Live data from Hacker News

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

marcusolang.substack.com

251–260 of 533 posts

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

#251
Actors have known this for decades: self-expression isn’t only a stage problem. It’s a life problem. Most people fail to express themselves on an hourly basis. Being good at expressing yourself is unnatural. Having clarity of what “yourself” even is is unnatural. The truth is that we’re all making comments, jokes, deciding what’s important and what not using old programming in our brains… programming that was given to us by our childhood and our education. Very few people can consistently have the luxury of being/ability to be creative with that old programming, and even those that can often have to plan ahead of time/rigidly control the environment in order to achieve a creative result.

The exact same problem exists with writing. In fact, this problem seems to exist across all fields: science, for example, is filled with people who have never done a groundbreaking study, presented a new idea, or solved an unsolved problem. These people and their jobs are so common that the education system orients itself to teach to them rather than anyone else. In the same way, an education in literature focused on the more likely traits you’ll need to get a job: hitting deadlines, following the expected story structure, etc etc.

Having confined ourselves to a tiny little box, can we really be surprised that we’re so easy to imitate?

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

#252

Earlier quoted context omitted.

They are probably like me: if punctuation isn't on my keyboard, I don't use it.

Yeah, this is what I don't understand, surely people aren't "using" em dashes deliberately. I assumed MS word was just inserting them automatically when the user used a minus symbol between two words. Kind of like angled quotes.

I've been using em dashes for much longer than transformers have existed. It's easily accessible on at least the Android and macOS keyboards.

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

#253

Always interesting (in an informative way) to see people "defending" em-dashes from my personal perspective. Before you get mad, let me explain: before ChatGPT, I only ever saw em-dashes when MS Word would sometimes turn a dash into a "longer dash" as I always thought of it. I have NEVER typed an em-dash, and I don't know how to do it on Windows or Android. I actually remember having issues with running a program tha…

I actually got punked during a demo because I wrote some terminal commands and stored them in the macOS notepad and didnt notice it had changed -- to —.

When I copy and pasted them in it failed obviously so... yeah. If you have terminal commands that use `--` don't copy+paste them out of notepad.

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

#254

Always interesting (in an informative way) to see people "defending" em-dashes from my personal perspective. Before you get mad, let me explain: before ChatGPT, I only ever saw em-dashes when MS Word would sometimes turn a dash into a "longer dash" as I always thought of it. I have NEVER typed an em-dash, and I don't know how to do it on Windows or Android. I actually remember having issues with running a program tha…

Maybe I'm weird, but one of the first things I've always done when setting up emacs is to enable Typo mode (or Typopunct) for writing modes, which handles typing en and em dashes and "smart" quotation marks in a fairly natural way.

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

#255

Earlier quoted context omitted.

Are Kenyans really taught to write that way? I’m highly skeptical. At one point the author tries to argue this local pedagogy is downstream of “The Queen’s English” & British imperial tradition, but modern LLM-speak is a couple orders of magnitude closer in the vector space to LinkedIn clout-chasing than anything from that world.

Yes they are, or rather, we were when I was in primary school. My essays (we called them composition) were filled with these these red check marks for every esoteric word, proverb, metaphor or simile you used. The more you had the higher you'd score. So I did my homework with a dictionary open. I remember writing some document at work in the US and everyone commenting on how Queen's English it was. This was before Ch…

Sure, I believe that completely. But that's not how ChatGPT writes!

Here are some random examples from one of the (at least) half-dozen LLM-co-written posts that rose high on the front page over the weekend:

https://blog.canoozie.net/disks-lie-building-a-wal-that-actu...

You write a record to disk before applying it to your in-memory state. If you crash, you replay the log and recover. Done. Except your disk is lying to you.

This is why people who've lost data in production are paranoid about durability. And rightfully so.

Why this matters: Hardware bit flips happen. Disk firmware corrupts data. Memory busses misbehave. And here's the kicker: None of these trigger an error flag.

Together, they mean: "I know this is slower. I also know I actually care about durability."

This creates an ordering guarantee without context switches. Both writes complete before we return control to the application. No race conditions. No reordering.

... I only got about halfway through. This is just phrasing, forget about the clickbaity noun-phrase subheads or random boldface.

None of these are representative (I hope!) of the kind of "sophisticated" writing meant to reinforce class distinctions or whatever. It's just blech LinkedIn-speak.

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

#256
post #236

Earlier quoted context omitted.

Why can't the LLM refrain from improving a sentence that's already really good? Sometimes I wish the LLM would just tell me, "You asked me to improve this sentence, but it's already great and I don't see anything to change. Any 'improvement' would actually make it worse. Are you sure you want to continue?"

> Why can't the LLM refrain from improving a sentence that's already really good? Because you told it to improve it. Modern LLMs are trained to follow instructions unquestioningly, they will never tell you "you told me to do X but I don't think I should", they'll just do it even if it's unnecessary. If you want the LLM to avoid making changes that it thinks are unnecessary, you need to explicitly give it the option t…

That may be what most or all current LLMs do by default, but it isn't self-evident that it's what LLMs inherently must do.

A reasonable human, given the same task, wouldn't just make arbitrary changes to an already-well-composed sentence with no identified typos and hope for the best. They would clarify that the sentence is already generally high-quality, then ask probing questions about any perceived issues and the context in and ends to which it must become "better".

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

#257

It's pretty rude to "accuse" someone of using AI. Would you yell "Dictionary!", "Grammarly!", "Reference manual!", "Newspaper quote!" at them? Maybe "Harvard!" or "Tutored!" ? You don't know who they are or what their life is like. Maybe they're blind and using it as an assisted device. Maybe their hand is injured and they use it to output information faster. Maybe they're old, infirm, a non-native English speaker, e…

> Let's say you happen to be lucky, don't accuse someone unfairly, and they are using ChatGPT to write what they said. Who cares?!

People who want to read thoughts of other people and not meaningless slop.

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

#258
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…

I have two kids in high school. It's frustrating to me that the teachers spend so much of their time encouraging kids to make their writing more interesting, and less direct, and padded to meet word length criteria. They'll then spend the first few years of their career unlearning this and attempting to write as directly and clearly as possible with as few words as possible.

I can’t guess how old they are but there is some sense in doing that if you think about it like math exercises. It makes for terrible prose but the only way to get the ability to write more complicated sentences is to practice writing them, even when they are not necessary.

The problem is that teachers stop pushing complexity for complexity’s sake way to late.

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

#259
I have a degree in Journalism and now work in customer support. Occasionally, people accuse me of being an AI because of my writing style.

Thankfully, no one I report to internally wants me to simplify my English to prevent LLM accusations. The work I do requires deliberate use of language.

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

#260

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.

I do have an em dash key on the keyboard on my phone :)
Post reply on HN