joeriddles on using LLMs as copyeditors, not ghostwriters
A blogger argues LLMs should critique your writing after you've finished, never contribute phrases themselves.
What to know
- joeriddles argues LLMs should only critique finished writing as copyeditors—never generate phrases or sentences that end up in the final piece.
- The core risk: readers detect artificial language, and LLM praise can reinforce flawed first drafts instead of prompting real revision.
- Hacker News commenters split on whether LLM assistance degrades writing quality or whether content value depends on ideas, not effort; some defend narrow uses like factual verification.
- A persistent tension: LLMs are useful for catching technical errors and structural problems, but their stylistic suggestions tend toward genericness that erodes authenticity.
The dispute Whether LLM use in writing is categorically harmful to prose quality and reader trust, or whether its impact depends entirely on how narrowly and skeptically writers deploy it. · positions read across 66 posts and comments
LLM-assisted writing fundamentally damages authentic communication and should be avoided for human-facing content.
-
“The best advice for writing for other humans is: don't use LLMs. If you're writing for a human mind to ingest and extract meaning from, then LLMs are poison.”
Eddy_Viscosity2 · Hacker News ↗
LLMs have legitimate, narrow uses—fact-checking, spotting structural problems, flagging repetition—if applied with discipline after drafting.
-
“for a technical blogger 'please check this post for factual accuracy' is a good way to not look like an idiot. Often it complains about hyperbole, which I tend to ignore since there's no point blogging unless you have some firm opinions.”
thombles · Hacker News ↗
The value of writing lies in conveying ideas, not in writing effort itself; stylistic perfection matters less than substance.
-
“Because the value of writing are not the words on a piece of paper but the idea they convey. Politicians speech are not worth listening too because they have a copywriter polish them?”
siscia · Hacker News ↗
joeriddles Writer and blogger
How it unfolded 3 developments, newest first · click a bar or a number to jump articlespostscomments
-
3
Commenters debate practical limits of LLM feedback for writing
Multiple voices push back on the usefulness of LLM critiques themselves. One commenter notes LLMs have poor taste in writing; another advocates using them only for factual accuracy checks. A third refines the approach: use LLMs only after multiple drafts to flag specific problems like word repetition.
“LLMs have absolutely terrible taste when it comes to writing. I don't find their feedback useful at all, beyond trivial spelling/grammar mistakes.”
— Retr0id -
J
"How To Write With An LLM" https:// sockpuppet.org/blog/2026/09/17 /how-to-write-with-an-llm/ A problem I see is that of course this way of writing is still work and takes time, care, and attention -- exactly what most people using an LLM here are seeking to avoid. Those who _do_ put in this effort could likely do the same editing job without the…
2 more of the top 3 · 52 posts in this stretch
-
A workflow I've recently discovered for myself, that may be useful to anyone who speaks at least two languages: Ask the LLM to write a first draft in a language that isn't the one the piece should ultimately be in. Then use the LLM's first draft as a blueprint, to write a first draft yourself in the intended target language. That way, you won't be…
-
V
A funny piece of writing… How to write with an LLM: https:// sockpuppet.org/blog/2026/09/17 /how-to-write-with-an-llm/
-
-
2
Hacker News discussion surfaces disagreement on AI's role in writing
Comments reveal two competing camps: some argue LLMs should be avoided entirely for human-facing writing, while others defend their use for fact-checking and structural feedback. A dominant concern emerges about authenticity and reader fatigue from suspecting AI involvement.
“I fear in the future people will read even less because of how often people cheap out and use AI to write.”
— S-E-P -
I think style is overrated. Yeah if you write commercially, you are a journalist or a copywriter, sure, you need to write in certain style. There’s rules to this shit. I think it was Hemingway who said that. Then again, the good ones break the rules.Today even if you don’t use LLM’s following certain formal style you end up sounding like ad copy…
2 more of the top 3 · 8 posts in this stretch
-
> If you can't spend the time to write it, why should anyone read it?This isn’t your thought; you are merely regurgitating a sentence we have all heard many times before, practically word for word.Presumably you think there is value in posting yet another copy of that other person’s thoughts in this discussion, despite having spent no time or…
-
> If you can't spend the time to write it, why should anyone read it?Because the value of writing are not the words on a piece of paper but the idea they convey.Politicians speech are not worth listening too because they have a copywriter polish them?Teacher assistant homeworks are not worth to do, because they are made by a TA and not by the…
-
-
1
joeriddles publishes LLM writing guide on Sockpuppet blog
joeriddles posts an essay outlining two rules for using LLMs in writing: write your piece first, then feed it to a model to find flaws. The author argues readers detect LLM-generated phrases at parts-per-trillion sensitivity and advocates treating LLMs as copyeditors, not ghostwriters.
“you need to use them like a copyeditor rather than a ghostwriter. So, step one of my method: write your piece. Then, step two: feed it to a good model to find flaws.”
