For me I take the view that it’s similar to asking a human for feedback. I sift it, ditch what I’m not interested in or don’t agree with, do more research on what might be interesting, then decide what I want to incorporate and rewrite from there.

On grammar, typos, and the like I tend to take LLM feedback as read in most cases. Beyond this I think it’s a mistake not to do the legwork yourself, just as you’d have to if you’ve ever worked with a human editor.

But the LLM is helpful because it reduces the cycle time for feedback, which helps maintain momentum - helps me anyway.