"Those rethinks are load-bearing parts of your voice."
Loved the (possibly not deliberately ironic) use of the LLM'S favourite analogy, load-bearing.
Nice wee article though. I particularly agree with "Don’t take all of the model’s copyediting advice." I've been using LLMs to review teaching material and often it just doesn't get the point of teaching. It's good for prompting reflection on your writing but it's still an idiot savant.
Can't vouch for that but I can vouch for `Dreyer's English` as both hilarious (if you're the sort of person who relishes finding le mot juste, like me) and excellent as a style guide.
Yeah it's very short, but I can't remember if I read all of it, or just flipped through pieces. It has good advice and I think fairly "famous." (edit: this reminded me I still have my copy :-D)
I know someone in a profession that does a lot of writing, and it blew my mind how clearly feedback was communicated by a superior. Made me wish tech people had better written communication skills. ;-;
It’s good—better than the much-revered Elements of Style, imho, which is overly prescriptive and frankly unhelpful at turns, even if it’s well written.
But my all-time favorite is Virginia Tufte’s Artful Sentences: Syntax as Style. It illustrates the variety of English sentence structures in an ordered way with a plethora of examples. The approach is not prescriptive; rather, it allows you inductively to develop a feel for the syntactical rhythms of the language.
Also, I love Stanley Fish’s How to Write a Sentence: And How to Read One. It’s a lovely, entertaining little book, filled with Fish’s insights as an eminent literary critic. What I appreciate most about the book is that Fish walks you through a number of examples and explains how and why they work, so you can walk away as both a better writer and a better reader.
It‘s been available under different variations of the title, you don‘t need the latest one, and amazon.de should have a used copy for five Euros or so.
I've been reading Steven Pinker's "The Sense of Style". Unlike "The Elements of Style", which is fine, it does a good job anchoring its suggestion in first principals. I do think I need to read a book on grammar to truly appreciate it though.
"On Writing" is another book like "The Elements of Style", both are too prescriptive, albeit not useless.
Steven Pinker’s “The Language Instinct” is not a bad book for learning grammar. It’s a book about linguistics - not specifically grammar, but it covers diagramming sentences, and grammar falls out from there
I fear in the future people will read even less because of how often people cheap out and use AI to write.
I know the author of this article tells you never to use a single word it suggests, however I still, while reading, am checking for any amount of AI used.
This makes reading less enjoyable, and even a bit stressful.
If you can't spend the time to write it, why should anyone read it?
Everything I post is from my own finger tips, only to get a reply from someone using a bot. I'm tired.
I don't ever watch TV or streaming shows anymore. It's been a huge improvement in my life. It's the same with reading. Reading is mostly a waste of my time, with some notable exceptions. I'm glad I spend way less time doing each of these!
It's sad that reading has become that way for you.
I love reading, but I mostly read non-fiction and I'm a bit of an amateur history buff. Last time I read a fiction book I was left feeling like I was preached to by an alien about how life doesn't really matter (sci-fi authors will often do that). The state of literature is pretty dire.
It’s hard to find good new literature - it may be out there, but it’s hard to find. But there’s lifetimes worth of good older literature, that’s much easier to find, that you haven’t read yet.
Just read people you can trust. Why are you giving yourself all this busy work?
Just make your own tree of material to read. You should have a couple dozen writers/journalists you admire, look at who these people read then start reading those people, then you repeat the cycle.
Don't waste your time reading anything new, most new things are bad. Most ideas we struggle with, are ideas we have been discussing since the written record was invented out of necessity.
Anything new worth reading will assuredly make your way to you if you are at all connected.
No it really wouldn't. I like the authors Jeff VanderMeer and Peter Watts. They have had multiple interviews where they talk about their peers, who they respect from the past, and who they like in our current age. I have found maybe subsequent authors + journalists to read from these two.
Try to think a little more critically here. If you can't trust the opinion of people you supposedly like, already established in their craft, who can you trust?
Have no idea why you think this would increase influencer culture, but thanks for telling us all publicly how you interact with social media: in an sloppy uncritical way.
My advice for you is to pull the plug and read books that are older than 125 years.
For everyone that you consider "good" there are at least a dozen people who are equally "good" but without the social proof. What you describe played out exactly in music and art pre-AI. The record exec and the gallery owner were the people you "trusted" who king-made and gate-kept what we saw based on what they thought was most marketable.
> Have no idea why you think this would increase influencer culture, but thanks for telling us all publicly how you interact with social media: in an sloppy uncritical way.
This is a personal attack that is unsubstantiated by what I wrote, read the guidelines and follow them or go elsewhere.
I think we could agree that everyone already does this up to a point. This is basically just an exploration-exploitation dilemma, where everyone tries to maximize how much value they gain from the things they read, and a lot of people have strategies to pick what material to read.
Reading trusted authors is likely to be valuable, but they may devalue over time. We don't know if our chosen authors maximize our value, nor whether exploratory reading does, etc.
The thing is, that was the internet before AI. In fact, generative AI almost certainly raised the AVERAGE quality of stuff on the internet, human slop was/is absolute trash, whereas AI slop is just bland and meandering.
The problem here is that the volume of low-mid content is making it harder to find the best content.
More than the average person, I suppose. For some reason, AI writing isn't as irritating to me as it seems to be for everyone else.
