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

AI;DR (AI; Didn't Read)

rickmanelius.com

Post reply on HN
Print view View original

221–230 of 729 posts

Re: AI;DR (AI; Didn't Read)

#221

Post by BeetleB »

watwut wrote: post #185
BeetleB wrote: post #134

Earlier quoted context omitted.

> The part that astonishes me is that in the year of our common era two thousand twenty-six that it's not universally offensive and reviling to post an AI-generated response to another person. Because it wasn't pre-AI. It was normal for people to post links as arguments, counterarguments, etc. It annoyed me, and I didn't bother clicking most of them, and would occasionally tell them "If you can't bother articulating…

> If that behavior is acceptable to the masses, so is AI generated content. No, linking blog post and posting AI generated content is not the same. One is ok, other is not.

> No, linking blog post and posting AI generated content is not the same. One is ok, other is not.

Meet "the masses".

Sorry, but no. Sending me a link as an alternative to having a conversation is totally not OK.

Re: AI;DR (AI; Didn't Read)

#222

Post by elendilm »

mediaman wrote: post #188
tpoacher wrote: post #129

Earlier quoted context omitted.

I completely agree in principle, but to play devil's advocate, if an "author's" prompting technique is better than mine such that they generate a more useful article than what my own AI session might produce on average, then maybe there's value in some generated articles. The above still implies some effort going into good prompting, however. I completely agree about the uselessness of "build me a castle; no bugs plz…

It's possible, but I've experimented with different style guides and prompt methods and have never gotten it to output what I'd call "good" writing. It is almost always low information density. Sometimes I can get it to remove most of the extraordinarily cliche phrases it injects into everything, along with the tortured, gauche prose (especially Claude). But what remains is an expansion algorithm: it takes a simple i…

One can give details of a product and ask the ai to generate the documentation.

Re: AI;DR (AI; Didn't Read)

#223

Post by coderatlarge »

cortesoft wrote: post #48

I really like the point I read somewhere the other day; instead of sending me the AI output, just send me the prompt you used to generate it. That is the only part that contains only the information you are trying to convey. The rest is just guesses flowery language added, and it confuses the actual message being sent.

i personally prompt to produce a baseline then re-prompt to tweak then re-re-prompt to re-order, then re-re-re-prompt to expand certain parts, then re-re-re-reprompt to properly cross reference internally , then re-re-re-re-reprompt to proof read and add missing references . so there is no single prompt that produced the document and if i were to start from scratch the path would likely be different.

Re: AI;DR (AI; Didn't Read)

#224

Post by nick__m »

miyoji wrote: post #169
otterley wrote: post #120

Earlier quoted context omitted.

The HN Guidelines explicitly forbid posting AI-generated comments; they will be deleted if detected or reported. I'd like them to go further and delete links to AI-generated content, but I haven't been able to persuade management to do that yet.

The HN guidelines prohibit a lot of behaviors that remain unmoderated, you can see it in any thread that goes over 80 comments.

If those behaviors bothers you enough you can always mail hn@ycombinator.com because dang is not omniscient even if sometimes it looks like he is...

Re: AI;DR (AI; Didn't Read)

#225

Post by BeetleB »

LPisGood wrote: post #211
BeetleB wrote: post #124

Earlier quoted context omitted.

It's a code review, right? Give feedback that about the docs and block merging till the issue is resolved.

This sounds easy in principle, but a half dozen of these sort sorts of massive PR’s per week is basically untenable. I’m not gonna read the hundreds of lines of added documentation to decide if they’re correct or not. The price of generating new words is just so much higher than the price of evaluating it that I can’t be bothered.

> but a half dozen of these sort sorts of massive PR’s per week is basically untenable.

Actually, rejecting them is precisely what will make them easy.

"Sorry, the comments are so bad I'm stopping here. Please fix them and then I'll resume the code review."

You're giving everybody (including yourself) more work by:

1. Reviewing the code (even if you skip the documentation).

2. Letting too many abstruse comments in which everyone in the team will have to read.

3. Allowing the behavior to continue.

Become the bottleneck so the team can talk about it. If they decide this shouldn't be a blocker, just declare you won't review the comments going forward.

Re: AI;DR (AI; Didn't Read)

#227

Post by BeetleB »

aliasxneo wrote: post #218
sebastiennight wrote: post #186

Earlier quoted context omitted.

I would have said the opposite: I'd assume the link to be to a blog post, or Wikipedia page, that articulates the idea in a clearer more succint way than the person might be able of. This is, of course, before people started sending Instagram Reel or YouTube Short links. Or, maybe worse, links to 3-hour-long YouTube podcasts.

Eh, but it can become just as low-effort as AI slop. I've participated in a number of conversations here where it appears the person I was interacting with (this was pre-AI) was just googling off some keywords and pasting links with one or two sentences attached. Even in cases where they legitimately read the thing they posted, the static nature of the link leaves no room for actually responding to any nuance I might…

Yes - I would think this is obvious to HN commenters. Generally, when someone leaves a comment on HN that is nothing but a link, it gets downvoted.

Re: AI;DR (AI; Didn't Read)

#228

Post by VohuMana »

delecti wrote: post #170
corndoge wrote: post #147

Earlier quoted context omitted.

Fighting the ocean is futile

It's not the ocean, it's the poster's own team. A simple "AI comments suck" in a sprint retro would be trivially easy and would at least start the conversation.

I think the biggest issue might not be the immediate team but upper leadership. Companies which have mandated AI usage override a lot of what an individual or individual team wants. If that’s the case then it would be a lot like fighting the ocean, especially if your immediate team sees having AI write docs as an easy way to move the needle on LT’s AI monitoring dashboard.

Re: AI;DR (AI; Didn't Read)

#229

Post by elendilm »

Its a bit lame in 2026, to attack the messenger instead of the content of the message.

Its awfully similiar to bitching about reading mails on a computer and attacking the sender.

The virtue signaling is beyond me. I dont care about AI;DR or TL;DR.

Give me good content. And I will read it.

Re: AI;DR (AI; Didn't Read)

#230

Post by trelbutate »

purplethreads wrote: post #151

Impossible to know unless you did read. TL;DR works because I can see the length at a glance And you cannot tell all AI. Only mainstream crap like ChatGPT and Gemini which is full of cached tropes and boilerplate formats so it all sounds the same. My custom invoicing software automates notes based on years of my previous notes and tasks I did - looks nothing like AI. Use a real library and local model, mess with sett…

So? This is about ovious stuff where you notice the typical annoying AI style directly in the first paragraph. After all, 99% of "regular" people use the mainstream models, and anyone who uses a local model probably knows enough about AI that they don't dump raw output on you.
Post reply on HN