If you freely admit that you struggle with reading comprehension, why would your opinion on how best to write be valuable?
I'm not saying that as an attack, but the parent comment was completely comprehensible; it doesn't seem like you have the required expertise in this area to comment.
How do you know what the text would have been without LLM assist? Did I miss something? You are so confident in your claims, yet I don't see the non-LLM-assisted version.
"Explain how to solve" and "write like X" are crucially different tasks. One of them is about going through the steps of a process, and the other is about mimicking the result of a process.
Neural networks most certainly go through a process to transform input into output (even to mimic the results of another process) but it's a very different one from human neutral networks. But I think this is the crucial point of the debate, essentially unchanged from Searle's "Chinese Room" argument from decades ago.
The person in that room, looking up a dictionary with Chinese phrases and patterns, certainly follows a process, but it's easy to dismiss the notion that the person understands Chinese. But the question is if you zoom out, is the room itself intelligent because it is following a process, even if it's just a bunch of pattern recognition?
like OP originally said, the LLM doesn't have access to the actual process of the author, only the completed/refined output.
Not sure why you need a concrete example to "test", but just think about the fact that the LLM has no idea how a writer brainstorms, re-iterates on their work, or even comes up with the ideas in the first place.
This isn't true in general, and not even true in many specific cases, because a great deal of writers have described the process of writing in detail and all of that is in their training data. Claude and chatgpt very much know how novels are written, and you can go into claude code and tell it you want to write a novel and it'll walk you through quite a lot of it -- worldbuilding, characters, plotting, timelines, etc.
It's very true that LLMs are not good at "ideas" to begin with, though.
Professional writer here. On our longer work, we go through multiple iterations, with lots of teardowns and recalibrations based on feedback from early, private readers, professional editors, pop culture -- and who knows. You won't find very clear explanations of how this happens, even in writers' attempts to explain their craft. We don't systematize it, and unless we keep detailed in-process logs (doubtful), we can't even reconstruct it.
It's certainly possible to mimic many aspects of a notable writer's published style. ("Bad Hemingway" contests have been a jokey delight for decades.) But on the sliding scale of ingenious-to-obnoxious uses for AI, this Grammarly/Superhuman idea feels uniquely misguided.
The distinction being made is the difference between intellectual knowledge and experience, not originality.
Imagine a interviewing a particularly diligent new grad. They've memorized every textbook and best practices book they can find. Will that alone make them a senior+ developer, or do they need a few years learning all the ways reality is more complicated than the curriculum?
Let's take the work of Raymond Carver as just one example. He would type drafts which would go through repeated iteration with a massive amount of hand-written markup, revision and excision by his editor.
To really recreate his writing style, you would need the notes he started with for himself, the drafts that never even made it to his editor, the drafts that did make to the editor, all the edits made, and the final product, all properly sequenced and encoded as data.
In theory, one could munge this data and train an LLM and it would probably get significantly better at writing terse prose where there are actually coherent, deep things going on in the underlying story (more generally, this is complicated by the fact that many authors intentionally destroy notes so their work can stand on its own--and this gives them another reason to do so). But until that's done, you're going to get LLMs replicating style without the deep cohesion that makes such writing rewarding to read.
A good point. "Famous author" is a marketing term for Grammarly here; it's easy to conceive of an "author" as being an individual that we associate with a finite set of published works, all of which contain data.
But authors have not done this work alone. Grammarly is not going to sell "get advice from the editorial team at Vintage" or "Grammarly requires your wife to type the thing out first, though"
I'll also note that no human would probably want advice from the living versions of the author themselves.
i don't buy this logic. if i have studied an author greatly i will be able to recognise patterns and be able to write like them.
ex: i read a lot of shakespeare, understand patterns, understand where he came from, his biography and i will be able to write like him. why is it different for an LLM?
You will produce output that emulates the patters of Shakespeare's works, but you won't arrive at them by the same process Shakespeare did. You are subject to similar limitations as the llm in this case, just to a lesser degree (you share some 'human experience' with the author, and might be able to reason about their though process from biographies and such)
As another example, I can write a story about hobbits and elves in a LotR world with a style that approximates Tolkien. But it won't be colored by my first-hand WW1 experiences, and won't be written with the intention of creating a world that gives my conlangs cultural context, or the intention of making a bedtime story for my kids. I will never be able to write what Tolkien would have written because I'm not Tolkien, and do not see the world as Tolkien saw it. I don't even like designing languages
that's fair and you have highlighted a good limitation. but we do this all the time - we try to understand the author, learn from them and mimic them and we succeed to good extent.
that's why we have really good fake van gogh's for which a person can't tell the difference.
of course you can't do the same as the original person but you get close enough many times and as humans we do this frequently.
in the context of this post i think it is for sure possible to mimic a dead author and give steps to achieve writing that would sound like them using an LLM - just like a human.