I treat it the same way I treat human writing: by speed reading most of the article so I can find the points the author is trying to make and decide whether I should read the entire thing.
People on my FOSS project couldn't see the issue with their AI slopped documentation contributions.
On one hand I'm like, yeah fair enough it needed writing and something is better than nothing.
On the other I know nobody wants to read it now because it's just word vomit rather than how a human would write something they'd like another human to read.
On Debian we recently voted whether to permit or forbid llm usage (spoiler, AI usage at will won).
One person was arguing that they need llm because english isn't their first language and then it helps them write better and be understood. I was incapable of reading their (extremely long) email of arguments; I tried but my mind just went elsewhere as my eyes were moving through the lines.
At the very end there was a disclaimer that llm had been used to "aid" in writing that very email.
Poor guy thinks he's communicating better but all he's doing is making his emails completely unreadable. It's a sad state of affairs.
There is now increased evolutionary pressure for rules protecting scarcity to become norm. Communication media will likely adopt limits on the size and throughput of messages.
It kind of makes sense that if English is not their first language, the can't review the LLM English output also.
However most likely they just don't understand what good communication looks like, LLMs are perfectly capable of turning anything into clear concise communication, in fact an easy tell that something is LLM written is that it's just too precise and clear, humans are much more rambling.
> 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 course professor?
Of course there are writing as: "Hey ChatGPT write me a piece around coding with LLMs" and yeah, those are not worth reading.
But most of the writing is usually, these are the ideas, this is how the idea are structured together, now let's review them and then let's get a nice prose out of it.
Yeah, it's phrased like a reductio ad absurdum but it's close to being literally true. It's not technically "copywriters" but their words are "polished" for pleasantness, often with the explicit guidance of consultants, until most of the truth or novelty is gone.
> But most of the writing is usually, these are the ideas, this is how the idea are structured together, now let's review them and then let's get a nice prose out of it.
I know lots of AI-enabled writers believe this, but I've never actually seen it be true.
How about Anthropic? I've seen people say it's surprising that their blog isn't written with AI, but I think it's far more likely that it is written with AI; they are just good at reviewing and getting a nice prose out of their models.
> 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 effort in thinking it up yourself.
Why is that? Is it because you think there is inherent value in the sentence you transcribed, in spite of the near zero effort you spent creating it? If you think anybody here should read it, then you have undermined your own point. If you don’t think anybody should read it, then you shouldn’t post it.
JimDabell said they didn't come up with that thought themselves. They never implied the poster didn't mean it. sm-silversight responded, "How do you know it's not his/her thought?" You can reasonably interpret them as asking how we know they didn't come up with that thought independently.
If we go with your interpretation instead, then sm-silversight simply misread the comment they replied to and their post doesn't follow. No one doubted OP felt sincere about not wanting to read AI.
> despite having spent no time or effort in thinking it up yourself.
I mean, how can you say that he didn't think it himself? I thought this same thing and realised apparently I'm not the first. You have no idea how many of my blog posts ideas have come in HN first before I could publish. People can have the same thoughts. And have em all the time as well.
Psss.. See how @sm-silversight who commented on your post said the same thing I did? That's realtime example right there.
Coming back to the topic at hand. I agree with the OP. If you don't care to write it, why should anyone read it? AI has good usecases. But am not sure writing is one.
Writing is not just about the end result. It's also about the thought process. I learn about the topic more as I write. I correct my incorrect understandings as I write. When am pissed, my article has a different tone. Am rude, too direct. When am content/happy, different one. All of this is sterilised into something robotic where the author won't even remember what he/she wrote? What's the to like? For brownie points?
Selecting between alternatives is also a very valuable skill. Also known as "taste".
You are a senior software architect, you "prompt" 10 junior architects to write a software architecture proposal and then pick one which you send the client.
Would you say it's worthless, because the senior architect didn't care to write it?
There are plenty of industries where "taste" is a real job.
Or for some reason prompting a LLM and forwarding it's output is different than prompting a human and forwarding the output.
> Would you say it's worthless, because the senior architect didn't care to write it?
Lemme ask you a counter question, the senior architect writes the proposal and the junior writes it. Which one do you think client likes better?
Moreover, Your focus is on the end-result. Sure, in corporate environment, most people don't care about what they do as long as the end results checks some boxes. That wasn't the discussion here. The discussion is about writing and reading in general. Whether it's worth my time or not if you don't mean (forget mean, don't even remember) what you wrote.
Also, in your own example, the client don't care as well. As long the client's checks all the boxes his/her/their manager said should satisfy. Nobody really gives a damn about the quality.
Also, are you saying you'll be fine paying for Financial Times, WSJ and NYTimes KNOWING all they do is shove the story through an LLM? Neither will there be a soul, nor will there be any material effect on people who reads it.
> Or you think that for some reason prompting a LLM and forwarding it's output after vetting is different than prompting a human and forwarding the output after vetting.
There is difference no? I forward the output to get good feedback and correction from someone BETTER. And there is a process involved in it which showcases the "TASTE" you mentioned from the person whom you are forwarding your output to be vetted and that person comes up to you with feedback. And guess what? You learn from the person's feedback. You don't go back again and again forever to learn the same thing. That's exactly what am trying to point out.
> nor will there be any material effect on people who reads it.
