaning, everything you engage with recently will determine your feed.

The 𝕏 Algorithm in scheme

Source: https://github.com/xai-org/x-algorithm/

The 𝕏 Algorithm Architecture: How it Works

The Pipeline Stages

  1. Query Hydration: Fetch the user’s recent engagement history and metadata (eg. following list)

  2. Candidate Sourcing: Retrieve post candidates from:

    • Thunder: Recent posts from followed accounts (in-network)
    • Phoenix Retrieval: ML-discovered posts from the global corpus (out-of-network)

  3. Candidate Hydration: Enrich post candidates with:
    • Core post data (text, media, etc.)
    • Author information (username, verification status)
    • Video duration (for video posts)
    • Subscription status

  4. Pre-Scoring Filters: Remove posts for these purposes:

    Filter Purpose
    DropDuplicatesFilter Remove duplicate post IDs
    CoreDataHydrationFilter Remove posts that failed to hydrate core metadata
    AgeFilter Remove posts older than threshold
    SelfpostFilter Remove user’s own posts
    RepostDeduplicationFilter Dedupe reposts of same content
    IneligibleSubscriptionFilter Remove paywalled content user can’t access
    PreviouslySeenPostsFilter Remove posts user has already seen
    PreviouslyServedPostsFilter Remove posts already served in session
    MutedKeywordFilter Remove posts with user’s muted keywords
    AuthorSocialgraphFilter Remove posts from blocked/muted authors

  5. Scoring: Apply multiple scorers sequentially:

    • Phoenix Scorer: Get ML predictions from the Phoenix transformer model
    • Weighted Scorer: Combine predictions into a final relevance score
    • Author Diversity Scorer: Attenuate repeated author scores for diversity
    • OON Scorer: Adjust scores for out-of-network content

  6. Selection: Sort by score and select the top K candidates

  7. Post-Selection Processing: Final validation of post candidates to be served

    Filter Purpose
    VFFilter Remove posts that are deleted/spam/violence/gore etc.
    DedupConversationFilter Deduplicate multiple branches of the same conversation thread

The 𝕏 Algorithm Phoenix Scorers explained

The Phoenix Grok-based transformer model predicts probabilities for multiple engagement types:

TheΒ Weighted ScorerΒ combines these into a final score:

Final Score = Ξ£ (weight_i Γ— P(action_i)) + NEGATIVE_SCORES_OFFSET

Basically, the positive engagements on your post minus the negative engagements.

Note 1: If you analyse the code, you’ll notice that there are actually 19 different scorers. (As there are 3 different Share types, and 2 measurements for Dwell (score and time).

Note 2: For retweets, Phoenix looks up predictions using the original tweet ID.

Note 3: In addition to the vqv_score (Video Quality View), there is an additional weight (vqv_weight_eligibility) that assigns additional positive points if the video length exceeds a specific minimum duration. The consensus is that this current minimum duration is 2 minutes.

So, although the exact Model Weights and Parameters are hidden, there is a common belief that not all engagement scorers are treated equally. Some are more important (have a higher weight) than others.

I found these Relative Weights (source: https://x.com/CryptoKaleo/status/2013499298013393374)

After the Phoenix scoring, there are two additional filters (called scorers):

  • Author Diversity Scorer: Attenuate repeated author scores for diversity. This means that after your first post appears in someone’s feed, each additional post gets a progressively lower score. You can’t dominate anyone’s timeline. The diversity penalty is applied AFTER the ML scoringβ€”meaning even if all your posts would score highly, they get knocked down just for being from the same author.
  • Out-of-network (OON) Scorer: Adjust scores for out-of-network content. Prioritise in-network candidates over out-of-network candidates.

The architecture is public, while the “brains” of the operation remain hidden

This open-sourced architecture describes the main modules. However, “for security reasons”, 3 modules are still hidden: the Clients, Params, and Util mods.

So, this public release is essentially a framework without the engine:

  1. Missing Weighting Parameters – The code confirms that “positive behaviors add points” and “negative behaviors deduct points”, but the exact numerical values are stripped out.
  2. Hidden Model Weights – The internal parameters and calculations of the model are not included.
  3. Undisclosed Client and Training Data – There is zero visibility into what data trained the model and how user behavior is sampled.

Source: https://x.com/BlockFlow_News/status/2013510113873813781

The core principle of the algorithm

Each 𝕏-user gets a unique, personalised timeline Feed that shows different Posts (and Ads) based on their recent engagement history, metadata, and xAI’s Grok LLM model.

