[Bjartr]

Assuming we're starting with a blank slate, and a heteronormative male user that would happen to enjoy consuming that content on TikTok:

In the initial set of recommendations based only on overall popularity, there might be a video that's popular that incidentally contains a pretty woman. If the user skips most videos after barely a few seconds, but watches that one fully 3 times through, then the recommendation engine probably looks at users it does know more about that exhibit similar behavior and have higher engagement. It will then recommend videos that those users would probably watch a lot. Now the recommendations are shifted in the direction from "generally popular" to "contains pretty women". You repeat this enough times and the user ends up navigating the space of recommendations until they're maximally engaged (in theory). That means they might end up at softcore porn. Goodness knows that porn is popular if nothing else.

The recommendation engine doesn't even have to know anything about the content of the video. Just know what already high-engagement users that watched that video a lot also watched a lot.

That's at it's most basic really, I'm sure there's additional cleverness on top in practice.

[oogali]

So, in the old days, if you fall asleep in front of the TV you might have some weird infomercial-fueled dreams. But they’re purged when you wake up.

Now, if you fall asleep in front of your phone screen, it takes days or weeks to shake out that mistake?

[Bjartr]

Maybe, or maybe the system is good enough to low weight or completely discount hours long periods of non interaction.