This is a ridiculous thing to say - "because the Weather app in my phone is 100% automated with no human "soul" in it, I will not take it into account into how should I dress today"
> the client don't care as well
This applies here too. If you didn't pay for author's output, are not a subscriber to their Substack, why should they bother to hand craft you a quality human written post?
> If you didn't bother to write it, I won't bother to read it
So the argument is that effort should be somehow matched. Ok, let's go with that. It's well know that writing something takes 10x more effort than reading it. So if we use the market argument, if it takes you 10 min to read a blog post, the author should spend 1 min writing it, because writing is 10x more intense, and this is only possible with a LLM. You might say "but there is one author, and 1000 readers". That gets us back to the paying argument.
> how can you say that he didn't think it himself?
Because the same sentence has been repeated practically word-for-word ad nauseam all over social media for years. What do you think is plausible - that they repeated something that is damn near omnipresent in the discourse, or that they never saw any of the many, many times it has come up and independently came up with the exact same formulation? They are perfectly able to step in and claim that it was their original thought if they want to.
> What do you think is plausible - that they repeated something that is damn near omnipresent in the discourse, or that they never saw any of the many, many times it has come up and independently came up with the exact same formulation?
Both are fully possible.
We're talking about a simple sentence that sounds a lot like something a primary school teacher or parent of young children would say. "If you won't do/don't/haven't done X, why should I Y?" is very normal moral/ethical phrasing.
I suppose I heard someone say it before I spelled it out in that way, but I am pretty confident I would ultimately have used a sufficiently similar expression, because I have been on the receiving end of the problem.
And that is putting aside the communicative compression of aphorisms. People don't use shared aphorisms to avoid ever doing the thinking themselves; they use them to shorthand more complex arguments for a listener who has already heard them. They are shared macros for agreed concepts. (Using them correctly requires having done the thinking they package up at least once).
OK, how about 'nothing is real, nobody will ever care again, let's all never listen to anybody else ever again'?
That's more or less the same thing expressed more nihilistically. But nihilism is, like, just a word man (to 'The Dude' it up a bit). Perhaps we are either fiddling on the deck of the Titanic, or just staring at the waves?
What do you think the results will be of the machines consuming only their own slop and Habsburging themselves intellectually, and then all the humans abandoning any attempt to either talk or listen? As a global civilization of humans? I'm not sure we've explored the likely consequences of 'if you can't spend them time to write it why should anyone read it'.
It's a pithy way of expressing what many people feel. A meme, if you will. Echoing it is participating in the group psychology. And expression doesn't need to be wholly original to have meaning. I think your dismissal is way off base.
Some things are worth repeating, so the community knows that many people share the belief. Often they're slogans, sometimes they're just plain good arguments.
You are moving the goalpost. OC is not talking about thoughts having to be unique. You can very much read someone else's thoughts, examine them critically and come to the conclusion of agreeing with them. You might then write a comment like OC putting these thoughts into your own words – maybe abridging them, placing different emphasize according to what you find most important or even adding new ideas – and quote or paraphrase something you found very fitting.
That is completely different from generating words that are not an expression of your thoughts or at the very best take some concise thoughts from the prompt and stretch them into a lengthy word soup.
Of course there are people who just parrot other people's thoughts without understanding them. That's closer to using an LLM. But you can often see how well someone understands something and how much reasoning of their own they put into it through their writing. And for the writer writing is a very good way to reflect on their own thoughts and to get them into order. Proper writing is thinking.
The way I see it is that a clearly AI generated article is the result of some prompts. So the "author" wrote tens of words, which then got inflated to hundreds and maybe thousands by a computer program. This is a very inefficient way to convey an idea, especially if the reader has access to the same program. I'd rather the author shared their prompts, because maybe there's some originality in it, and I can then decide if I want to explore the idea further, maybe even with an LLM.
Strongly agree. Whenever I see an "AI-written" disclaimer, I skip it entirely. And if it's not disclosed, the exact moment I realize it's AI output, I immediately close the tab.
It feels like a waste of the reader's time.
To focus your point: we fear that with ideas having easier replication that the noise in the signal will increase.
But this is what people said about the printing press. And the internet. Less effort to spread the memes. Has it been a net negative? Maybe in some respects. Can you stop it? Probably not.
> I still, while reading, am checking for any amount of AI used
Im sorry for you. It must be hard to detach yourself with a fixation. I also cant help but spend my attention spotting where the magician is hiding the coin instead of trying to enjoy the show
> If you can't spend the time to write it, why should anyone read it?
Most people in these threads repeat this question. As if pre-ai all writing was from deep thinkers full of genuine intention.
At work the jira tickets have become massive walls of AI slop. What’s worse is they contain huge amounts if useless “thinking” where the LLM explains what it did and checked rather than just giving the final result.
As a result, when I see an AI wall of text I just don’t bother reading it and DM the submitter asking what it’s about.
Language is meant for sharing information. I don't think there's anything wrong with using AI to write - the real issue is that AI-generated writing can be hard to understand. Once AI solves the readability problem, its writing will actually be better suited for communicating with humans.
Not only hard to understand, but if one uses it without first understanding the topic, it's a disaster.
Couple weeks ago I had someone linking to a doc page in my ticket "Made this summary, hope it helps". It was 100% AI generated, the person clearly had no understanding of the problem, it only mentioned UI changes although the thing required changes in many systems. Complete waste of time, I don't think I will humor anyone who makes AI summaries anymore.
