https://news.ycombinator.com/item?id=49747070

I think people are stuck in the idea that the way you "use AI to write" is to let it generate alternative words for your thoughts. That's a terrible way to write. I advocate for a rule: "any word an LLM suggests to you is disqualified, even if it's better than the word you've chosen". Nobody is vigilant enough to keep LLM word selection from bleaching out their personal style.

But LLMs can do things for language (natch) that deterministic programs can't. Those things are helpful and you should consider taking advantage of them. Here's a short list of ways an LLM can potentially improve your writing:

* It can instantly spot overused words and turns of phrase, or, better still, worthless filler and throat-clearing like "just" and "very" and "it's important to note".

* It can rescue active verbs trapped inside nouns, where sentences are wrapped in zombie verbs like "make" or "reach" or "start" or "have", carbonite-frozen verbs like "decision" or "agreement" or "distortion".

* It can match the subjects of your sentences with actual characters in the action of your story or argument, flagging all the times you accidentally nail the subject of a sentence down to some random part of the scenery. It can check to see whether the new detail each sentence adds (if it adds any at all --- something else it can check) is in the stress position of the sentence.

* It can check your transitions and flag places where the openings of sentences and paragraphs are abrupt. For that matter: it can check the topic sentences of paragraphs and the flow from graf to graf.

* It can check for passive voice, but also note the (many) instances where passive is the right call for what you're trying to say.

The model never gets tired. It generally never forgets the rules. It can instantaneously diagram out a sentence and work out an accurate model of the semantics of your writing. It's doing things you cannot do with a grammar checker.

You're not going to want to act on everything an LLM flags. LLMs have an idiosyncratic sense of style (I keep saying they write every sentence like it's the headline of a magazine article). Some of these quirks of writing will be part of your voice, and you'll need to keep them.

You're not going to want the LLM to give you alternate words and sentences. That way lies Velveeta. And many times, the LLM will flag a usage issue and your response won't be to act on the suggestion, but just to rewrite the sentence or paragraph entirely --- or, better yet: just delete it, which is an awesome feeling.

This is using an LLM as a copyeditor. I've worked with professional copyeditors, and the feeling of working with an LLM copyeditor is comparable, except that the LLM is much more thorough, and I don't feel bad about ignoring it when we disagree. This style of working doesn't allow the model to infect your writing; it's just making you better informed about the words you're choosing. I think more people should try it.

It's an Internet urban myth. I'm just stepping in to call it out as such.

I have personally decided, in advance, that one goal I have in writing is improved clarity. The model didn't tell me to do that; Joseph Williams did, decades ago.

In the service of that goal, I've written down a proofreading checklist. It includes things like "look for overused words", "eliminate throat-clearing filler like 'it's important to remember that'", "make sure every paragraph has a clear topic sentence", "make sure my real verbs aren't buried inside nouns". Stuff like that.

Those are stylistic choices, I suppose, but they're mostly the difference between bad style and a whole universe of good styles.

More importantly: they're technical. They're not really judgement calls. The subject of a sentence either is or is not a character taking actions in the story you're trying to tell. It is better, almost always, if the subject is a character, and not accidentally some random piece of the scenery of your point.

Models are very good at flagging these things. Humans are too, but they're not as thorough.

Many people on this thread have suggested that having a model flag these kinds of issues bleaches out personal style. I don't think that's true; what I think is happening is that they missed the point I'm making, and assumed that I was advocating for having a model make broad subjective calls about my writing.

I'd love to know. I'll buy it!

I don't care whether the LLM likes these constructions or not. I don't like them. I usually don't want to keep them in my work. It's my call what to change; I just want issues flagged.

Your prompts would be different. Or, they would if you decided that having an LLM merely point things out about your own writing wasn't itself a form of contamination. You do you!

I wrote this article in about 45 minutes and didn't workshop it with anybody else, so I'm not surprised it's gone over people's heads; it was just something I was talking about on Twitter that I wanted to get down on a page. But it's pretty obvious that a lot of people here have missed the point.

    Workshop a piece with me. NO ENCOURAGEMENT. Encouragement is
    useless; the only useful things are suggested corrections.
    DO NOT WRITE COPY FOR ME. Any words you provide will be disqualified,
    so if you come up with good words, I’m fucked because I can’t use
    them. Tell me ABOUT what should change.
    Assume I know my audience extremely well.
    We’re going to do this in a series of passes. Keep your suggestions
    locked in to the current pass we’re on.
    Note typos, but DO NOT generate long structural critiques based on
    those typos; note them and move on, assuming that I meant to write
    properly.

But if you've generally been doing drafts and want to keep writing like that, if part of your process is going to continue to be refining and sharpening, then I think you should know that we're at a point where automation can accelerate that process for you. You can be getting the same amount of work done with less effort, or allowing yourself to concentrate more on the creative thinking part and less on the tedium.

That's the point of the post.