Also, I've found it's best to never trust it's response to a "why" question (formatted this way because a lot of people will will ask AI to speak for them, so you can still get a"why" response without ever having personally prompted for it.)

I give it (low effort) bullet points, general direction, plain (and usually too honest/direct and sometimes even insulting) message I would’ve sent, references and other stuff and things come always out better than what I could’ve ever produced.

For me, the alternative would be to not write at all or spend a disproportionate time on getting some motivation to even write a single paragraph.

I rewrite it from there, and it's completely different by the time I'm done because it's version is terrible enough that it annoys me into correcting it.

You can wrangle it into something more interesting with shaping and filtering passes, and you can also ask for styles of dead people. (It gets annoyed if you ask for the living.)

That can take you surprisingly far. But most people accept the first thing they get, which is why you see the same style everywhere.

It actually feels wrong to mention them by name now (because they are actual humans) but the "They're wrong. Here's why." school of writing was strong in the early 2000s and hasn't really gone away.

It's now just how some people talk.

I recently found a programming task it really sucks at: trying to make a texture from normal house pictures and apply that to a 3D house model.

Fucking Jack Dorsey.

I tend to run the content through something like Luna to deslopify now.

As an example of before/after: "Perform an inspection of the filter" vs. "Inspect the filter