Agreed. Recently I've made the effort in disclosing on my website posts that 100% of the words are written by me. I do make graphs and share data here and there, and the same applies - I'm transparent if an agent happened to be used in the process. I don't mind if someone used an LLM to write something, but disclosing such is a good rule to go by IMO.
I've seen this in action as well. The biggest value by far is seeing the overused phrases and tics in your writing style. The prompt I like is to tell it to highlight and flag passive voice and run ons since those are my major pain points. I can also tell when its getting out of "real" advice since it'll offer the same "trim 10-15%". Also important to tell it to highlight specifics otherwise it'll give vague editorial advice that isn't anchored. Another fun exercise is to submit other authors writing as well. Say a short story from a magazine. Some of the edits are legit, but do it enough times and you'll start to see the same generic writing advice gets applies to just about any input.
another iteresting thing models can do is to highlight and notice themes and motifs in a piece. I find that helpful when thinking about a piece of work. Might be obvious ones, sometimes it can be subtle themes. Good for stirring your own brain.
On a somewhat off-topic note, it seems like even the richest publications no longer employ copy editors, or not enough of them anyway. I am constantly spotting obvious and stupid errors in articles (e.g., duplicated words and misspellings) in the New York Times, Washington Post, et al. I'm certain it didn't use to be that way. (Fact-checkers also seem to have gone extinct; at least once or twice a week I'll read a news article with a glaring factual error or an absurd mathematical error.)
I see that as well. Sometimes I can see that they are prioritizing speed to print for breaking news (publishing to the web happens continuously vs the cadence of a daily newspaper) but often it is just being sloppy.
When most people are consuming _their_ news (as opposed to _the_ news) in the form of a thumbnail in an algorithmic social media feed, those copy errors matter less.
This is similar to how I've come to use them but it's focused too much on the mechanics or writing. I've found them more valuable at role-playing as a specific profile of reader and asking it how they would receive the arguments advanced by the writing and what counterarguments they could present. After some rounds of this process, you either close all the gaps in the argument or realize it's not a strong one.
It's darkly amusing that while the author advises us not to let LLMs pick our words, their post includes this chunk of AI slop:
"Those rethinks are load-bearing parts of your voice. Readers won’t put their fingers on what’s wrong, but they’ll sense that you’ve become artificially-flavored."
The metaphor at the start is AI-like weirdness too: "without pasteurizing and jacking it with corn syrup." Pasteurising is good, corn syrup is bad - what the heck am I supposed to make of it? It's nonsense.
It may even have been handwritten by the author, but it's slop nonetheless.
You may be telling yourself that you're disciplined and you're just using the LLMs for review. But while you're reading their output, the slop makes its way directly into your brain anyway - and then it drips out into your writing.
I saw "load-bearing" there and instantly assumed Thomas was making a deliberate point that it's OK to use terms that LLMs have poisoned provided you use them effectively and in a way that adds to the piece.
I'm personally furious that "load-bearing" has become an LLM tell, it's a really useful metaphor!
I suspect the author was thinking "homogenizing" but his brain picked pasteurizing by accident. Pasteurizing and homogenizing are both things done to milk, but homogenizing has an additional meaning of making something uniform (and more loosely it's often used to imply that you've made something generic, bland, and boring).
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 occasion it pointed me towards some documentation that undermined my entire post - and led to a much better one a week later once I'd processed and applied that new information. Thanks, LLM.
I do this all the time. It's shocking how well it works. A year or two ago suggesting that someone use LLMs for fact checking would get you laughed out of a room, but today the good ones (Fable, GPT-5.6/6) with a search tool enabled are genuinely excellent at this.
They can even retrieve articles you link to and check that you aren't misrepresenting them.
This is bad advice for anything serious that can be subtly wrong. I’ve had Fable being consequentially wrong about what a certain, rather small, code block does in our codebase. Not even on something very complex which wasted a lot of time and effort from the team until we checked the code ourselves. I think these tools are still useful and one should learn to use them but blind trust for anything of importance is misguided IMO.
I use Fable to give me feedback on things I write. But I discard about 50%, because it often does not have the context and thus tends to favour hedging stuff. Also, it does not always vibe with my writing style.
But the 50% I do take into account, improves the text! And, like TFA, I never ask it for concrete text. It only helps me diagnose the issues, I prescribe the medicine!
Hyperbole = strong opinions? If you're stating your 'strong opinions' as fact, then you deserve the push back. If you're stating your strong opinions as strong opinions, then fair game.
If I want to say that iOS is useless for developing Bluetooth 5 features then this is true for all practical purposes and doesn’t deserve elaboration in my text, even if Apple’s API technically exposes one or two tiny pieces.
You say this but fact and opinion are very similar and not at all easy to distinguish.
For instance, if I said the grass is green vs if I said the grass looks nice vs if I said the grass is doing well and looks how it should vs if I said in my opinion the grass is healthier than its ever been.
If English is your second language and you intent to write in your mother tongue, my advice is to use English to communicate with the LLM.
This makes Rule 1 straightforward ("You may not use a single word an LLM suggests to you") and helps avoid the horrible feeling that the machine is taking over your personal voice.
