X releases its For You algorithm's and core ranking engine's source code on GitHub and adds tools that let users see if X's ranking systems “shadowbanned” them
TechCrunchSarah Perez
Context & Ripple Effects
X’s latest disclosure extends a longer, incomplete transparency record: Twitter previously published part of its For You recommendation code while excluding ad recommendations, and X later released its core recommendation system for For You.
The release follows a recent ranking tweak that boosted posts to mutual followers and arrives alongside user-facing checks for ranking-based visibility limits. It gives users and outside observers more material to connect stated ranking changes with visible distribution outcomes.
First-order effects
X users can check whether its ranking systems flagged them for reduced visibility, while developers and researchers can inspect the published For You and core-ranking code on GitHub.
X’s ranking-team decisions, including visibility changes intended to reshape replies, become more open to technical scrutiny against the code it has released.
Second-order effects
Creators and moderators gain a clearer basis to challenge or explain reach changes, raising the reputational cost for X when product behavior appears inconsistent with its published ranking logic.
If X continues pairing code releases with user-level ranking diagnostics, recommendation transparency may shift from one-off source dumps toward ongoing, user-auditable distribution governance.
The combination of open ranking code and restricted content access points to a platform model in which implementation transparency and control over data reuse are managed independently.
The trend: Social platforms are facing pressure to make algorithmic distribution more legible to users while retaining control over how their underlying data is reused.
Open-sourcing the For You timeline — Today, we are taking another major step in our ongoing efforts to increase transparency. We're open-sourcing the code that affects a post's visibility in the For You timeline, and releasing a new tool that shows people labels applied to the…
You know how everyone started seeing their friends in the timeline a few weeks ago? With our new open-source code base, you'd also have been able to see what changed under the hood — here's the story: https://github.com/...
I read the X algorithm source code so you don't have to. Its primary recommendation is that you become the sort of person people discuss in private group chats.
“Am I shadowbanned?” “Is X fair?” “Why am I seeing this post?” We want the public to be able to answer these themselves. Today we're giving an unprecedented level of transparency into the X algorithm so people can audit, critique and even help improve it. Enjoy & send feedback.
This part in the middle pretty telling: “This is important for advertisers and brands” Sounds like X is struggling to get advertisers at the rate they want to be a money maker. I dont see how this would help them tho. Advertisers want ROI on ad spend comparable to Meta/Google
X continues to lead in building trust through transparency. Public discourse needs accountable systems that support free expression and informed debate. That's why we've open-sourced the code that affects a post's visibility in the For You timeline and built a new tool that
This is a massive step for platform transparency. X is open-sourcing the code that determines visibility in the For You feed, while giving users direct access to the labels affecting their accounts and posts. You'll finally be able to see whether your reach is being limited, [ima…
SITUATION EXPLAINED: X just open-sourced the For You algorithm. • A report is -234.0, wipes out 468 likes • A copy-link share is weighted +20.0 against a like at +0.5, so one is worth 40 likes • Share via DM is only +5.0, the same as a reply or a quote • Not Interested is [video]
Today X is taking a major step towards unprecedented transparency. By expanding the open-source For You ranking code and launching a new tool that clearly shows visibility-limiting labels, X is giving people a clear view into how posts are ranked and filtered. This is important…
X open-sourced its feed algorithm — The xai-org/x-algorithm repo shows how the “For You” feed is built end-to-end: — • Candidate generation (in-network + discovery) …
They published the algorithm about two months ago it seems: — github.com/xai-org/x-al... How useful this is for interrogating bias without firehose access to the platform is another question. Whether it allows Musk to manually promote posts is another entirely.