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

381–390 of 729 posts

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

#381

Post by preg_match »

b112 wrote: post #231
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…

You're precluding the possibility that the other party instructed the LLM to write what he intended to say. That is not currently possible. At best, you could train on millions of personal examples of style, eg historical emails, reports, etc, and you'd still never get what the person would have written. I'd be astonished if an LLM didn't even miss important nuance, data, and focus on the wrong point. It think the pa…

I will use LLMs to find spelling and grammar mistakes, as well as voice inconsistencies. I then carefully review the diff.

Yes there are deterministic tools for this, but grammar is actually kind of complicated and the tools either miss mistakes, or suggest obviously worse edits. Looking at you, Microsoft Word.

All the writing is my own and I read all of it. Naturally there’s no LLM-isms because I wrote 99.9% of the original text. But, it was AI assisted. So, I don’t think it’s cut and dry.

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

#382

Post by preg_match »

koyote wrote: post #263
aaaronic wrote: post #252

Earlier quoted context omitted.

My "favorite" Claudism is when I critique its work and ask it to remove some unnecessary part of the design -- and then the diff has more green than red because it added comments about why the code is no longer there -- the code that was never in the mainline and never asked for!

It's not just claude, all AI is unable to produce something concise. On the surface everything looks 'good' whether code or prose, but then if you dig a bit, try and understand the whole text you quickly realise that 80% of it is unecessary and the whole thing could have been re-worded/re-coded into something a fraction of its size and complexity. I asked Sol to reduce the length of some documentation we had by makin…

I have to ask Claude to compact the comments every time, and I give specific criteria for it. Never ever reiterate what’s in the code, never mention decisions not made, never mention the conversation, etc etc.

Even then it is conservative. For the love of God, compact the comments.

Comments become a huge maintenance burden, especially in the age of AI. They just grow and grow, and then mislead the AI later on.

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

#383

Post by wpietri »

qarl2 wrote: post #346
Alpha3031 wrote: post #320

Earlier quoted context omitted.

Again, you are free to interpret my comments however you wish. My primary intent was to express my belief that people having different preferences to you regarding reading AI output does not constitute some bizzare hivemind, which you appear to have accepted. Your preferences regarding communications between yourself and your wife are none of my business. I recognise preferences may exist, and I am not one to kink-sh…

My dearest dude - You called my wife bizarre. Then you said "TECHNICALLY, I didn't call your WIFE bizarre I called her ACTIONS bizarre." I would ask you to stop talking to me, but it seems unlikely to work. So. You have a nice day, now.

You're the one who decided to imagine that a reasonable discussion comment was an attack on your wife. You're also the one who started out calling things bizarre. As somebody not involved in this discussion, to me it looks like drama-seeking behavior.

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

#384

Post by dhorthy »

sobellian wrote: post #196
gortok wrote: post #36

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. If I'm reading something on the internet, I'm either reading it to learn, or I'm reading it to be persuaded. If I wanted the LLM to teach me (thank you, no), I would ask an LLM. I'm reading your website/newsletter/email because I…

A few thoughts. - I'm open to seeing information from an AI (I'm fine with an LLM "teaching me") so long as it is high quality. That does require human inspection. - I've seen a related bit about AI-written emails where the commenter would rather see the prompt. I agree. As a software engineer, I like reproducibility. If an AI outputs an interesting result, show me the "source" (i.e. the model, effort, prompt, etc.).…

> AI-written emails where the commenter would rather see the prompt

this a thousand times this

LLMs are information transformers. if you're trying to take some rough idea and blow it out into something that "feels" substantive, you're just combining your high-signal idea / prompt with a bunch of meaningless bloat and noise from the model weights.

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

#385

Post by ryandrake »

_--__--__ wrote: post #277
aaaronic wrote: post #252

Earlier quoted context omitted.

My "favorite" Claudism is when I critique its work and ask it to remove some unnecessary part of the design -- and then the diff has more green than red because it added comments about why the code is no longer there -- the code that was never in the mainline and never asked for!

Yeah this is awful. Every codebase becomes a graveyard of references to ideas or behaviors that were barely considered. It's probably also a compounding source of context poisoning when a minority of the comments/documentation are about how the current code actually works.

It also likes to spew references to documents that are not, and never have been, in the repo. So if you're not careful you'l have comments all over your codebase saying things like: foo() - Perform foo action as documented in PRIVATE_INTERNAL.doc

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

#387

Post by platevoltage »

a2ff6eeb0 wrote: post #334
platevoltage wrote: post #160

Earlier quoted context omitted.

I'll take "subpar" human writing, music, art, or whatever any day of the week.

People say this, but AI artists keep getting listens on music platforms, doing at least as well as human artists if the listener is making a blind choice. https://www.promarket.org/2026/05/04/consumers-prefer-ai-mus...

Sure. Kid Rock also sold more records than the Pixies.

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

#388

Post by deathanatos »

The problem is merely determining to "AI; DR" itself is not free. Reading an article takes effort, effort that one hopes will result in something intellectually stimulating. By the time you sample enough of the content to make the determination that the article is AI, you've already invested effort, and now found out the rug has been pulled.

Sure, before, there was always the possibility that the article wouldn't deliver. Sturgeon's Law. But now it's like 10× more, and the amount of slop out there means its even harder to find that (human-written) gem amongst all the chaff. This last month especially, I've started to wonder "what even is the point of HN?" as more and more of the frontpage ends up dominated by slop. The thing that made HN worth it in the beginning is that it had a high gem:chaff ratio — at least compared to other corners of the Internet at the time I joined.

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

#389

Post by ninkendo »

rbongers wrote: post #309
LPisGood wrote: post #56

My coworkers continue to dump hundreds of lines of AI documentation in every PR and every other line of code has between one and ten lines of AI generated comments, talking about the real unlock and how things are byte for byte identical on the load bearing path or how the acceptance ladder is misleading. Features are coming out and metrics are improving, but we’re basically in a post readability code base, with the…

Two very useful directives to give AI when it comes to documentation: 1) Document what's there, not the diff. Documentation of how code was removed or changed to fix a bug or add a feature is not useful and difficult to maintain; documentation should explain how code works now. 2) Documentation should live close to the source as possible. Prefer line based comments and standardized function documentation. Top-level s…

> Document what's there, not the diff

We recently added a similar thing to our style guide, It’s astonishing to me that we have to spell this out, that something as obvious as this needs to be explained to LLM’s at all. They’re supposed to be exceeding human intelligence, at least at things like programming, but can’t understand basic things like what code comments are.

Post reply on HN