This principle applies to both the “For You” feed (out-of-network posts, discovered through ML-based retrieval) and the “Following” feed (in-network posts).

This xAI Grok LLM model looks at these interrelationships:

  1. User Profile data: The bio, interests, following, followers, location, and other users’ data. Including data about how the user (re)acts and engages on the platform (recently and in general).
  2. Poster Profile data: The bio/profile, interests, following, followers, and other data. What topics/interests is the Poster posting about?
  3. Recent explicit engagement interaction between Poster and User.
  4. Recent explicit engagement interaction between the User and (similar) other Posters.

So, the Poster has no direct influence on whether his post is shown in someone’s timeline.

Only indirectly, as per the algorithm, the chance increases if the (potential) User is a Follower of the Poster, and/or (recently) engaged with each other (either in public or in private chats).

Hence, it’s the user who sits in the driver’s seat; his prior (engagement) actions with all potential post Candidates control the ranking of his timeline(s).

Note that the algorithm produces the results for a Session and uses an Age Filter (only recent posts are shown). In the next Session, the results will be different (Tip: bookmark or save Posts you like and don’t want to “lose”)

The 𝕏-platform is a commercial platform that encourages usage as often and for as long as possible (to maximise ad revenue). The primary way to do this is to show content that users prefer. Hence, by “learning and collecting personal data” and “improving the user experiences” to give users what they like and want.

So, as a user, be careful about how you engage. Your feed is literally what you train it to be. If you keep interacting with drama, bait, or low-quality takes, that’s what your X-Timeline experiences become for you. The algorithm is just mirroring your own behaviour.

So, as a user, you can actively “inform” the algorithm what you want to be included in your timeline(s). Just increase your “positive” engagement actions as per the Phoenix scorer, and clean up your feed by taking “negative” actions.

Also, users can enter/visit the 𝕏-platform in many ways.

Some will visit their home timeline regularly, while others may only enter the platform via redirects (shares, website embeds, other social media platforms, email recommendations, etc.).

As with most social media platforms, there are often many other 𝕏 features besides the timelines.

You know 𝕏 has other “features” such as “Explore”, “Today’s News”, “What’s happening (Trending)”, “Who to Follow”, “Relevant People”, “Notifications”, “Mentions”, “Chat”, “Grok”, “Lists”, “Communities”, “Creator Studio”, “Subscriptions”, 𝕏 Spaces, and “Premium” features. And what else am I missing?

But it’s the user who decides when, how, and which features to use for their personal interest and “benefits”.

And for the marketers, which ones to use to connect and engage with their target audiences.

Below, I will focus on how to take advantage of this new ranking algorithm from a business point of view (including creators and influencers) and especially for marketing managers who want to increase and optimise their 𝕏-marketing via regular posting (not via advertising).

But be aware that posting (and engaging) on 𝕏 should be part of the overall social media (content) marketing strategy and (free and paid) campaigns. Hence, not just restricted to 𝕏 alone, but should be considered as an integral part of all other social media and marketing “communications”.

𝕏 Marketing Goals and KPIs

It’s crucial to get a clear vision of what metrics deliver meaningful insights. Ask yourself the following questions to set a solid baseline for measuring your 𝕏 campaigns.

QuestionConsiderations
What is my primary (marketing) objective on 𝕏?To increase engagement, brand awareness, lead generation, or conversions?
Who are my ideal customers on 𝕏, and what is my target audience?Understand which metrics to track to understand the reach and effectiveness of your campaigns.
What actions do I want my audience to take?Follow, Click, Website visits, Share, Comment, Vote, Sign-up, etc.
How frequently should I review my progress?Set a timeframe to make timely adjustments based on performance data.

𝕏 Marketing KPIs (Key Performance Indicators) reflect whether your 𝕏 Posts deliver the expected results tied to your marketing goals. The KPIs monitor whether your (free) posts are garnering significant engagement, persuading users to take action, or need re-evaluation for optimization.