I’ve used llms in two ways while writing fiction. First I’ll have a story idea and use the llm to explore what has come before that may be related; then I’ll go read some stuff. This has worked great for seeing where my ideas fit and flushing them out. Second I’ll describe settings or plot devices and use the llm to brainstorm consequences or further ideas. This fails miserably. The llms suggestions are devoid of creativity. This is all moot though because I’m really not a writer, I’ve just always thought I might like to be one someday.
> Present the original and new writing to the model and ask it which is better.
LLMs have absolutely terrible taste when it comes to writing. I don't find their feedback useful at all, beyond trivial spelling/grammar mistakes, which you don't really need an LLM for in the first place.
Proofreading is all you need.
Edit: I do sometimes ask an LLM for a fact-check, though.
Yeah, the best advice is: Don't. Write it yourself; make judgements; learn.
In general use today, AI primarily functions as a stupidity amplifier: it empowers dumb people to do dumb things more pervasively, with less effort, and at unprecedented scale.
We're moving into an era of artificially enhanced stupidity.
This aligns with my observations, but I'm less optimistic about what you get out of it.
The models are good at pointing out basic syntax issues that slip past spell checkers. But here's how you can get a comparable result: just let it stew. Grab lunch, walk in the park, re-read your article. You'll be surprised.
As noted in the article, style recommendations from an LLM are almost always bad. The advice in the article is sound, but to follow it, you need to know how good writing looks like. So you still need to read a style guide or two. I'm sure the author did.
The most promising use of LLMs is to have them criticize your high-level argument, but they struggle with that. I think it has to do with the training. They're desperate to please and it's difficult to get them to say "this idea sucks". You can explicitly prompt them to be brutal, but the result is often over-the-top. You can present them with the article without mentioning its yours, then ask them to write a polemic. That can work, but it's not a streamlined approach.
At one point in my graduate college studies, I tutored qualified (DEI) undergrads 'for free' (for them) as part of a work-study program which paid me a bit for that work.
OTOH, an AI could not have qualified as such a student. But even if it did, before we began I would certainly bargain for considerably more than work-study tutoring paid.
Indeed. I have been experimenting with using frontier models for creative writing.
Using adversarial models to evolve ideas. I have a whole novel of material, and the feedback has indeed been useful. But the actual novel? Not even AI models like their own writing once you give the simple prompt of "account for model sycophancy".
The resulting structure and plot beats are good with AI as copy editor. Only the least discerning reader might not care or notice the actual non-human writing. And hey - maybe those are your readers. Probably not.
Can we all appreciate for a moment the sci- dystopia which snuck up on us all? I just used to phrase: " non-human writing". 50 years ago, that would send a chill up your spine.
Till today, I was doing the complete opposite of what the article suggests. Definitely going to try this approach out, pretty helpful.
I have a specific ChatGPT chat that rewrites my posts really well every time; I usually just give it a rough draft and let it clean things up. But it was pretty interesting to realize how good these LLMs are at actually finding mistakes rather than just rewriting things. The point about not letting the model influence your voice was also very, very relevant.
I feel like it normalizes writing faux pas; any use of a semicolon could have just been a new sentence.
I’m thinking that people that get years semi-colon and colon filled paragraphs are going to believe this is a normal and good way to write on their own.
I mostly use LLMs for coding, so this is an interesting use case. I’m curious how long an article it can handle in practice before the context starts becoming an issue.
All the Big AI APIs handle a million tokens of context. That's enough for 750,000 words or, several entire novels.
Context isn't an issue. It's style.
The argument the author is making is that if you use an LLM to write for you, you end up with a homogeneous work that's just like everything else.
In journalism, that's sort of what you want.
In novels/function, that's the opposite of what you want.
However, there's degrees to these things. If you're looking at a sentence you wrote, thinking there's something "off" it can be helpful to have the LLM rewrite it just to see how it thinks it could be better worded.
I've done this a few times and I do find it helpful. Just like the author, I never just accept what it gives me. I simply use it as an OK-ish copyeditor that's good at spotting issues and suggesting solutions.
The frontier live voice models (especially GPT Voice/Live or whatever they call it this week) do not have the typical AI-tells. So I wonder about a few things:
Why is this?
Why couldn’t whatever went into post-training these voice models be applied to the text-gen models to get rid of AI smells?
Could we set up a pipeline that leverages the voice models to clean up text that reeks of AI ?
I would guess that it's just a matter of context, I haven't used voice mode at all but I imagine you don't get full paragraphs from them but get something more conversational instead
I think it's good advice. I find it a bit funny the author said to not use a single word coming out of the LLM, but they probably did just that because I never heard a human being say "load-bearing" before but now it's all over the place, also used here. Or I don't get the irony.
The irony comes in the last sentence: "Readers won’t put their fingers on what’s wrong, but they’ll sense that you’ve become artificially-flavored." The joke is that he wrote the preceding sentences in the paragraph in a way that intentionally plays up written-by-LLM-isms so that you feel the sense being described in the quoted sentence.
288 comments
[ 0.22 ms ] story [ 54.9 ms ] threadLoved the (possibly not deliberately ironic) use of the LLM'S favourite analogy, load-bearing.
Nice wee article though. I particularly agree with "Don’t take all of the model’s copyediting advice." I've been using LLMs to review teaching material and often it just doesn't get the point of teaching. It's good for prompting reflection on your writing but it's still an idiot savant.
