One LLM prompt I've been using for overcoming author blindness is just "how would you analyze this story/essay" and then asking follow-up questions about anything I'm curious about. Not asking it for feedback, but just seeing what it thinks the story/essay is about and what the plot/argument is. If there's anything it seems to misunderstand, I consider clarifying.
Though one potential problem is that some LLMs may be _too_ good at understanding all your references and things that you are hinting at relative to most readers. I wrote one story that I asked Claude Opus to analyze and it spit out a sophisticated analysis that basically understood everything that I was trying to do with the worldbuilding, and correctly drew connections to all the theoretical frameworks etc. that I was alluding to and drawing from.
Then I sent that same story to a professionally published author who I respect quite a bit, and got back a list of notes that indicated that it wasn't clear at all to him what the story was trying to do and he got confused several times. And reading those notes I could see that oh yeah, things X, Y and Z actually _are_ confusing, Opus just managed to figure out my intent despite them. Or it didn't focus on them in the first place: its analysis focused on the worldbuilding and the ideas the setting was communicating, while the editor said things like "you haven't described this apartment at all, I have no idea of what it looks like" which an LLM didn't comment on since it wasn't trying to visualize the apartment at all.
So just because the LLM understands the thing isn't a guarantee that a human would. One possible fix is to give the story to a dumber/smaller model to analyze. Another is to give the story to the model one chapter a time rather than in one piece. A model that's fed a full story will reason about it as a whole, so if e.g. something becomes clear in chapter 4 that was confusing in chapter 1, the model will just comment based on the fuller understanding. A model that has only been given chapter 1 will only work based on the information it has.
I think that this would be an issue even with the prompt described in your post, that asks it to comment on something line by line. If you've given it a full story, its reply might _start_ from the first line of your story. But it has still read your full story before it starts composing a reply, so information from the end of the story will still influence its interpretation of the beginning of it.
The episodic nature of the writing I’m used to working with shows up here, I think. I mostly trust LLMs to give sensible line level feedback up to maybe 2000 words maximum. In the scope of this guide, I’m suggesting LLMs be used mostly like a table saw or some other very defined piece of machinery. Maybe I should just embrace our new machine overlords and tell people to have discussions about stories with their LLMs, but I’m not comfortable doing that knowing the damage a data regurgitator could do to a story if the author doesn’t have the knowledge or confidence to push back.
Yeah, that's a very valid concern. I'm confident enough in my writing that I can just take part of the LLM feedback and make use of it and go "no that's dumb" for all the rest, but a lot of people aren't.
> As the first workshop started that night, I turned to the ostensible authors and told them I knew that AI wrote their stories. [...] For a few moments, all was quiet except the classroom’s ticking radiators. Then, a teary-eyed confession: one of the ostensible authors said she only used AI because she was scared of looking stupid, of being criticized for bad writing. She said she loved writing stories and hated having used AI. But she couldn’t stop herself, recounting a sequence similar to an addict’s descent: at first she fed her story into AI for a grammar check, it suggested line edits and she accepted, then it asked if she wanted structural edits, then it offered to rewrite the entire piece.
On the other hand, discussing your story with the LLM can provide a weird motivation to write more. It's delightful to give something to an LLM and be like "how would you analyze these characters in terms of Kegan's theory of adult development" or "how would you analyze this story's society through a systems thinking frame" or whatever you happen to be interested in and seeing what it spits out. (Claude Opus is particularly good with this kind of thing; worth trying both 4.6 and 4.7 since they have somewhat different strengths, 4.7 especially feels a bit neurotic about engaging with darker stuff.)
"What would you infer or speculate about the author" is also a fun if somewhat unnerving prompt to try at times; you may not realize how much your writing reveals about you until you try it on a few different pieces.
Man the quoted part reads so dystopian. Phew. Nice article, thanks for linking it.
It so happens that this morning I actually tried to make Claude write a profile of “this one author” (partly inspired by your earlier post here on Substack). I gave it examples from four of my novels and the profile it drew felt pretty close to like it could have given me my home address if I had asked for it. Eery stuff.
