Why replies beat posts on X: what the open-source algorithm weights
X has published its ranking code twice. The 2023 release weighted a reply at 13.5 against 0.5 for a like, and a reply the author answered at 75. The 2026 code keeps the same shape. Here is what the numbers say and what a small account should do about it.
If you have 80 followers and you post a launch announcement, almost nobody sees it. If you write a useful reply under a post from someone with 80,000 followers, hundreds of people see it, and some of them click your profile. Every founder who has tried both knows this from experience. The unusual thing about X is that you can read the reason in the source code.
X has open-sourced its "For You" ranking twice: once in 2023 as twitter/the-algorithm, and again in 2026 as xai-org/x-algorithm, which the company now updates on GitHub. Both releases include the weights the ranker applies to different kinds of engagement. This article goes through what they say, what they do not say, and how a small account should post.
What did X's 2023 algorithm weight a reply at?
X's 2023 heavy ranker weighted a predicted reply at 13.5 against 0.5 for a predicted like, and a reply the original author then engaged with at 75. The heavy ranker is the model that scores candidate posts for the For You timeline, and its README listed the full set of weights as of April 2023:
| Predicted action | Weight |
|---|---|
| Like (favorite) | 0.5 |
| Retweet | 1.0 |
| Good click (open and stay) | 11.0 |
| Good profile click | 12.0 |
| Reply | 13.5 |
| Reply that the author then engages with | 75.0 |
| Negative feedback (not interested, etc.) | -74.0 |
| Report | -369.0 |
Source: the projects/home/recap README in twitter/the-algorithm-ml on GitHub. Read across the table: a reply was worth 27 likes, and a reply that the original author replied to or liked was worth 150 likes. This is where the widely quoted "replies are 27x a like" line comes from. It was true for that model, at that date.
What does X's 2026 algorithm weight a reply at?
X's 2026 code weights a predicted reply at 5.0 against 0.5 for a predicted like, so a reply is worth ten likes rather than twenty-seven. The 2026 system is a different one: ranking is done by a transformer model called Phoenix, and the weights live in a config file, home-mixer/params/param.rs, rather than in a README. The defaults in that file as of September 2026:
| Predicted action | Weight |
|---|---|
| Like (favorite) | 0.5 |
| Retweet | 1.0 |
| Share | 2.0 |
| Follow the author | 4.0 |
| Reply | 5.0 |
| Quote | 5.0 |
| Share via DM | 5.0 |
| Share via copy link | 20.0 |
| Reply, when the viewer and author follow each other | 5.0 + 15.0 boost |
| Block the author | -31.2 |
| Not interested | -43.2 |
| Mute the author | -58.8 |
| Report | -234.0 |
The absolute numbers changed between 2023 and 2026. The shape did not. A predicted follow is worth eight likes. The single strongest positive signal is now someone copying the link to your post, which is what people do when they send it to a group chat. And the negative signals are still enormous compared to the positives, so a post that annoys people loses more than a post that pleases them gains.
What do X's engagement weights not mean?
The weights multiply the model's predicted probability that a given viewer takes an action, not raw counts of that action. The 2026 file has a comment block above the weights that calls out "one report cancels 468 likes" as exactly the wrong reading. A report is weighted heavily because reports are more than a thousand times rarer than likes, and the weight is what lets a rare prediction affect the score at all.
Two more things X's code makes explicit:
- Replies from accounts the viewer does not follow are filtered out of For You. The filter is named
OONRetweetReplyFilter. A reply under a big account's post does not get injected into strangers' timelines as its own item. It gets seen because people open the big post and read the conversation, and because the author and their followers, who may follow you, do see it. - Out-of-network posts are discounted. A post from someone the viewer does not follow is multiplied by a factor below one (0.75 in the current defaults) before it competes with posts from accounts they follow.
So the honest version of "replies beat posts" is this: the ranker rewards posts that people reply to far more than posts people like, and the conversation under a post with reach is the only place a small account gets read by strangers at all. Both point the same way.
How should a small account use X's ranking weights?
A small account should spend most of its X time replying in other people's threads, write replies the author will answer, shape its own posts as questions, keep a profile worth following, and avoid anything that earns a mute or a block. Six habits follow from the weights above.
1. Spend most of your X time in other people's threads
Pick ten to twenty accounts your customers follow: not celebrities, but people in your niche with real conversations under their posts. Turn on notifications for them. When they post, reply within the first fifteen minutes with something that adds information: a number, a counter-example, a specific tool, a short story. Not "great post" and not your link. Early, substantive replies sit at the top of the conversation as it grows.
2. Write replies the author will answer
In the 2023 model, a reply the author engaged with was the highest-weighted action in the table. The 2026 code does not expose an equivalent parameter, but the author's engagement still puts a reply at the top of the conversation view, where everyone who opens the post reads it. The reliable way to get an author to answer: ask a specific question they know the answer to, or disagree politely with a reason. Flattery gets a like at best.
3. Make your own posts questions
A predicted reply is worth ten predicted likes. Posts that end with a real question, that present a choice, or that state an opinion someone will want to correct, get replies. Announcements get likes. Reply to every reply you get, quickly; each answered reply keeps the thread alive in the ranker and the conversation view.
4. Be worth following
Follow-the-author is weighted 4.0, eight times a like, and the profile is where a reply turns into a user. Your bio should say what you build and for whom in one line, your pinned post should be a demo, and your recent posts should make sense to someone arriving from a reply. A profile with a clear pinned post converts reply readers; a profile full of retweets does not.
5. Do not fish for the negatives
Not interested, mute and block are weighted between 60 and 120 times a like. Tagging people who did not ask, replying with a link and nothing else, and posting the same reply under twenty posts generate exactly those signals, and they attach to your account, not only the post. X's code also says directly navigating to a post has no ranking effect, so link drops in group chats do not help either.
6. Post replies yourself
Automated replies are the fastest way to collect mutes and reports, and X's spam enforcement runs separately from the ranker. AutoTraction, on a waitlist for an October 2026 launch, is built around this: it finds the threads and drafts the replies, and you paste them from your own account, at human pace. One reply a day is all the four-minute-a-day routine asks for.
How can you check X's current ranking weights yourself?
Open home-mixer/params/param.rs in the public repository at github.com/xai-org/x-algorithm and search for _weight. X has said it will push updates roughly every four weeks, so the defaults above may have moved by the time you read this. The direction has held for three years: conversation outranks applause, and a small account gets its reach from the conversations it joins, not the posts it makes.