Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

marcusolang.substack.com

Post reply on HN
Print view View original

201–210 of 533 posts

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

#201

Post by Kim_Bruning »

zdragnar wrote: post #192
Kim_Bruning wrote: post #158

Earlier quoted context omitted.

Depends what you ask the LLM to do! If you're using it to write in programming language, you often actually get something that runs (provided your specifications are good - or your instructions for writing the specifications are specific enough!) . If you're asking for natural language output ... yeah... you need to watch it like a hawk by hand - sure. It'd be nice if there was some way to test-suite natural language…

The last time I asked it to write something in a programming language, it put together a class that seemed reasonable at first blush, but after review found it did not do what it was supposed to do. The tests were even worse. They exercised the code, tossed the result, then essentially asserted that true was equal to true. When I told it what was wrong and how to fix it, it instead introduced some superfluous public…

Yeah, people have wildly different experiences.

I think it depends on what models you are using and what you're asking them to do, and whether that's actually inside their technical abilities. There are not always good manuals for this.

My last experience: I asked claude to code-read for me, and it dug out some really obscure bugs in old Siemens Structured Text source code .

A friend's last experience: they had an agent write an entire Christmas-themed adventure game from scratch (that ran perfectly).

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

#202

Post by notahacker »

elcapitan wrote: post #9

Ironically, mistakes and idiosyncrasies are becoming a sign of authenticity and trustworthiness, while polish and quality signal the opposite. Earlier today I stumbled upon a blog post that started with a sentence that was obviously written by someone with a slavic background (most writers from other language families create certain grammatical patterns when writing in another language, e.g. German is also quite typi…

To an extent this has always been the case (this kid has clearly made a strong attempt at following some quite basic instructions, versus this kid's answer is - perhaps literally - textbook).

But yeah, I definitely find mild grammatical quirks expected from English as a foreign language speakers a positive these days, because the writing appears to reflects their actual thoughts and actual fluency.

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

#203

Post by leoc »

nitwit005 wrote: post #193

This is also happening to artists, people who make YouTube shorts, and similar. Everyone gets accused of being AI if the feel happens to match. I'm sure there's some voice actor out there who can't get work because they sound too similar to the generated voices that appear in TikTok videos.

I doubt it’s affecting his work, but my impression is that if anyone is owed money from the use of their personal likeness in AI image generators (as a source for generic figures, not as someone specifically requested by the prompt) then Pierce Brosnan is likely near the front of the queue.

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

#204

Post by hyghjiyhu »

gowld wrote: post #189
tptacek wrote: post #187

Earlier quoted context omitted.

GPT writing uses varied sentence lengths, deliberate rhythm, lots of full breaks, and few needless words. It also tends to read as if intended for a William Shatner performance. I don't think the annoying bits about GPT's writing are structural. It probably writes technically better than most of us do in our second drafts.

Are you saying that needless sentences don't count as needless words? As GPT would say, "You've hit upon a crucial point underlying the entire situtation!"

I think that's a great sentence to include... you know, provided it's actually true.

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

#205

Post by KeplerBoy »

Tepix wrote: post #54
mort96 wrote: post #34

Earlier quoted context omitted.

> I even checked one of his responses in WhatsApp if it's AI by asking the Meta AI whether it's AI written, and Meta AI also agreed that it's AI written I will never understand why some people apparently think asking a chat bot whether text was written by a chat bot is a reasonable approach to determining whether text was written by a chat bot.

Well, case in point: If you ask an AI to grade an essay, it will grade the essay highest that it wrote itself.

Pangram seems to disagree. Not sure how they do it, but their system reliably detected AI in my tests.

https://www.pangram.com/blog/pangram-predicts-21-of-iclr-rev...

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

#206

Post by MarkusQ »

stackghost wrote: post #191
bookworm123 wrote: post #169

Earlier quoted context omitted.

Genuine question, what would you write instead of "proceeded to"? To me, as a non native English speaker, it seems reasonable to use this expression, and it would not even stick out to me tbh

You can usually use "then" or "went". >I proceeded to open the fridge >I went to open the fridge or >I proceeded to flush the toilet >I then flushed the toilet There's nothing wrong with "proceeded", it's just one of those things that's overused by bad writers.

"Went" is a powerful word. With suitable helpers it can replace "proceeded", as you demonstrated, "attended" ("I went to a good school") as well as "became" ("On hearing this, Joe went all silent") or "said" ("So then she went 'Dude!' and we all laughed") and hundreds of other words.

Only a handful of words ("got", "y'know" and "fuck") rival its versatility.

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

#207

Post by Y_Y »

0xbadcafebee wrote: post #146
rukshn wrote: post #28

I had a similar experience. We were talking about a colleague for using ChatGPT in our WhatsApp group chat to sound smart and coming up with interesting points. The talk sounds so mechanical and sounds exactly as ChatGPT. His responses in Zoom Calls were the same mechanical and sounds like AI generated. I even checked one of his responses in WhatsApp if it's AI by asking the Meta AI whether it's AI written, and Meta…

> We were talking about a colleague for using ChatGPT in our WhatsApp group chat to sound smart and coming up with interesting points. How dare they.

You're expected to infer that it wasn't working.

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

#208

Post by unsupp0rted »

xboxnolifes wrote: post #183
valbaca wrote: post #171

Earlier quoted context omitted.

> I proceeded to do the work. > I did the work. > I worked.

Each one of these has slightly different readings in my eyes.

Not different enough to make it worth using anything but the simplest one.

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

#209

Post by hyghjiyhu »

xboxnolifes wrote: post #183
valbaca wrote: post #171

Earlier quoted context omitted.

> I proceeded to do the work. > I did the work. > I worked.

Each one of these has slightly different readings in my eyes.

Unlike the last variant, the first two imply there was some quantity of work and it was all completed.

I don't really see the difference between the two though.

Post reply on HN