Not everything works like integrals. Some things don't have a standard process that everyone follows the same way.
Editing is one of these things. There can be lots of different processes, informed by lots of different things, and getting similar output is no guarantee of a similar process.
The process is irrelevant if the output is the same, because we never observe the process. I assume you are arguing that the outputs are not guaranteed to be the same unless you reproduce the process.
If we are talking about human artifacts, you never have reproducibility. The same person will behave differently from one moment to the next, one environment to another. But I assume you will call that natural variation. Can you say that models can't approximate the artifacts within that natural variation?
It's relevant for data it hasn't been trained on. LLMs are trained to be all-knowing which is great as a utility but that does not come close to capturing an individual.
If I trained (or, more likely, fine-tuned) an LLM to generate code like what's found in an individual's GitHub repositories, could you comfortably say it writes code the same way as that individual? Sure, it will capture style and conventions, but what about our limitations? What do you think happens if you fine-tune a model to write code like a frontend developer and ask it to write a simple operating system kernel? It's realistically not in their (individual) data but the response still depends on the individual's thought process.
I don't know if LLMs are trained to imitate sources like that. I also don't know what would happen if you asked it to do something like someone who does not know how to do it. Would they refuse, make mistakes, or assume the person can learn? Humans can do all three, so barring more specific instructions any such response is reasonable.
> Humans can do all three, so barring more specific instructions any such response is reasonable.
Of course, but reasonable behavior across all humans is not the same as what one specific human would do. An individual, depending on the scenario, might stick to a specific choice because of their personality etc. which is not always explained, and heavily summarized if it is.
>If I trained (or, more likely, fine-tuned) an LLM to generate code like what's found in an individual's GitHub repositories, could you comfortably say it writes code the same way as that individual? Sure, it will capture style and conventions, but what about our limitations? What do you think happens if you fine-tune a model to write code like a frontend developer and ask it to write a simple operating system kernel? It's realistically not in their (individual) data but the response still depends on the individual's thought process.
Look, I don't think you understand how LLM's work. Its not about fine tuning. Its about generalised reasoning. The key word is "generalised" which can only happen if it has been trained on literally everything.
> It's relevant for data it hasn't been trained on
LLM's absolutely can reason on and conceptualise on things it has not been trained on, because of the generalised reasoning ability.
> LLM's absolutely can reason on and conceptualise on things it has not been trained on, because of the generalised reasoning ability.
Yes, but how does that help it capture the nuances of an individual? It can try to infer but it will not have enough information to always be correct, where correctness is what the actual individual would do.
i think there's a lot to be said about the process as well, the motivations, the intuitions, life experiences, and seeing the world through a certain lens. this creates for more interesting writing even when you are inspired by a certain past author. if you simply want to be a stochastic parrot that replicates the style of hemingway, it's not that difficult, but you'll also _likely_ have an empty story and you can extend the same concept to music
Even if the visualization of the integration process via steps typed out in the chat interface is the same as what you would have done on paper, the way the steps were obtained is likely very different for you and LLM. You recognized the integral's type and applied corresponding technique to solve it. LLM found the most likely continuation of tokens after your input among all the data it has been fed, and those tokens happen to be the typography for the integral steps. It is very unlikely are you doing the same, i.e. calculating probabilities of all the words you know and then choosing the one with the highest probability of being correct.
You are not able to write like Shakespeare. Shakespeare isn't really even a great example of an "author" per se. Like anybody else you could get away with: "well I read a lot of Bukowski and can do a passable imitation" or "I'm a Steinbeck scholar and here's a description of his style." But not Shakespeare.
I get that you're into AI products and ok, fine. But no you have not "studied [Shakespeare] greatly" nor are you "able to write like [Shakespeare]." That's the one historical entity that you should not have chosen for this conversation.
This bot is likely just regurgitating bits from the non-fiction writing of authors like an animatronic robot in the Hall of Presidents. Literally nobody would know if the LLM was doing even a passable job of Truman Capote-ing its way through their half-written attempt at NaNoWriMo
You can understand his biography and analyses about how shakespeare might have written. You can apply this knowledge to modify your writing process.
The LLM does not model text at this meta-level. It can only use those texts as examples, it cannot apply what is written there to it's generation process.
Yes, what I said should be falsifiable. The burden is on you to give me an example, but I can give you an idea.
You need to show me an LLM applying writing techniques do not have examples in its corpus.
You would have to use some relatively unknown author, I can suggest Iida Turpeinen. There will be interviews of her describing her writing technique, but no examples that aren't from Elolliset (Beasts of the sea).
