Following an account feels like a simple contract:
I chose this person, so show me what they post.
Ranked feeds complicate that expectation.
A platform may use the follow as one signal among many rather than as a command to display every post. The feed has limited space, the user may follow hundreds or thousands of accounts, and recommendation systems may also insert material from outside that network.
X provides a very clear current example. Its documentation says the default For You timeline contains posts from accounts and Topics a user follows, plus recommended posts selected from other signals. Its separate Following timeline shows only posts from followed accounts in reverse chronological order. See About your For You timeline and X’s description of For You recommendations.
The two views answer different questions.
Following creates eligibility, not guaranteed exposure
A ranked feed may have thousands of candidate posts available between visits.
The system chooses a subset. Posts can compete with recommendations, reposts, promoted material, newer posts, and other followed accounts. Even if the platform has not blocked or suppressed a creator, ordinary ranking can mean that a specific post never appears during the user’s session.
That can feel like disappearance from the user’s side.
The creator still exists. The follow still exists. The post still exists.
The ranked surface simply spent its limited attention elsewhere.
Fair measurement needs both sides of the feed
It is easy to say, “I follow this account and never see it anymore,” but one person’s memory is not a reliable audit.
A useful comparison would record posts published by a defined set of followed accounts, then track which ones actually appear in the default ranked feed over a fixed period. Compare that with a chronological following-only feed where available. Control for how often the user opens the service, how many accounts they follow, post frequency, muted settings, and whether the posts remain online.
That separates ranking omission from deletion, moderation, inactivity, or simple timing.
The result may still show uneven visibility. But now the claim has a measurable meaning.
This matters for Algorithmic Reality because a follow graph can suggest that users built their own information environment while the default feed quietly applies another selection layer on top.
You chose the accounts.
The platform may still choose which of their posts become your day.