[md5person]

I think it's because the generated text will generally follow a reasonable "structure", it's "framed" relatively well and you (as a person) will recognize those patterns quickly. There's plenty of "glue" used throughout the text. Those are all patterns which we pick up very quickly, and we're used to seeing them in "real text".

Exampels from the comment above include using things like: "A year ago", "made headlines", "Now, it's the {event}, and {name} is at it again. But this time, ...", "{name} was not impressed", "You know, I feel like, I feel like you could have ...", "I don't know if... but...".

Those are all very common in those "online celebrity magazine" type texts...

It's only when you actually read into the stuff that's in-between, you'll come to see it's pretty much a load of nonsense. But that takes a bit more time and slower reading.