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

551–560 of 729 posts

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

#551

Post by mrweasel »

Taek wrote: post #514
preg_match wrote: post #382

Earlier quoted context omitted.

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.

I just wrote a utility to rip all comments out of the code. Now the code is fully uncommented and it has saved lots of input tokens and also lots of meandering because the model is no longer getting stuck on bad ideas it told itself about.

That's is something I did not consider, the model using the existing comments as input. Comments that it may itself have written.

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

#552

Post by r_lee »

attheballot wrote: post #544
pavon wrote: post #3

AI—DR

This bit in particular > Look, I get it. It’s Q3 2026, and we should expect that everyone is utilizing AI at SOME point in their process (sourcing ideas, creating outlines, refining prose, etc.). I stopped reading there.

I really don't understand the "refining prose"

it's more like, "refining prose so that nobody sane will bother reading it". like wow it's so useful to claudefy your thoughts, wow look at how amazing your blog post looks now with how much more slop you produced from your prompt, amazing.

I really wonder like, do those authors not think from the perspective of the reader?

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

#553

Post by 7e »

The new modern workflow is to take a succinct idea and expand it into pages and pages of slop using AI. Nobody reads this slop, they ask another AI to summarize it back down to the original succinct core.

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

#555

Post by supermatt »

Planktonne wrote: post #549
CuriouslyC wrote: post #443

Earlier quoted context omitted.

You say this, but it's likely a lie. Maybe not for you, but for every N people like you that say it, a high percentage of them are lying. There's research on people's preference for AI generated content over human content when the provenance of the content is blind, which flips on its head when provenance is not blind. The truth is the actual "art" never mattered, most people are living in Plato's cave and they're sc…

> people's preference for AI generated content over human content when the provenance of the content is blind, which flips on its head when provenance is not blind I don't think this shows what you think it shows. AI output (in short clumps) looks like human output; it's designed to do that. Naturally people will sometimes prefer it to other stuff that looks like human output, but crucially this shifts when they real…

> this shifts when they realise

I think this is pretty much is what they were saying about the provenance being blind. If you are able to deduce the LLM usage through the long-form text then that removes the blindness and objectivity.

I wonder if you view adversarially humanised LLM-generated content in the same light as that which hasn't been obfuscated. I recall seeing some paper with examples posted here a few months ago, where I (and the participants in the study) literally couldn't tell the difference between them and human writing. I have considered using humanisation myself but there is both less control over the output and it (obviously) loses the LLM-like structure that I find so easy to read - and is therefore antithesis to my own objectives.

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

#556

Post by roarcher »

account42 wrote: post #545
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

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.

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

#558

Post by meerita »

I am writing excellent documentation with AI. The key success is to have rules to write documentation, PRs, commits, etc. I use ASD-STE100 and some constraints on what to write, how, and what it matters to my projects.

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

#559

Post by 72deluxe »

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…

It's like people didn't realise that it was unmaintainable before and now we have a new level of unmaintainability. The insane amount of code produced means it's only maintainable with AI.

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

#560

Post by stelonix »

tehlike wrote: post #465
roarcher wrote: post #415

Earlier quoted context omitted.

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.

This has been a thing for long while, on codex too. You ask it to do something, then tell it to do something in a different way, then it assumes it needs to do the refactor in a backward compatible way, or creates migrations for it etc.

Oh good I thought I was doing something wrong! Using ChatGPT web for planning, ask for a prompt then notice something weird in the prompt and whether I:

1) use the edit in-place functionality; or

2) ask it to rewrite to remove something

It'll write the prompt as if the agent (codex) knew about the conversation and add "don't do X" etc. At first that bothered but I realized it doesn't really change the output so I stopped caring.

Still, no experience is unique I guess.

Post reply on HN