Does anyone know about "Style: Lessons in Clarity and Grace" ? Seems like an interesting book
I know someone in a profession that does a lot of writing, and it blew my mind how clearly feedback was communicated by a superior. Made me wish tech people had better written communication skills. ;-;
But my all-time favorite is Virginia Tufte’s Artful Sentences: Syntax as Style. It illustrates the variety of English sentence structures in an ordered way with a plethora of examples. The approach is not prescriptive; rather, it allows you inductively to develop a feel for the syntactical rhythms of the language.
Also, I love Stanley Fish’s How to Write a Sentence: And How to Read One. It’s a lovely, entertaining little book, filled with Fish’s insights as an eminent literary critic. What I appreciate most about the book is that Fish walks you through a number of examples and explains how and why they work, so you can walk away as both a better writer and a better reader.
"On Writing" is another book like "The Elements of Style", both are too prescriptive, albeit not useless.
If you can't spend the time to write it, why should anyone read it?
Everything I post is from my own finger tips, only to get a reply from someone using a bot. I'm tired.
I love reading, but I mostly read non-fiction and I'm a bit of an amateur history buff. Last time I read a fiction book I was left feeling like I was preached to by an alien about how life doesn't really matter (sci-fi authors will often do that). The state of literature is pretty dire.
Just make your own tree of material to read. You should have a couple dozen writers/journalists you admire, look at who these people read then start reading those people, then you repeat the cycle.
Don't waste your time reading anything new, most new things are bad. Most ideas we struggle with, are ideas we have been discussing since the written record was invented out of necessity.
Anything new worth reading will assuredly make your way to you if you are at all connected.
Try to think a little more critically here. If you can't trust the opinion of people you supposedly like, already established in their craft, who can you trust?
Have no idea why you think this would increase influencer culture, but thanks for telling us all publicly how you interact with social media: in an sloppy uncritical way.
My advice for you is to pull the plug and read books that are older than 125 years.
> Have no idea why you think this would increase influencer culture, but thanks for telling us all publicly how you interact with social media: in an sloppy uncritical way.
This is a personal attack that is unsubstantiated by what I wrote, read the guidelines and follow them or go elsewhere.
Reading trusted authors is likely to be valuable, but they may devalue over time. We don't know if our chosen authors maximize our value, nor whether exploratory reading does, etc.
https://en.wikipedia.org/wiki/Exploration%E2%80%93exploitati...
100%. We're producing more content, faster, than ever before but ... most of it is just click-producing garbage that won't stand the test of time.
The problem here is that the volume of low-mid content is making it harder to find the best content.
Because the information in the post could be valuable regardless of human or LLM involvement.
I treat it the same way I treat human writing: by speed reading most of the article so I can find the points the author is trying to make and decide whether I should read the entire thing.
On one hand I'm like, yeah fair enough it needed writing and something is better than nothing.
On the other I know nobody wants to read it now because it's just word vomit rather than how a human would write something they'd like another human to read.
I hate it so much.
One person was arguing that they need llm because english isn't their first language and then it helps them write better and be understood. I was incapable of reading their (extremely long) email of arguments; I tried but my mind just went elsewhere as my eyes were moving through the lines.
At the very end there was a disclaimer that llm had been used to "aid" in writing that very email.
Poor guy thinks he's communicating better but all he's doing is making his emails completely unreadable. It's a sad state of affairs.
However most likely they just don't understand what good communication looks like, LLMs are perfectly capable of turning anything into clear concise communication, in fact an easy tell that something is LLM written is that it's just too precise and clear, humans are much more rambling.
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 course professor?
Of course there are writing as: "Hey ChatGPT write me a piece around coding with LLMs" and yeah, those are not worth reading.
But most of the writing is usually, these are the ideas, this is how the idea are structured together, now let's review them and then let's get a nice prose out of it.
It often makes them less informative and a lot less sincere.
I know lots of AI-enabled writers believe this, but I've never actually seen it be true.
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 effort in thinking it up yourself.
Why is that? Is it because you think there is inherent value in the sentence you transcribed, in spite of the near zero effort you spent creating it? If you think anybody here should read it, then you have undermined your own point. If you don’t think anybody should read it, then you shouldn’t post it.
If the spouses-to-be at a marriage ceremony say "I do", would you denounce them as frauds because they heard it before? Hopefully not.
If we go with your interpretation instead, then sm-silversight simply misread the comment they replied to and their post doesn't follow. No one doubted OP felt sincere about not wanting to read AI.
I mean, how can you say that he didn't think it himself? I thought this same thing and realised apparently I'm not the first. You have no idea how many of my blog posts ideas have come in HN first before I could publish. People can have the same thoughts. And have em all the time as well.
Psss.. See how @sm-silversight who commented on your post said the same thing I did? That's realtime example right there.
Coming back to the topic at hand. I agree with the OP. If you don't care to write it, why should anyone read it? AI has good usecases. But am not sure writing is one.
Writing is not just about the end result. It's also about the thought process. I learn about the topic more as I write. I correct my incorrect understandings as I write. When am pissed, my article has a different tone. Am rude, too direct. When am content/happy, different one. All of this is sterilised into something robotic where the author won't even remember what he/she wrote? What's the to like? For brownie points?
You are a senior software architect, you "prompt" 10 junior architects to write a software architecture proposal and then pick one which you send the client.
Would you say it's worthless, because the senior architect didn't care to write it?