One LLM prompt I've been using for overcoming author blindness is just "how would you analyze this story/essay" and then asking follow-up questions about anything I'm curious about. Not asking it for feedback, but just seeing what it thinks the story/essay is about and what the plot/argument is. If there's anything it seems to misunderstand, I consider clarifying.
Though one potential problem is that some LLMs may be _too_ good at understanding all your references and things that you are hinting at relative to most readers. I wrote one story that I asked Claude Opus to analyze and it spit out a sophisticated analysis that basically understood everything that I was trying to do with the worldbuilding, and correctly drew connections to all the theoretical frameworks etc. that I was alluding to and drawing from.
Then I sent that same story to a professionally published author who I respect quite a bit, and got back a list of notes that indicated that it wasn't clear at all to him what the story was trying to do and he got confused several times. And reading those notes I could see that oh yeah, things X, Y and Z actually _are_ confusing, Opus just managed to figure out my intent despite them. Or it didn't focus on them in the first place: its analysis focused on the worldbuilding and the ideas the setting was communicating, while the editor said things like "you haven't described this apartment at all, I have no idea of what it looks like" which an LLM didn't comment on since it wasn't trying to visualize the apartment at all.
So just because the LLM understands the thing isn't a guarantee that a human would. One possible fix is to give the story to a dumber/smaller model to analyze. Another is to give the story to the model one chapter a time rather than in one piece. A model that's fed a full story will reason about it as a whole, so if e.g. something becomes clear in chapter 4 that was confusing in chapter 1, the model will just comment based on the fuller understanding. A model that has only been given chapter 1 will only work based on the information it has.
I think that this would be an issue even with the prompt described in your post, that asks it to comment on something line by line. If you've given it a full story, its reply might _start_ from the first line of your story. But it has still read your full story before it starts composing a reply, so information from the end of the story will still influence its interpretation of the beginning of it.
That is a fun and interesting experience to read.
The episodic nature of the writing I’m used to working with shows up here, I think. I mostly trust LLMs to give sensible line level feedback up to maybe 2000 words maximum. In the scope of this guide, I’m suggesting LLMs be used mostly like a table saw or some other very defined piece of machinery. Maybe I should just embrace our new machine overlords and tell people to have discussions about stories with their LLMs, but I’m not comfortable doing that knowing the damage a data regurgitator could do to a story if the author doesn’t have the knowledge or confidence to push back.
Yeah, that's a very valid concern. I'm confident enough in my writing that I can just take part of the LLM feedback and make use of it and go "no that's dumb" for all the rest, but a lot of people aren't.
Related: https://www.theguardian.com/us-news/ng-interactive/2026/may/10/fiction-writing-professor-ai
> As the first workshop started that night, I turned to the ostensible authors and told them I knew that AI wrote their stories. [...] For a few moments, all was quiet except the classroom’s ticking radiators. Then, a teary-eyed confession: one of the ostensible authors said she only used AI because she was scared of looking stupid, of being criticized for bad writing. She said she loved writing stories and hated having used AI. But she couldn’t stop herself, recounting a sequence similar to an addict’s descent: at first she fed her story into AI for a grammar check, it suggested line edits and she accepted, then it asked if she wanted structural edits, then it offered to rewrite the entire piece.
On the other hand, discussing your story with the LLM can provide a weird motivation to write more. It's delightful to give something to an LLM and be like "how would you analyze these characters in terms of Kegan's theory of adult development" or "how would you analyze this story's society through a systems thinking frame" or whatever you happen to be interested in and seeing what it spits out. (Claude Opus is particularly good with this kind of thing; worth trying both 4.6 and 4.7 since they have somewhat different strengths, 4.7 especially feels a bit neurotic about engaging with darker stuff.)
"What would you infer or speculate about the author" is also a fun if somewhat unnerving prompt to try at times; you may not realize how much your writing reveals about you until you try it on a few different pieces.
Man the quoted part reads so dystopian. Phew. Nice article, thanks for linking it.
It so happens that this morning I actually tried to make Claude write a profile of “this one author” (partly inspired by your earlier post here on Substack). I gave it examples from four of my novels and the profile it drew felt pretty close to like it could have given me my home address if I had asked for it. Eery stuff.