One flaw of the LLMs I've used: they will never give you harsh criticism. While it would be nice to think all my writing is just that good, I know there are no circumstances where someone will ask for feedback and it will say “throw the whole thing out and start again.”
@molly0xfff I wonder if that contributes to the cold-reading effect, like Barnum statements. If the statement is generic, then it’s more likely to hit (and get reinforced) but less likely to be actually valuable, because it took no chances. And if it did take a chance, the hit rate might plummet because it doesn’t actually understand your writing or what makes it better.