There are plenty of industries where "taste" is a real job.
Or for some reason prompting a LLM and forwarding it's output is different than prompting a human and forwarding the output.
Lemme ask you a counter question, the senior architect writes the proposal and the junior writes it. Which one do you think client likes better?
Moreover, Your focus is on the end-result. Sure, in corporate environment, most people don't care about what they do as long as the end results checks some boxes. That wasn't the discussion here. The discussion is about writing and reading in general. Whether it's worth my time or not if you don't mean (forget mean, don't even remember) what you wrote.
Also, in your own example, the client don't care as well. As long the client's checks all the boxes his/her/their manager said should satisfy. Nobody really gives a damn about the quality.
Also, are you saying you'll be fine paying for Financial Times, WSJ and NYTimes KNOWING all they do is shove the story through an LLM? Neither will there be a soul, nor will there be any material effect on people who reads it.
> Or you think that for some reason prompting a LLM and forwarding it's output after vetting is different than prompting a human and forwarding the output after vetting.
There is difference no? I forward the output to get good feedback and correction from someone BETTER. And there is a process involved in it which showcases the "TASTE" you mentioned from the person whom you are forwarding your output to be vetted and that person comes up to you with feedback. And guess what? You learn from the person's feedback. You don't go back again and again forever to learn the same thing. That's exactly what am trying to point out.
Maybe I just want the news.
> nor will there be any material effect on people who reads it.
This is a ridiculous thing to say - "because the Weather app in my phone is 100% automated with no human "soul" in it, I will not take it into account into how should I dress today"
> the client don't care as well
This applies here too. If you didn't pay for author's output, are not a subscriber to their Substack, why should they bother to hand craft you a quality human written post?
> If you didn't bother to write it, I won't bother to read it
So the argument is that effort should be somehow matched. Ok, let's go with that. It's well know that writing something takes 10x more effort than reading it. So if we use the market argument, if it takes you 10 min to read a blog post, the author should spend 1 min writing it, because writing is 10x more intense, and this is only possible with a LLM. You might say "but there is one author, and 1000 readers". That gets us back to the paying argument.
Because the same sentence has been repeated practically word-for-word ad nauseam all over social media for years. What do you think is plausible - that they repeated something that is damn near omnipresent in the discourse, or that they never saw any of the many, many times it has come up and independently came up with the exact same formulation? They are perfectly able to step in and claim that it was their original thought if they want to.
Both are fully possible.
We're talking about a simple sentence that sounds a lot like something a primary school teacher or parent of young children would say. "If you won't do/don't/haven't done X, why should I Y?" is very normal moral/ethical phrasing.
I suppose I heard someone say it before I spelled it out in that way, but I am pretty confident I would ultimately have used a sufficiently similar expression, because I have been on the receiving end of the problem.
And that is putting aside the communicative compression of aphorisms. People don't use shared aphorisms to avoid ever doing the thinking themselves; they use them to shorthand more complex arguments for a listener who has already heard them. They are shared macros for agreed concepts. (Using them correctly requires having done the thinking they package up at least once).
That's more or less the same thing expressed more nihilistically. But nihilism is, like, just a word man (to 'The Dude' it up a bit). Perhaps we are either fiddling on the deck of the Titanic, or just staring at the waves?
What do you think the results will be of the machines consuming only their own slop and Habsburging themselves intellectually, and then all the humans abandoning any attempt to either talk or listen? As a global civilization of humans? I'm not sure we've explored the likely consequences of 'if you can't spend them time to write it why should anyone read it'.
Maybe it's gone too far already.
That is completely different from generating words that are not an expression of your thoughts or at the very best take some concise thoughts from the prompt and stretch them into a lengthy word soup.
Of course there are people who just parrot other people's thoughts without understanding them. That's closer to using an LLM. But you can often see how well someone understands something and how much reasoning of their own they put into it through their writing. And for the writer writing is a very good way to reflect on their own thoughts and to get them into order. Proper writing is thinking.
But this is what people said about the printing press. And the internet. Less effort to spread the memes. Has it been a net negative? Maybe in some respects. Can you stop it? Probably not.
Im sorry for you. It must be hard to detach yourself with a fixation. I also cant help but spend my attention spotting where the magician is hiding the coin instead of trying to enjoy the show
> If you can't spend the time to write it, why should anyone read it?
Most people in these threads repeat this question. As if pre-ai all writing was from deep thinkers full of genuine intention.
As a result, when I see an AI wall of text I just don’t bother reading it and DM the submitter asking what it’s about.
I don't think writing it is the whole process, research could be 10 or 100x longer.
Couple weeks ago I had someone linking to a doc page in my ticket "Made this summary, hope it helps". It was 100% AI generated, the person clearly had no understanding of the problem, it only mentioned UI changes although the thing required changes in many systems. Complete waste of time, I don't think I will humor anyone who makes AI summaries anymore.
another iteresting thing models can do is to highlight and notice themes and motifs in a piece. I find that helpful when thinking about a piece of work. Might be obvious ones, sometimes it can be subtle themes. Good for stirring your own brain.
In the extreme these can be annoying, but more often I find them kinda charming, as an expression of the author's personality.
This is what you need to know. Seriously, after 25 years in news (writing), you realize that you need “second eyes”, not the first hands.
