Live data from Hacker News

I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me

marcusolang.substack.com

371–380 of 533 posts

Re: I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me

#371

I was just reading the 1897 style guide of the City News Bureau (Chicago), in the book "Hello, Sweetheart, Get Me Rewrite!". Some highlights: - Do not confuse 'night' with 'evening'. - This office spells it 'programme'. - Hotels are 'kept', not 'run'. - Dead men do not leave 'wives', but they may leave 'widows'. - 'Very' is a word often used without discrimination. It is not difficult to express the same meaning when…

Americans have no idea what evening is. It's always night for them.

Re: I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me

#372
post #269

Earlier quoted context omitted.

Right, it is currently incapable of providing a straight answer without clearing it's throat selling the answer. It reminds me of those recipe blogs that just can't get to the fucking recipe. It's bad writing! But it's not bad technically, in a style-guide kind of way.

Sometimes I wonder if the throat-clearing is an indispensable part of getting to the "good bits" that follow. Like, do those extra tokens give it more "room to think" even if they're basically meaningless in themselves?

The output tokens are the only information that is carried forward through each inference pass, so "more room to think" is incompatible with "basically meaningless". Perhaps one could imagine it somehow stenographically encoding information in its precise choice of meaningless throat clearing, but there are only so many variations on that theme - word choice is heavily constrained, so it doesn't feel like you could store a whole lot of information there without it starting to read froopiliciously.

Re: I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me

#373
post #80

> There were unspoken rules, commandments passed down from teacher to student, year after year. The first commandment? Thou shalt begin with a proverb or a powerful opening statement. “Haste makes waste,” we would write, before launching into a tale about rushing to the market and forgetting the money. The second? Thou shalt demonstrate a wide vocabulary. You didn’t just ‘walk’; you ‘strode purposefully’, ‘trudged we…

Our legal systems are based around being concise and succinct, relevant, and objectively unbiased. I was raised to be respectful by "getting to the point, afap" to avoid wasting anybody's time. But I've noticed that mostly only the members of the science and legal community exercising similar principles.

> Our legal systems are based around being concise and succinct

That's a good one. Got any more?

Re: I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me

#374
In russian there is a saying that translates "try to prove that you are not a camel" which describes the impossibility of proving what is obviously not true to an unwilling and/or obtuse party.

According to russian language wikipedia (https://ru.wikipedia.org/wiki/%D0%94%D0%BE%D0%BA%D0%B0%D0%B7...) the original tale go out to famous Persian poet Rumi from XII century, which just makes me tickled pink about how awesome language is.

Re: I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me

#375
post #244

Earlier quoted context omitted.

It certainly over uses some techniques which might be valid in smaller doses, like negation. Not negation with some clarifying point to it MASSIVE EM DASH but negation as a rhetorical trick to use fifteen words instead of five and add a veneer of profundity to something utterly banal. It doesn't just use it one time per paragraph, but three. These aren't particularly long or convoluted sentences; they just could easi…

> MASSIVE EM DASH Tangent: the thing I find most annoying about ChatGPT's use of em-dashes is that it never even uses them for the one thing they're best suited for. ChatGPT's em-dashes could almost always be replaced with a colon or a comma. But the true non-redundant-syntax use of em-dashes in English prose, is in the embedding into a sentence of self-interruptive 'joiner' sub-sentences that can themselves bear pun…

Personally, I do not see the distinction here between the two sentences, but your last paragraph got me thinking: should we be using parenthetical, self-interruptive clauses? When we are speaking extemporaneously, we may need them, but when writing, could we rearrange things so they are not needed?

One reason I came up with for doing so is to acknowledge a caveat or answer a question that the author anticipates will enter a typical reader's mind at that point in the narrative.

If that is the case, then it seems to me that when an author does this, they are making use of their theory of mind, anticipating what the reader may be thinking as they read, and acknowledging that it will likely differ from what they, as the author, is thinking of (and knows about the topic) at that point.

If this makes any sense, then we might ask if at least a rudimentary theory of mind is needed to effectively use parenthetical clauses, or can it be faked through the rote application of empirically-learned style rules? LLMs have shown they can do the latter, but excessive use might be signalling a lack of understanding.

Re: I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me

#376

The author uses dash (-) not em dash (—), there is a big difference in that everyone has a dedicated dash/undersocore key on their keyboard, but nobody has a em dash key. You can use word processing software etc, but using em dash consistently throughout a text is very unnatural in casual written texts.

There is an easy shortcut for em dashes on macOS, Opt+Shift+-. This makes it really easy to use them, which I do all the time in casual settings (indeed, more often than in formal settings).

And a very easy shortcut in Vim: Ctrl+K M -

Re: I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me

#377

Earlier quoted context omitted.

Obsession with short sentences and generally pushing extreme simplicity of structure and word choice has been terrible for English prose. It’s not been terrible because most people aren’t aided by such guidance (most are) but because the same people who can’t be trusted to wield a quill without the bumper-lanes installed see a sentence longer than ten words, or a semicolon, or god forbid literate and appropriate nuan…

"He walked up to Helen and asked, 'What are you doing?'" "He strode up to Helen and asked, 'What are you doing?'" "He sidled up to Helen and asked, 'What are you doing?'" "He tromped up to Helen and asked, 'What are you doing?'" Each of those sentences conveys as slightly different action. You can almost imagine the person's face has a different expression in each version. Yes, I hate it when amateurs just search/rep…

Mark Twain on this subject:

> Well, also he will notice in the course of time, as his reading goes on, that the difference between the almost right word and the right word is really a large matter—’tis the difference between the lightning-bug and the lightning.

But also:

> Unconsciously he accustoms himself to writing short sentences as a rule. At times he may indulge himself with a long one, but he will make sure that there are no folds in it, no vaguenesses, no parenthetical interruptions of its view as a whole.

Re: I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me

#378

If you are "average", you will sound like an AI, because an AI is the average of its training data. I don't think it's only Kenyans; I've seen the same distinctive "dialect" from many others.

The "voice" of chatbots comes from the stuff after the main training, which is very different to the average human voice. Even the main training would give you something like "average on the internet" voice, which is quite different to the average human voice.

Re: I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me

#379
post #117

While author is correct in general, I would like to add a counter-point regarding em-dashes specifically. Yes, many people use them like this - and many website frameworks will automatically replace a keyboard not-really-a-minus symbol with em-dash. So that is not a sign of the LLM generated slop. What LLMs also do though, is use em-dashes like this (imagine that "--" is an em-dash here): "So, when you read my work--…

Tbh whether I use spaces around em dashes depends more on the font than anything. Some fonts have em dashes that are so long that putting spaces around them would be ridiculous.

Re: I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me

#380
post #80

> There were unspoken rules, commandments passed down from teacher to student, year after year. The first commandment? Thou shalt begin with a proverb or a powerful opening statement. “Haste makes waste,” we would write, before launching into a tale about rushing to the market and forgetting the money. The second? Thou shalt demonstrate a wide vocabulary. You didn’t just ‘walk’; you ‘strode purposefully’, ‘trudged we…

The article itself does an excellent job spelling out the background: > This style has a history, of course, a history far older than the microchip: It is a direct linguistic descendant of the British Empire. The English we were taught was not the fluid, evolving language of modern-day London or California, filled with slang and convenient abbreviations. It was the Queen's English, the language of the colonial admini…

Sometimes it's about matching the fashion of the group you aspire to be part of, sometimes it's about having that fashion imposed on you so you look "professional".

Security guards at tech company offices are the only ones who wear suits, presumably because it's a mandated uniform, not by choice.

Post reply on HN