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

Throwing AI-generated walls of text into conversations

noslopgrenade.com

Post reply on HN
Print view View original

361–370 of 453 posts

Re: Throwing AI-generated walls of text into conversations

#361

Post by bfivyvysj »

SchemaLoad wrote: post #303
Aurornis wrote: post #190

Earlier quoted context omitted.

> I don't really get why some people seem to think that it's somehow better to have their bullet point prompt as a huge text. Simple: It looks like you did more work. Before everyone had ChatGPT, a long document meant that someone sat at their computer and invested more effort than someone rattling off a list of partially formed bullet points. In the process of writing the doc they usually refined the idea. Now anyon…

But now I can use AI to summarise the wall of text back in to the original bullet points.

You even get a couple of new ones for free.

Re: Throwing AI-generated walls of text into conversations

#362

Post by dolebirchwood »

donatj wrote: post #20
SwiftyBug wrote: post #8

> Nobody writes essays in Slack I 100% write long texts in Slack. I always try to provide as much context as possible when reaching out to someone with a question or request.

Honestly, speaking as a friend, and as someone who's been at this a very long time, maybe stop doing that? It doesn't foster conversion and I personally find it kind of a hostile/disrespectful communication style. It's much harder to have a proper back and forth with a firehouse than it is a few sentences at a time. It declares authority "these are the facts" rather than "let's discuss ideas" and if you haven't fully…

> It's much harder to have a proper back and forth with a firehouse than it is a few sentences at a time.

Sometimes just providing the context about an issue is itself enough to warrant a few paragraphs, let alone a few sentences.

Obviously, it's best to express a problem, its options, and its recommended solution(s) in as few words as possible, but it's unwarranted to hold an absolute position that every discussion must be an inefficient exchange of mere sentences at a time.

I'd rather have an outline-style essay given to me in one go for me to digest and research async rather than be subjected to a barrage of back-and-forth pings. That's the real disrespect of other people's time.

Re: Throwing AI-generated walls of text into conversations

#363

Post by oliculipolicula »

hungryhobbit wrote: post #259

AI conversations are like dreams: everyone has one they like and wants to share it with others ... but no on gives a crap about your dream/chat session, because it was uniquely appealing to you , and not them. Don't bore your co-workers (or others) with descriptions of your dreams, and don't throw a computer's dreams (AI chat logs) at them either.

Dreams are usually predicated on info-dense stuff, like personality or prompts

https://www.nature.com/articles/s44271-026-00447-2

Re: Throwing AI-generated walls of text into conversations

#365

Post by boomlinde »

ineedasername wrote: post #337
nlawalker wrote: post #128

I've decided that I'm done being pissy about this kind of response, or thinking that it's something that can be coached away. I choose to look at it like any other cultural communication difference - something that you learn about, try to give some grace to, and work a little harder to bridge (unless you're defusing a bomb, performing surgery, flying an airplane etc.). In this person's communication culture, they are…

>In this person's communication culture, they are saying Wittgenstein termed precisely this sort of practice a “language game”. With the rest of his work (Philosophical Investigations in particular) it is a hugely useful lens through which to view and significantly better understand the use and function of language in all its forms. Given that language is becoming a ubiquitous UI and UX and glue for just about everyt…

A language game assumes mutually understood "rules" in the form of shared context that makes language that would otherwise be unclear meaningful. If the intended meaning is not conveyed, we're failing at playing a language game.

In this case, the notion that the slop grenade is intended to communicate "I don't know, but here's my attempt to help" is as far as we know entirely a fiction, possibly a favorable interpretation GP uses not to let themselves be annoyed. In reality, the intent could be any number of things or nothing in particular.

It seems more likely to me that these slop grenades are attempts at appearing to a third party to have weighed in on important decisions. It's a deliberate technique to become more visible in order to win favor with someone who can't tell reasoned responses from useless bullshit.

This self-aggrandizing trash was a normal part of professional culture before the current LLM sewage torrent, but tactlessly used LLMs are so awful at writing that it's never been so transparent before.

