Lesson 62 · 2 min
Why your feed shows what it shows
Recommendation algorithms watch what you click, watch and skip, then show you more of whatever kept you there.
Every video app, shop and news feed has to choose a handful of items from millions. A recommendation algorithm makes that choice for you, in a fraction of a second.
It learns from signals: what you watched to the end, what you skipped, liked, shared, searched for or paused on. It also learns from people whose habits look like yours. If they enjoyed something, you probably will too.
This creates a loop. Watch two cooking clips and the feed sends more, so you watch more, so it sends more. The loop is good at finding what holds attention, which is not always what you would choose on a calm day.
You can steer it. Use "not interested", search for what you actually want, unfollow accounts that drain you, and clear your watch history if the feed has gone somewhere you dislike.
Do it now
Reshape your feed in ten minutes
- 1. Open the app you scroll most.
- 2. Mark five posts you do not want to see as "not interested".
- 3. Search for and watch two things you would like more of, such as a skill or hobby.
- 4. Check your feed again tomorrow and see what changed.
Quick check
Keep going
Next →AI that sees your photosWords from this lesson
- Algorithm
- A set of step-by-step instructions a computer follows to solve a problem or make a decision.
- Machine learning
- Teaching computers by showing them many examples so they find the patterns themselves, instead of being given every rule.