X open-sources "recommendation algorithm" code and launches transparency tool, users can view account and post downranking labels
TechFlow reports that on August 15, the X platform announced further improvements to algorithm transparency, officially open-sourcing code related to the exposure ranking of posts in the "For You" recommendation timeline, and launching new transparency tools that allow users to check whether their accounts or posts have been tagged with labels that may limit visibility.
X stated that this move aims to enable users to judge for themselves whether the platform limits their content distribution, whether the recommendation system is fair, and why they see specific content. The two features released this time are referred to by X as "complementary pieces of the puzzle": the open-source code displays the generation mechanism of the "For You" timeline, including content labels affecting post exposure and their functions; while the transparency tool allows users to check whether their own accounts or posts have restriction labels affecting visibility.
It is reported that the feature is still in the pilot phase and is open only to randomly selected eligible accounts. The initial test subjects are users who have been registered for more than one year and have published more than 10 posts in the past month. X plans to gradually expand coverage based on user feedback. Third-party recommendation system experts have currently been invited to review and test this code release in advance to ensure information disclosure is clearer and more practical. The company stated that in the future, as the recommendation algorithm continues to evolve, relevant transparency mechanisms will be updated regularly.