When most people are consuming _their_ news (as opposed to _the_ news) in the form of a thumbnail in an algorithmic social media feed, those copy errors matter less.
"Those rethinks are load-bearing parts of your voice. Readers won’t put their fingers on what’s wrong, but they’ll sense that you’ve become artificially-flavored."
The metaphor at the start is AI-like weirdness too: "without pasteurizing and jacking it with corn syrup." Pasteurising is good, corn syrup is bad - what the heck am I supposed to make of it? It's nonsense.
It may even have been handwritten by the author, but it's slop nonetheless.
You may be telling yourself that you're disciplined and you're just using the LLMs for review. But while you're reading their output, the slop makes its way directly into your brain anyway - and then it drips out into your writing.
I'm personally furious that "load-bearing" has become an LLM tell, it's a really useful metaphor!
Pasteurising something is making it sterile. Safer, but bland and not as interesting. I guess that’s the intended metaphor.
TLDR: Don’t.
They can even retrieve articles you link to and check that you aren't misrepresenting them.
But the 50% I do take into account, improves the text! And, like TFA, I never ask it for concrete text. It only helps me diagnose the issues, I prescribe the medicine!
For instance, if I said the grass is green vs if I said the grass looks nice vs if I said the grass is doing well and looks how it should vs if I said in my opinion the grass is healthier than its ever been.
- Establish a single thesis an external reviewer could recover from the diff.
- Unify vocabulary across code, comments, tests, and commit message.
- Use the same vocabulary consistently to refer to the same concepts.
- Keep every hunk that serves the thesis; consider the removal or deferral of the rest.
- Introduce abstractions at the point of need.
- Align tests to narrate the same story as the implementation.
- Reconcile the commit message and the diff.
- Order changes expositorily, not chronologically.
- Explain what the change does and why. Do not explain the details of the development process.
- Prefer to edit subtractively.
- Recompile and run all relevant tests after edits.
- Iterate.
This makes Rule 1 straightforward ("You may not use a single word an LLM suggests to you") and helps avoid the horrible feeling that the machine is taking over your personal voice.
LLMs have absolutely terrible taste when it comes to writing. I don't find their feedback useful at all, beyond trivial spelling/grammar mistakes, which you don't really need an LLM for in the first place.
Proofreading is all you need.
Edit: I do sometimes ask an LLM for a fact-check, though.
In general use today, AI primarily functions as a stupidity amplifier: it empowers dumb people to do dumb things more pervasively, with less effort, and at unprecedented scale.
We're moving into an era of artificially enhanced stupidity.
The models are good at pointing out basic syntax issues that slip past spell checkers. But here's how you can get a comparable result: just let it stew. Grab lunch, walk in the park, re-read your article. You'll be surprised.
As noted in the article, style recommendations from an LLM are almost always bad. The advice in the article is sound, but to follow it, you need to know how good writing looks like. So you still need to read a style guide or two. I'm sure the author did.
The most promising use of LLMs is to have them criticize your high-level argument, but they struggle with that. I think it has to do with the training. They're desperate to please and it's difficult to get them to say "this idea sucks". You can explicitly prompt them to be brutal, but the result is often over-the-top. You can present them with the article without mentioning its yours, then ask them to write a polemic. That can work, but it's not a streamlined approach.
OTOH, an AI could not have qualified as such a student. But even if it did, before we began I would certainly bargain for considerably more than work-study tutoring paid.
Using adversarial models to evolve ideas. I have a whole novel of material, and the feedback has indeed been useful. But the actual novel? Not even AI models like their own writing once you give the simple prompt of "account for model sycophancy".
The resulting structure and plot beats are good with AI as copy editor. Only the least discerning reader might not care or notice the actual non-human writing. And hey - maybe those are your readers. Probably not.
Can we all appreciate for a moment the sci- dystopia which snuck up on us all? I just used to phrase: " non-human writing". 50 years ago, that would send a chill up your spine.
I have a specific ChatGPT chat that rewrites my posts really well every time; I usually just give it a rough draft and let it clean things up. But it was pretty interesting to realize how good these LLMs are at actually finding mistakes rather than just rewriting things. The point about not letting the model influence your voice was also very, very relevant.
I’m thinking that people that get years semi-colon and colon filled paragraphs are going to believe this is a normal and good way to write on their own.
Don’t
Context isn't an issue. It's style.
The argument the author is making is that if you use an LLM to write for you, you end up with a homogeneous work that's just like everything else.
In journalism, that's sort of what you want.
In novels/function, that's the opposite of what you want.
However, there's degrees to these things. If you're looking at a sentence you wrote, thinking there's something "off" it can be helpful to have the LLM rewrite it just to see how it thinks it could be better worded.
I've done this a few times and I do find it helpful. Just like the author, I never just accept what it gives me. I simply use it as an OK-ish copyeditor that's good at spotting issues and suggesting solutions.
Why is this?
Why couldn’t whatever went into post-training these voice models be applied to the text-gen models to get rid of AI smells?
Could we set up a pipeline that leverages the voice models to clean up text that reeks of AI ?
I have but it was a house construction worker explaining its practice on youtube.
If not, it does risk planting the seed of doubt - have I been duped once again into reading tokenslop again?
Risky move. Surprised the LLM copy editor didn’t flag it.
[0] https://x.com/search?q=%22load%20bearing%22%20until%3A2020-0...