Re: Throwing AI-generated walls of text into conversations

#366

Post by protocolture »

hungryhobbit wrote: post #259

AI conversations are like dreams: everyone has one they like and wants to share it with others ... but no on gives a crap about your dream/chat session, because it was uniquely appealing to you , and not them. Don't bore your co-workers (or others) with descriptions of your dreams, and don't throw a computer's dreams (AI chat logs) at them either.

I saw a post on the torment nexus that was about 12 pages long and kept stopping to say "Chat told me" or "So I asked chat"

And I asked why they kept saying it. I hadnt made the connection yet. I thought it was something about twitch.

THe bloke replied "Oh sorry about that I have recently acquired ChatGPT as my personal assistant"

And I just couldnt. He was basically explaining all the cool things he discussed with ChatGPT.

Why would he think anyone else cares? I dont understand.

Re: Throwing AI-generated walls of text into conversations

#367

Post by protocolture »

ChiMan wrote: post #327
hungryhobbit wrote: post #259

AI conversations are like dreams: everyone has one they like and wants to share it with others ... but no on gives a crap about your dream/chat session, because it was uniquely appealing to you , and not them. Don't bore your co-workers (or others) with descriptions of your dreams, and don't throw a computer's dreams (AI chat logs) at them either.

>Don't bore your co-workers (or others) with descriptions of your dreams, and don't throw a computer's dreams (AI chat logs) at them either. Beautiful. An ode and axiom for our new age.

Its not just an ode, its an axiom for our new age.

Re: Throwing AI-generated walls of text into conversations

#368

Post by keybored »

Forgeties79 wrote: post #319
keybored wrote: post #251

Earlier quoted context omitted.

People make jokes here plenty. And being sarcastic? Only all the time. You can post 300-word matter-of-fact, spelling out all the premises comments. Or twenty-word quips that say the same thing. Both will be accepted depending on the mood. But stubbornly trying to win arguments (imagined or real)? Oy vey. That’s a reservation that takes up a private jumbo jet. Edit: And I saw your pot/kettle reply that you deleted. O…

I removed it - apparently not fast enough - because it felt mean-spirited and I was trying to let this go but apparently you are unable to do the same. Also, making fun of the way somebody talks is incredibly rude and shitty. I don’t know why you feel the need to mock me like that in an attempt to make me feel self conscious about my speech patterns. That’s not cool and it is incredibly low, to say the least. Either…

I’m sorry, it wasn’t my intention to make fun of the way you talk. I didn’t take that particular address to me as genuine.

Re: Throwing AI-generated walls of text into conversations

#369

Post by Mashimo »

hootz wrote: post #48
great_wubwub wrote: post #43

Earlier quoted context omitted.

I have a coworker whose first language isn't English. She uses AI to polish up her writing, particularly long documents. She puts a ton of effort into making sure that it still reads well. Because of this effort her writing is strong and precise. Before AI she made all the obvious mistakes you'd expect from someone who's not a native English speaker. It's very hard to tell that she used AI because she puts so much ef…

Then a better recommendation should be to use specialized AI proofreading tools, such as Kagi Translate's proofread feature. Yeah, it uses AI, but the "harness" around it forces you to use it only to improve your text, not sloppify it. https://translate.kagi.com/proofread

You can also just tell any LLM service like ChatGPT, Gemini or claude to "proofread this text, don't change too much" and it will also work.

Re: Throwing AI-generated walls of text into conversations

#370

Post by adastra22 »

imperfect_blue wrote: post #351
handoflixue wrote: post #347

Earlier quoted context omitted.

Anecdotally, LLMs are apparently good enough at writing to routinely make the front page of Hacker News. Twitter has a plague of bot comments. From all these up-votes, we can infer there is an audience and this is good faith. Partly, I admit, I just tend to be wary of shame as a tool. "Someone said something I dislike" has a long history of being abused. Conversely, even something like your gum example, one can point…

Using LLM as a writing assistant to properly format your ideas, while lazy, is not the same thing as a slop bomb. They're highly rated because the original ideas are good, even if the writing quality is sloppish, and it genuinely contains human input that you can't get simply by asking LLMs a question.

If the AI has enough editing input that your article comes off stylistically as AI-written, it is lazy and your writing is not as good as you think it is.
Post reply on HN