Because the entire point is the LLM cannot understand text about text.
If someone has already done the work of giving an example of how to produce text according to a process, we have no way of knowing if the LLM has followed the process or copied the existing example.
And my point of course is that copying examples is the only way that LLMs can produce text. If you use an author who has been so analyzed to death that there are hundreds of examples of how to write like them, say, Hemingway, then that would not prove anything, because the LLM will just copy some existing "exercise in writing like Hemingway".
>Because the entire point is the LLM cannot understand text about text.
you have asked for an LLM to read a single interview and produce text that sounds similar to the author based on the techniques on that single interview.
There is no actual short story behind the link? moon_landing_turpeinen.md cannot be opened.
You could not have done better? Love it. You didn't even bother rewriting my post before pasting it into the box. The post isn't addressed as a prompt, it's my giving you the requirements of what to prompt.
Also, because you did that, you've actually provided evidence for my argument: notice that my attitudes about LLMs are reflected in the LLM output. E.g.:
"Now — the honest problem the challenge identifies: I'm reconstructing a description of a style, not internalizing the rhythm and texture of actual prose. A human who's read the book would have absorbed cadences, sentence lengths, paragraph structures, the specific ratio of concrete detail to abstraction — all the things that live below the level of "technique described in interviews.""
That's precisely because it can't separate metatext from text. It's just copying the vibe of what I'm saying, instead of understanding the message behind the text and trying to apply it. It also hallucinates somewhat here, because it's argument is about humans absorbing the text rather than the metatext. But that's also to be expected from a syntax-level tool like an LLM.
The end result is... nothing. You failed the task and you ended up supporting my point. But I appreciate that you took the time to do this experiment.
> "Now — the honest problem the challenge identifies: I'm reconstructing a description of a style, not internalizing the rhythm and texture of actual prose. A human who's read the book would have absorbed cadences, sentence lengths, paragraph structures, the specific ratio of concrete detail to abstraction — all the things that live below the level of "technique described in interviews.
a human would have to read all the text, so would an LLM but you have not allowed this from your previous constraint. then allow an LLM to reproduce something that is in its training set?
why do you expect an LLM to achieve something that even a human can't do?
Why are you taking the LLM-hallucinated version of the argument as truth? I even clearly stated how the LLM-version of my claim is a misunderstood version of the argument.
Do you remember the point we're arguing? That a human can understand text about a way of writing, and apply that information to the _process_ of writing (not the output).
If you admit the LLM can't do this, then you are conceding the point.
I don't know why you're claiming that humans can't do this when we very clearly can.
An illustrative example: I could describe a new way of rhyming to a human without an example, and they could produce a rhyme without an example. However describing this new rhyming scheme to an LLM without examples would not yield any results. (Rhyming is a bad example to test, however, because the LLM corpi have plenty of examples).
The point is that you dont become Jimi Hendrix or Eric Clapton even if you spend 20 years playing on a cover band. You can play the style, sound like but you wont create their next album.
Not being Jimi Hendrix or Eric Clapton is the context you are missing. LLMs are Cover Bands...
I find this repellent; why not, instead of trying to push unwelcome generated prose below the radar, stop trying to waste everyone's time? People don't object to these patterns because they hate lists of three; they object to them in this context because of what they signal about the content.
If using AI to write is nothing to be ashamed of, then you shouldn't feel the need to hide it. If it is something to be ashamed of, then you should stop doing it. If someone objects to you poisoning a well, the correct response is not to use a more subtle poison.
I sometimes like having my content editorialized. Some of the LLM writing tropes are ok to me—I'd delete them if I added this prompt to my instructions (but I wouldn't). But my editorial preferences—the sense of voice and tone I want the LLM to make—are rarely these tropes. Instead, I have a positive prompt of the angles I do enjoy.
However, what is cloying about these tropes for many is that they're becoming empty words. Instead of tack-sharp summaries or reductions to simple understanding, the model is spilling extra tokens for minimal value—I don't need to read "it's not X, it's Y" for the n-th time today. I'd really prefer tighter, more succinct reading that actually directly quotes sources (which modern models rarely do to avoid copyright traps).
I sometimes use AI to quickly summarise a handful of several MB long PDF files.
This allows me to order them in order of the relevance to start getting my data and information faster.
Applying a constraints like in the published template will make it slightly less awful. It's going to be discarded anyway, but at least the experience is going to be better.
Not every LLM output is going to be published for you to consume. If hazard a guess most never sees the light of the day.
Treating the act of refining text as a confession of shame misses the point of how writing works. Whether a draft begins as a model output, a dictation, or a scribbled note, the final responsibility belongs to the person who hits publish.
