[zephen]

I get that.

But, as discussed in some other threads, the leverage provided by the LLM allows the miscreant to inundate you with slop by only pressing a few buttons.

And rejection is work. So they can produce more slop, requiring more rejections, faster than you can read the slop.

This is what's new. You reject it, they feed your rejection back into the LLM, and hand you something 5 minutes later with so many formatting changes that diff is unhelpful, and enough subtle substantive changes embedded in it that if you don't read the entire thing, you might have missed something important.

[embedding-shape]

Yeah, that's not how it works, in my experience. They hand me something, I notice it's likely written by LLM, ask them. They say "Yeah, some quick things blah blah" and then I ask "Did you check all the details themselves?" and they say "Yeah, most of them" and then I answer "Ok, check all the details, then I'll go through it" and then later they come back and things look a lot better.

If you're ending up doing this back and forth with someone more than once, just outright refuse to work with someone so unprofessional who doesn't even validate their own work. It wouldn't fly in most workplaces I've worked in.