Discussion about this post

User's avatar
John E Simpson's avatar

I wasn't crazy about the Woodrell passage as a whole (although, yeah, "flourish upon flourish of small popping sounds" is pretty great) -- but then as you suggest, I bet if I'd read the preceding 25% of the book I might feel differently. To my taste, the passage sounds like the product of a writer who has learned too well the lesson of using vivid verbs. (I wonder if Ron Charles has read 'Winter's Bone'?)

One of the things I'm finding interesting about using Chat (Claude, in my case) is that while it can analyze prose brilliantly, it can't actively use its analytic skills to vet its own writing in the process of writing it. Most (?) human writers keep the analytic machine going in the background while they're writing, so when they write, say, "I was there," something immediately clicks in their head which tells them the sentence just doesn't say enough. I once asked Claude if that split in function (writing vs. editing) is actual or imagined and it said yes, that's how it works.

Since then I've submitted some of Claude's longer responses to Claude itself to see if it picks up on the same things that sometimes bother me about it, stylistically. (Claude's "incognito" mode works well for this, because it then won't know it's analyzing its own product.) But I'd really like to come up with a prompt sequence which says something like, "Generate [a full-length response to Prompt X], but don't share the response with me right away; save it, analyze it [as, say, Tom Shroder asked Chat to analyze various writing samples], and FIX it according to the results of that analysis; and, finally, present the fixed response to me as if it were the initial response to [Prompt X]." No idea if that's possible though.

Maggie Fox's avatar

"Are they intoxicated by their own language?"

I so wish I could have wielded that one when I was a junior editor trying to corral far older and wilier correspondents.

9 more comments...

No posts

Ready for more?