— joeriddles -
2 outlets How to Write with an LLM
first by HN Best, 9d ago · also HN Frontpage
-
Excessive generative AI output devalues all communication media unfortunately. As a greater and greater portion of text, imagery, audio, and video come to be synthetic, I don't see why anybody would be motivated to do deep reading, or listening, or analysis of said media. It's frightening to think what that might do to our civilization, almost…
2 more of the top 3 · 6 posts in this stretch
-
H
How to Write with an LLM L: https:// sockpuppet.org/blog/2026/09/17 /how-to-write-with-an-llm/ C: https:// news.ycombinator.com/item?id=4 9747070 posted on 2026.09.17 at 17:48:38 (c=0, p=6)
-
Even if you don't want style advice from an LLM (I generally don't, not for blogging), for a technical blogger "please check this post for factual accuracy" is a good way to not look like an idiot. Often it complains about hyperbole, which I tend to ignore since there's no point blogging unless you have some firm opinions, but on at least one…
-
What people are saying 15 voices from 1 site · best of 66 · verbatim
- Can readers actually distinguish LLM-influenced writing reliably, or is the detection claim overstated?
- What concrete workflow prevents LLM suggestions from influencing a writer's voice without requiring complete avoidance?
- Sep 20
-
Thank you for writing this.This is gold> Rule Number One: You may not use a single word an LLM suggests to you.Over the last week-ish I turned around 2 product announcement blogposts within ~24hrs. Both written manually by someone who doesn't do product marketing for a living. It actually felt incredibly satisfying to focus and smash something out…
- Sep 19
-
> In your first draft, most of your paragraphs are bad, your topic flow is incoherent, and you’ve got at least 750 words you don’t need.I stopped reading at this point. All of the above may have been correct five years ago, when there was a "canon" of good writing, but now LLMs pack that canon as tight as teenagers in a boy band concert. So, go…
-
I still manually edit almost every word for utmost precision in anything I expect a human to read since LLM prose is hard to read and often subtly wrong or misleadingly worded (those false contrasts ...).Commit messages are not exactly in this category for me, I view them mostly as a work log to be later inspected by another LLM to gather context…
-
This article reads like user tptacek:https://news.ycombinator.com/item?id=48417027 (3 months ago)> Use LLMs to critique your writing, check its structure, vet your choice of topic sentences, check flow from graf to graf and section to section, look for passive voice and overused words. LLMs are fantastic for that. But don't use a single word an…
-
> Rule Number One: You may not use a single word an LLM suggests to you.I think there's a use case where this rule can be ignored. Sometimes I ask LLM to help me pick a single word or short phrase in some language, that has specific meaning, and connotations. Or doesn't carry some connotations or associations. Especially when I have an idiom from…
- Sep 18
-
> frontier models are supernaturally good at selecting pleasing turns of phraseIt's not even the suggestions in isolation, but it tries to convince you that your writing is stellar and then slips in a word or two, and you accept it because otherwise you'd be skipping greatness. I guess in some way one has to have a bit of hubris about one's…
-
You just should not do things that human beings are good at with automated processes. Things such as: creative writing, painting, dancing that is not pre-programmed, going with the flow, living the moment, having sex, wrestling, cooking, acting, connecting with your loved ones... and so on.Word chains these programs produce are inherently…
-
Too simple, too dogmatic at the start and at the end (“don’t use LLMs” and “then they are poison”). The middle section is all good.Writing with a LLM is a boon if you are trying to write while mastering a new field. Imagine a neuroscientist entering robotics or an electrical engineer trying to enter the field of neuromorphic systems. In these…
-
This is very good advice. I hate when llms turn into yes-men. I am surprise that the author doesn't use ai to construct the skeleton of the written piece. In my opinion, they excel at this, with all the books they've guillotined and digested, our biological brain cannot match their content retention. I would do the old trick of "asking for a…
-
The advice of "use your voice" only works if you have a good writing voice and comes off like Henry Cavill's dating advice or famous writers who said that you shouldn't use a thesaurus.Paying close attention to posts written by folks who are not using LLM's the comments here regularly complain (sometimes extensively) about the writing quality…
-
I sort of agree, but I also think the advice here is circular. To look at the style suggestions produced by an LLM and decide that you agree with some of them in spirit, but want to put it in your own words, you already need how to know how to write well.In other words, you need to read a style manual or two, and you need to read and have opinions…
-
Step one: open up the LLMStep two: close the LLMStep three: pick up a pen and writeWriting with LLMs is a great way to make yourself stupid: https://lambdaland.org/posts/2026-08-07-ai-writing-stupid/I'm glad the OP acknowledges that you have to have to do the writing yourself—though they say this more as a means to avoid getting pegged as having…
-
> Readers can detect LLM words in the parts per trillion. However much work you put into scuffing up and humanizing it, an LLM paragraph will register to much of your audience not as writing but as output. So, first the bad news: you have to write for yourself.---and then> Those rethinks are load-bearing parts of your voice. Readers won’t put…
-
"LLM paragraph will register to much of your audience not as writing but as output"The best advice for writing for other humans is: don't use LLMs.If you're writing for machines, liking coding, then fine go for it. If you're writing for processes with formal highly structured content like manuals, specifications, form content, procedures…
-
Just write, write your own words, then create an effective communication persona within your LLM's non-reasoning (non-Chain-of-Thought) capabilities and have it critique your writing after describing your target audience. Then, write your own revision following the critique. Using this, it is not possible to write "AI slop" unless your own writing…