Main performance indicators for 𝕏 marketing focus on engagement, reach, and conversion, with top metrics including:

  • Impressions (views). Total number of times a tweet has been viewed.
  • Engagement rate. The percentage of people who interact with a tweet (likes, retweets, replies) relative to total impressions, indicating content resonance.
  • Amplification Rate:Β The number of retweets or reposts per tweet relative to your total followers.
  • Quote Tweets & Replies:Β Higher-value interactions that signify genuine conversation rather than passive liking.
  • Link clicks. Number of times users clicked on a URL in the tweet, indicating intent to learn more or visit a site.
  • Click-Through Rate (CTR): The ratio of link clicks to impressions, measuring the effectiveness of the tweet.
  • Conversion Rate:Β Percentage of users who take a specific action (e.g., signing up, purchasing) after clicking.
  • Profile clicks. Measures how many users are intrigued enough to view the full profile.
  • Follower growth. Net gain of followers, showing brand awareness and audience building.
  • Mentions. Measures brand awareness and organic buzz.
  • Average Response Time:Β How quickly your team replies to mentions or direct messages (DMs).

Note that other Phoenix Scorers are difficult to measure, such as dwell time, follow author score (directly attributed to specific post), and the “negative” scores (block, mute, report, not interested).

Differences between Free 𝕏 Posts and Ads

In comparison to advertising on 𝕏, you have less data and (KPI) analytics for regular (non-promote) posts. (The X Ads Manager dashboard has many built-in analytics to track key KPIs)

Also, in general, you tweet a regular post only once, while you can run as many ad campaigns on 𝕏 as you want with A/B-testing. And each “tweak” in the ad content (text, image, video, CTA, etc.) can be evaluated.

So, as each tweet is different, posted at a specific time and date, “competing” with thousands of other posts for the (highest) rankings to be included or not in someone’s timeline based on this 𝕏-algorithm, it’s often hard to find out why this specific tweet was performing well or poorly.

Yes, for a relatively poorly performing tweet, you’ll notice fewer impressions and/or less engagement by definition… but trying to find the underlying reason, it’s often “guessing” as there are no clear “quality” indicators.

You know, you can’t just ask all “viewers” why they didn’t engage or didn’t like the post.

Let alone that you have no clear insights into all “competing” posts and why the algorithm expects your Followers to be less responsive (based on unknown prior individual user behavior and “assigned” post characteristics).

Taking this into consideration, by knowing this new 𝕏-algorithm, let’s look at…

How to use this 𝕏-Algorithm knowledge for your 𝕏 Marketing?

As now we know the main drivers that determine whether your Posts will lead to impressions in users’ timelines, let’s look at best practices.

But first, let’s start with a short description of how many social media teams (and managers) were trying to optimise their presence on 𝕏 by taking advantage of the “old” Heavy Ranker algorithm.

Some Old-school methods (Bad practices)

  • Post regularly (flood the feed) when your audience is online.
  • Post similar content on all social media channels.
  • Find popular accounts or trending topics in your niche and leave short replies.
  • “Buy” (fake) Followers by rewarding them for following you (attracts the wrong group of “freebee seekers” only interested in rewards instead of the product/services).
  • Rewarding Likes and Post-engagement farming.
  • Pay for InfoFi or “bot” accounts that automatically engage (like, share, repost).
  • Include irrelevant keywords, hashtags, and mentions.

These often-used methods are outdated and less relevant, and now even ineffective and/or counterproductive.

Instead, focus on…

Best New Practices

Key insight: Content that sparks conversation and engagement (especially back-and-forth replies) dramatically outperforms content that just gets scrolled by and/or only gets passive likes.

For influencers, creators, and businesses, knowing these Phoenix scorers and likely weights (and the full X-algorithm concept) is essential for maximum reach and exposure.

Below are some general principles and tips based on this new 𝕏-algorithm.

Do’s

  • Maximize Positive Engagements and focus on the ones with the highest relative weight. The algorithm prioritizes conversation over broadcast – A post that generates a back-and-forth conversation is valued significantly higher than a post that simply gets viewed (and/or liked). Hence, reply to feedback. Ask questions, share opinions people want to react to, or make statements that invite discussion.
  • Hold Viewer Attention. Maximize Dwell time. If someone clicks your tweet/thread and stays for >2 minutes, you win. If they click and bounce in 3 seconds, you get penalized.
    Use long(er) text posts where viewers have to click or scroll to see all the content. Use line breaks to make content scannable. Grab viewers attentention and hook them into the content. Use Videos, Threads, 𝕏 Spaces (Live Podcasts), and publish Articles for longer dwell time.
  • Use Rich Media (Especially Video). Posts with images get roughly 2x the impressions of text-only posts. Native video (uploaded directly to 𝕏, not linked) gets 2-4x more reach. Add captions to videos.
  • Keep users on the 𝕏-platform. Avoid external links to other platforms or websites. Although the algorithm removed this “default” penalty and made it dynamic based on domain reputation, there are still penalties. For example…Substack/YouTube? Heavy penalty. News sites? Medium penalty. Links to X.com itself? Neutral.
  • Stay in your SimCluster (Niche). This filter calculates your “Vector Distance” from your niche. If you are a “Crypto Account” and you tweet about “Politics,” your distance score spikes. High distance = The algorithm assumes your followers don’t care.
  • Quality (professional) content above (low) Quantity content.
  • Jumping on Trends is no problem, but only if added value to the conversation.
  • Profile Authority is important. Use the Founders and Management Team accounts to start the initial posts (Reposts from the Company Account are no problem).
  • Upgrade your 𝕏-account to at least the Premium level (for verification mark, boost exposure, write Articles, and get better view stats).

