Live data from Hacker News

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

marcusolang.substack.com

521–530 of 533 posts

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

#521
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…

Are you an English speaking American? Because being a native English speaker and actually being English, or from a former English colony will differ. I'd characterise Americans as less pretentious and more straight talking. This kind flowery language is typical (or symptomatic depending on diagnosis) of how English people actually used to speak and write. The average English vocabulary has dwindled noticeably in my l…

Maybe so, but it was my time at a British university in the late-nineties that taught me how to write simply and precisely. Maybe I'd been infected (as described in sibling comments) with American "Business English"?

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

#522
post #280

Earlier quoted context omitted.

> These things are spoken entirely differently than — and on the page, they read entirely differently to — regular parenthetical-bearing sentences. > No, seriously, compare/contrast: "these things are spoken entirely differently than (and on the page, they read entirely differently to) regular parenthetical-bearing sentences." Those are spoken the same way, they read the same way, and they mean the same thing.

Is this maybe a thing like how only designers are aware of kerning? These read / sound very different to me, and to everyone I've brought up the subject with (who admittedly are in a certain bubble of people who either write professionally, or "do things" with their voices, or both.) • The length of the verbal pause is different. (It's hard to quantify this, as it's relative to your speaking rate, which can fluctuate…

In a previous life I was an English major, and (more important to the subject at hand, I think) a professional actor / voice actor. I endorse everything you say - including that it's maybe like the kerning issue. I damn sure, though, that the people who don't see it on the page would feel the difference were it spoken as written. (Which, ask a designer, is also like kerning - or so they say!)

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

#523

Earlier quoted context omitted.

It's a matter of degree. You're right, of course, but there was a time not so long ago when such things were ubiquitous - even on the internet. Once upon a time, even the darkest corners like 4chan were actually kind of tongue-in-cheek. Then it slowly dawned on everyone that there were a bunch of people there who weren't kidding, and things kind of went to pot. In a reversal of the aphorism; those were more complex t…

> Once upon a time, even the darkest corners like 4chan were actually kind of tongue-in-cheek. I distinctly remember both the invention of q-anon and the idea of Trump as a presidential candidate happening on 4chan as a we're-all-in-on-it joke, until true believers started showing up and thinking we believed too. Not a joke anymore...

> I distinctly remember both the invention of q-anon and the idea of Trump as a presidential candidate happening on 4chan as a we're-all-in-on-it joke

4chan was created in 2003. Trump's first bid for the Presidency was an attempt at the Reform Party nomination dropped early in the primary season—in 2000, the one cycle when that party had access to federal matching funds but wasn't effectively a vehicle for H. Ross Perot. Another Trump bid was a recurring topic of discussion in serious, if speculative, contexts ever since (and, for that matter, the idea of a Trump presidential run had been even before the first bid, back to the 1980s, as I recall.) It certainly is not an idea that first emerged as a 4chan joke.

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

#524
post #469

Earlier quoted context omitted.

> English is hard, even for native speakers. But it's also wonderful! English loves to steal words from other languages, and good writers love to choose the right word. It's like having an expansive wardrobe and picking just the right outfit for every event. Very true. Take this passage: ‘I am called Strider,’ he said in a low voice. ‘I am very pleased to meet you, Master – Underhill, if old Butterbur got your name r…

A very different book that would have been! Where can I read more?

His son Christopher spent his whole life editing and organising all his father's unfinished works.

The bulk of that was the History of Middle Earth of which a few volumes cover LoTR.

https://en.wikipedia.org/wiki/The_History_of_The_Lord_of_the...

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

#525

Earlier quoted context omitted.

Maybe for writing, but in digital art circles if anyone notices a mistake in your lines or perspective or any kind of technical error you will get the anti-AI cancel mob after you even if you didn’t use generative AI at all. I would not want to be an artist in the current environment, it’s total chaos.

Social media artists appear to be bucket crabs. If any of them succeed, the remainder express reactor-grade envy and attempt to tear them down. Perhaps it's the relative poverty and the low stakes of the field that drive it to this end.

That's also why they're the ones who are most vehemently opposed AI art. The algorithm only cares for content, not the artistry they add to their images.

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

#526

Earlier quoted context omitted.

It’s not even really a problem of the Internet necessarily; it’s rather a symptom of the growing political divide in Western society. Things are “simple” now because we’ve reached the point where nuanced discussion is pointless. In Europe you can be jailed for going against the Accepted Opinions™, and we’re seeing a rise in politically motivated attacks. There is no logical solution to emotionally backed rhetoric lik…

Who are the Turtle Island terrorists? I only know of four people accused of attempting to build a bomb, but not actually having done so. Surely you aren't taking a government at its word on a politically charged case? Need we trudge out the Chicago 7 again?

By their own words they were going to commit terrorism. That, logically, makes them terrorists. They were found, on film, to be making and experimenting with illegal explosives, and they were found to own even more materials. If you have trustworthy evidence that this is all fabrication—evidence that doesn’t exist in your mind—then I’d be more than happy to see it.

And if you’re saying all of this because you agree with them and their actions, at least have the courage to state you support terrorism directly.

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

#527

Earlier quoted context omitted.

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.

This is like complaining that they teach the Bohr model in science classes until they reach chemistry. The ideas, concepts and expectations can be refined after you've learned the foundational knowledge, skills and history required to do so. A lot of "why do we do things like that" questions students will naturally have can be answered with "because we used to do things like this /we need to avoid things like this /e…

Keeping outdated models in the curriculum needs to be addressed on a case-by-case basis. Some of them are detrimental to the learning process and should be relegated to a history of science class—skip directly to current understanding; others are useful because they're developmentally appropriate for younger students. Someone who has a background in science pedagogy would be the proper person to make that decision for the Bohr model.

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

#528

Earlier quoted context omitted.

> Once upon a time, even the darkest corners like 4chan were actually kind of tongue-in-cheek. I distinctly remember both the invention of q-anon and the idea of Trump as a presidential candidate happening on 4chan as a we're-all-in-on-it joke, until true believers started showing up and thinking we believed too. Not a joke anymore...

> I distinctly remember both the invention of q-anon and the idea of Trump as a presidential candidate happening on 4chan as a we're-all-in-on-it joke 4chan was created in 2003. Trump's first bid for the Presidency was an attempt at the Reform Party nomination dropped early in the primary season—in 2000, the one cycle when that party had access to federal matching funds but wasn't effectively a vehicle for H. Ross Pe…

Trump running wasn't a 4chan joke, but support of him was.

Also, thank you for encouraging me to read the Wikipedia article https://en.wikipedia.org/wiki/2000_Reform_Party_presidential....

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

#530

Earlier quoted context omitted.

> That doesn't work, they beat it so hard into ChatGPT I don't think you're able to set either the developer or system prompt on ChatGPT, you're gonna have to use the OpenAPI (or something else) to be able to set that. Once you have access to setting text in those, you can better steer how the responses are.

ChatGPT has personalization settings that you can use to set part of the system prompt. Other chatbots usually have this too. How much they follow it depends. Sometimes they know you wrote it and sometimes they don't. Claude in particular likes to complain to me its system prompt is poorly written, which it is.

> ChatGPT has personalization settings that you can use to set part of the system prompt

That's not true, which field do you believe this to be? Because all of the fields I currently see in ChatGPT do have an effect on your conversations, but they're not just raw injections into system/developer prompts, it's something else.

Try using the API with proper system/developer prompts, then copy-paste that exact same thing into ChatGPT's "personalization settings" and try to have the same conversation, and you'll get direct evidence that it isn't actually the system prompts, but they're injected somewhere into the conversation.

Post reply on HN