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

561–570 of 729 posts

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

#561

Post by 72deluxe »

freetime2 wrote: post #343
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…

What's astonishing to me is how quickly people at my workplace have adopted this habit. Six months ago my manager was vociferously complaining about his boss asking him to review a lengthy document that was clearly AI generated, saying that his boss wasn't even capable of understanding the document the LLM had created. Now the majority of technical communication I get from my manager is just a transcript exported dir…

This is very sad. I found it was interrupting coding when the editor would suggest new blocks of code without me actually thinking and I found I was just generally abandoning any thought processes.

So I've disabled that and now I'm explicit if I want to solve a problem because then it means my brain's actually engaged.

It seems to be like a shortcut to early onset dementia because the brain's never being actively involved in problem solving.

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

#563

Post by paldepind2 »

ninkendo wrote: post #389
rbongers wrote: post #309

Earlier quoted context omitted.

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.

My theory (which might be completely wrong) is that models do this because it improves quality for vibe coders.

When vibe coding the content of user prompts is ground truth and the only way any human thought affect the code base. So if the vibe coder says "do X not Y", recording int comments that "we shouldn't do Y" is important. It ensures that the agent doesn't accidentally decide to do Y tomorrow, which would frustrate the vibe coder who'd feel that the agent doesn't "remember" what it was told yesterday.

So for people who look at the code the comments are obvious and completely superfluous, but for the vibe coder it's a way to ensure that their tiny (relative to the size of the code base) input is not forgotten.

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

#564

Post by algoth1 »

roarcher wrote: post #519
doix wrote: post #510

Earlier quoted context omitted.

I hate that I have to change the way I write to avoid AI-isms. I loved using "load bearing" to describe weird code that you think you can delete but is actually holding everything together. Now people think I'm just parroting what Claude said. It sucks. I want my catch phrases back, I guess this is how em dash users felt

As a former em-dash enjoyer, I indeed feel your pain.

Same here for em-dashes

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

#565

Post by masto »

roarcher wrote: post #415
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!

Oh god this has been driving me nuts since Opus 5 landed. Every docblock is filled with long-winded jargon explaining why this design is superior to some other design, which never existed as far as any dev who might read that comment is concerned.

There needs to be a pithy name for this. I have been calling it context leak.

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

#566

Post by account42 »

roarcher wrote: post #556
account42 wrote: post #545

Earlier quoted context omitted.

I feel like a lot of these have been LinkedIn-isms or PR-isms long before they have been AI-isms so not much is lost.

I used to use em-dashes for explanatory clauses--like this one, for example--when using commas would make the sentence difficult to parse due to other nearby commas. They're only a LinkedIn-ism when used to create an unduly dramatic juxtaposition for an otherwise mundane idea. But now they set off people's AI radar when used for any reason at all.

Perhaps I am biased because I find the use of em-dashes without spaces (as is common in English typesetting) to be inherently ugly so I'm not too unhappy to see their use discouraged.

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

#568

Post by fallingbananna »

m132 wrote: post #158
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 like how some people take offence at that

I don't like it. I don't take any offence. It just triggers the same AI;DR for me.

If I think the task requires a human to think about it. And the person is the human paid to think about it. Whether I get a wall of AI text, prompt, or an entire AI conversation... there is no human insight in it.

If that person took the time to think about the problem, had a chat with the AI, and understood the output, surely they can take the final step and tell me the short result/summary themselves, right?

---

However, if I had to choose lesser evil, I would of course prefer to have a link to the AI conversation over having a wall of text directly in the conversation.

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

#569

Post by supermatt »

johnnyanmac wrote: post #529
supermatt wrote: post #190

Earlier quoted context omitted.

> which is barely any at all Clearly you either didn't read it, misunderstood it, disbelieved it, or just DGAF :)

Add some paragraphs and yes; your style is more "interesting than what an LLM generated. That's the only think truly hard to read compared to the output. Your style reveals the way you write sentences, the language and vocabulary you choose to employ, and even your emotion. Here's an obvious example: > I dont care ion people dont read my stuff. There are people that do and they find it useful. My ideas solidified hav…

My aim was to turn my ramblings into something more coherent. No more. No less.

I have made longer notes using exactly the process you prescribe, but that wasn't necessary for me in this case as it wasn't the most complex of ideas - I just regenerated until it gave me a fair approximation of what I wanted.

And to be fair - even if I had given it follow-up guidance it would still have the LLM "smell". It would receive EXACTLY the same treatment from the anti-llm crowd. Thats pretty much one of the core points of the post (judging the medium ahead of the content).

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

#570

Post by Yizahi »

roarcher wrote: post #502
hexasquid wrote: post #468

Earlier quoted context omitted.

Good instinct. Fair challenge. This corrects my framing. It makes your point sharp. This is a significant finding. Positively confirmed. That settles it, and it flips the picture. Honest verdict - this is not small. Let me wire it in.

There's got to be a Weird Al song like this coming soon.

Behold, The Masterpiece :)

https://news.ycombinator.com/item?id=49251221

Post reply on HN