Do nots

  • Do not flood the feed. Space out your Posts to avoid the Author Diversity Scorer penalty.
  • Don’t post spam or low-quality content. Don’t try to trick the system via post-engagement farming. Grok is actually reading all your posts and making adjustments (penalizing) for low quality. You can’t fool a keyword filter anymore. You must write something that the LLM AI respects.
  • Cross-posting identical content from other social media platforms. This is seen as self-promotion and will be downranked.
  • Stop reposting (or clipping) of externally (YouTube or TikTok) videos. Be a creator with new native videos posted exclusively on 𝕏.
  • Avoid Negative Feedback (blocks, muted, reports, not interested).
  • Avoid Controversial Content. Steer clear of safety filters.

Be in mind that each 𝕏-Profile is unique and based on (recent) activities (Posts and Engagement), but not set in stone. By adapting and changing your behavior, by definition, your 𝕏-Profile will change as it will be noticed by Grok.

For marketeers these are the most important steps:

  1. Define your target audience who are (potentially) interested in your products/services and Content.
  2. Develop the Ultimate Profile (Company or Personal) as you want Grok to summarize your Profile. See smart tip below.
  3. Publish the content in the form and format that your target audience prefers and is likely to engage with.
  4. Strive for as many Followers as possible, but accept that not all your Posts will end up in your followers’ timelines. Hence, also look at how to use the other platform features to connect with your audience (Chats, Communities, Subscriptions). For example, (re)direct 𝕏-users to your Profile Page, as that’s the only place where they can see all your Posts.

Wondering where to start?

A simple, practical tip to start is to categorize (and group) your recent posts based on total impressions per post.

For example, use 5 categories (Very Poor, Poor, Adequate, Good, Excellent) and try to find what makes the differences by looking at:

  • Type and length (Standard, Long-Form (Article), Threads)
  • Form (Text, Image, Video, Live Video, Poll, etc.)
  • Replies/Quotes/Reposts/DM
  • Content Categories (Educational/Informational, Entertaining/Memes, Personal/Status Updates, Promotional, Branding)
  • Usages of Keywords, Mentions, and Hashtags

Learn from your mistakes and bad performers, and focus on the elements that work for your audience. Set impressions and engagement targets. And make it a habit to analyze your performance and raise the bar.

But most and for all, use 𝕏 strategically.

Originally, 𝕏 is unique for its real-time, public-forum nature, focusing on immediate news, trends, and, often, unfiltered/raw conversation, setting it apart from more curated platforms like Instagram or LinkedIn.

The platform excels at showing “what’s happening now” through live hashtags, trends, and topical threads.

Since its new ownership, 𝕏 has expanded to include long(er)-form posts, AI and personalisation, and a pivot toward becoming an “everything app”, all to stimulate users to use the platform as much and long as possible (to increase ad and subscription revenues).

This new For You Feed 𝕏-algorithm is just one clear sign of the evolving functionality.

Note that starting January 2026, 𝕏 Premium Members can now post Articles, while before this was only a Premium+ privilege.

So, marketers should adapt and take advantage of this new direction.

Smart additional tips using AI

Take what you learn above and ask Grok to analyse your 𝕏-profile.

Whatever Grok says, ask it to make a 30-day plan to optimize your profile with a growth plan to increase exposure.

Boom! You will have a 30-day game plan.

If you want a more detailed look, then I’d highly suggest having your AI agent thoroughly review the 𝕏-algorithm and ask any questions about different parts of it.

Resources

Must follow 𝕏 Accounts:

X Engineering: https://x.com/XEng

xAI: https://x.com/xai

Nikita Bier, Head of Product 𝕏: https://x.com/nikitabier

TL;DR Grab your summary of this article via ChatGPT Perplexity Grok Google AI
Malcare WordPress Security