Improving prose to remove predictable patterns is the work of an editor. This process ensures the content is worth reading and respects the audience's time.
Comparing a software tool to "poisoning a well" turns a debate over style into a moral crisis that doesn’t fit the situation. If the information is accurate and the writing is clear, the water in the well is fine, regardless of the pump used to get it there. If the water tastes good, complaining about the plumbing is just a distraction.
Parents complaint is explicitly not about the style of the prose, use whatever you want to check your grammar and reduce redundancy. The complaint of poisoning the well is regarding content that is not intended to express anything at all, the old “why would I read what nobody bothered to write”
The issue is that you're conflating the process of transcription with the act of expression. If I feed an LLM my own raw research notes and technical observations and use it to help structure those thoughts into a readable essay, I haven't "avoided writing".
The "why would I read what nobody bothered to write" argument only applies to people who ask a bot to hallucinate an opinion from scratch. It doesn't apply to authors using the tool to clarify their own ideas.
LLM-generated text that is a hallucinated-from-scratch opinion is practically indistinguishable from LLM-generated text that is rooted in your research notes.
I find putting the former into my brain abhorrent to such an extent that I am willing to forego reading the few instances of the latter. I'd much rather have your raw research notes and observations.
> If I feed an LLM my own raw research notes and technical observations and use it to help structure those thoughts into a readable essay, I haven't "avoided writing".
> The "why would I read what nobody bothered to write" argument only applies to people who ask a bot to hallucinate an opinion from scratch. It doesn't apply to authors using the tool to clarify their own ideas.
You're wasting my time if you share LLM writing. If you're going to do it that way, share your notes and your prompt. Otherwise, you're being inconsiderate.
>Comparing a software tool to "poisoning a well" turns a debate over style into a moral crisis that doesn’t fit the situation. If the information is accurate and the writing is clear, the water in the well is fine, regardless of the pump used to get it there. If the water tastes good, complaining about the plumbing is just a distraction.
Speaking of poisoning wells, have you heard of this thing called Search Engine Optimization? Absolutely ruined the Internet.
For example it ignores the gazillion medium(-like) "articles" that are not much more than the output of a prompt. Here AI is not about style, is about content too. If you open such a post, maybe with the intent of learning anything, and you realize is AI slop, you might close it. Making it harder to recognize is poisoning the well in such cases.
There is no such thing as “qualified”. The engineers actually doing the work definitely get a seat at the table, otherwise it’s an academic circle jerk detached from reality.
If it's moral to strike at a country with nuclear capability that talks constantly about your country's destruction, then it's no less acceptable for Iran to strike the US than the other way around.
You can't condemn one and condone the other on that basis.
Iran has both reason and were developing capability to destroy a significant part of American national security. America absolutely must prevent that at any cost.
You could argue about how the rhetoric between the states got so bad that they each threatened each other's destruction. But the fact is that they got there.
- I forgot my password and Microsoft is sending reset emails to the account that that password bars.
- I remember my password but now it says I need a passkey and I don't know what that is.
- I forgot my password and in the process of resetting it, Microsoft created a duplicate account.
All of the above are real problems that I have seen in the wild. I could list many more.
Given that Microsoft knows--and has always known--user limitations, it behooves them to design idiot-proof software, not continually release poorly-designed changes.
I don't think that article makes a strong case; it deliberately phrases examples in the most ridiculous ways and pretends that this is a damning criticism of the phrase itself; it's 'you're telling me a shrimp fried this rice' but with a pretence of rationality.
I think it makes a pretty compelling case that most invocations of the statement are either blindingly obvious or probably false. Can you give a counterexample?
> most invocations of the statement are either blindingly obvious or probably false
So straightaway, you've walked significantly back from the claim in the headline; now half of the time it's 'blindingly obvious' that the statement is correct. That already feels like a strong counterexample to me, and it's the article's own first point.
Secondly, look at this one specifically:
> The purpose of the Ukrainian military is to get stuck in a years-long stalemate with Russia.
Firstly, this isn't obviously false. It's an unfair framing, but I think the Ukrainian military would agree that forcing a stalemate when attacked by a hostile power is absolutely part of their purpose.
Secondly, it is an unfair framing that deliberately ignores that all systems are contextual. A car's purpose is transport, but that doesn't mean it can phase through any obstacle.
The article makes an entirely specious argument, almost an archetypal example of a strawman. It can't sustain its own points over a few hundred words without steadily retreating, and that is far more pointless than the maxim it criticises.
I'm reminded of an XKCD comic [1] about smug miscommunication. Of course any principle is ridiculous when you pretend not to understand it.
I'm not saying that as an attack, but the parent comment was completely comprehensible; it doesn't seem like you have the required expertise in this area to comment.
reply