News for hackers. Stuff that matters.
Re:AI;DR (AI; Didn't Read) by roarcher on Monday August 17, 2026 @10:51PM (#49340650)
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.
Re:AI;DR (AI; Didn't Read) by foolserrandboy on Monday August 17, 2026 @11:33PM (#49340926)
Oh no, you said "landed"! It's dug into our brains!
Re:AI;DR (AI; Didn't Read) by dag11 on Tuesday August 18, 2026 @12:08AM (#49341136)
You could say it landed cleanly.
Re:AI;DR (AI; Didn't Read) by hexasquid on Tuesday August 18, 2026 @12:34AM (#49341295)
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.
Re:AI;DR (AI; Didn't Read) by roarcher on Tuesday August 18, 2026 @01:57AM (#49341818)
There's got to be a Weird Al song like this coming soon.
Re:AI;DR (AI; Didn't Read) by bkaae on Tuesday August 18, 2026 @03:12AM (#49342396)
Bless the lord that it's not been presented to us yet, because you just know that it exists already.
Re:AI;DR (AI; Didn't Read) by Yizahi on Tuesday August 18, 2026 @06:11AM (#49343546)
Re:AI;DR (AI; Didn't Read) by myvoiceismypass on Tuesday August 18, 2026 @02:29PM (#49350295)
This is one of my favorite things to have ever read on HN
Re:AI;DR (AI; Didn't Read) by roarcher on Monday August 17, 2026 @11:34PM (#49340943)
Oh. Oh no.
Re:AI;DR (AI; Didn't Read) by doix on Tuesday August 18, 2026 @02:12AM (#49341936)
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

Re:AI;DR (AI; Didn't Read) by account42 on Tuesday August 18, 2026 @04:00AM (#49342783)
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.
Re:AI;DR (AI; Didn't Read) by roarcher on Tuesday August 18, 2026 @05:01AM (#49343158)
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) by account42 on Tuesday August 18, 2026 @05:49AM (#49343435)
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) by Exolon on Tuesday August 18, 2026 @01:59PM (#49349769)
Same here. I was always more of an en-dash enjoyer, and used that back in academia since it's just a double-dash in Latex.
Re:AI;DR (AI; Didn't Read) by roarcher on Tuesday August 18, 2026 @02:42AM (#49342159)
As a former em-dash enjoyer, I indeed feel your pain.
Re:AI;DR (AI; Didn't Read) by filterfish on Tuesday August 18, 2026 @03:35AM (#49342598)
I'm with you an that one. RIP em-dash.
Re:AI;DR (AI; Didn't Read) by jannyfer on Tuesday August 18, 2026 @12:31PM (#49348205)
RIP. I had frequently used ALT + 0151.
Re:AI;DR (AI; Didn't Read) by algoth1 on Tuesday August 18, 2026 @05:41AM (#49343391)
Same here for em-dashes
Re:AI;DR (AI; Didn't Read) by tanseydavid on Wednesday August 19, 2026 @12:08PM (#49363452)
I will continue to use em-dashes as I always have.

When someone uses the presence of em-dash as the only signal for AI-generated then they are simply lazy.

Re:AI;DR (AI; Didn't Read) by cueo on Tuesday August 18, 2026 @05:51PM (#49353229)
Smoking gun!
Re:AI;DR (AI; Didn't Read) by tehlike on Tuesday August 18, 2026 @12:27AM (#49341248)
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.

Re:AI;DR (AI; Didn't Read) by geysersam on Tuesday August 18, 2026 @02:09AM (#49341912)
Omg the "backwards compatible fix" in a one-off script, I feel my ptsd coming on ...
Re:AI;DR (AI; Didn't Read) by stelonix on Tuesday August 18, 2026 @05:09AM (#49343222)
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.

Re:AI;DR (AI; Didn't Read) by theshrike79 on Tuesday August 18, 2026 @06:17AM (#49343591)
This is why I started adding a PROJECT.md file to all my projects and a hook for claude to read it.

It contains (Among other things) stuff like "this is a single user personal project, I'm the only user, this will never be open to the public internet" etc.

It kinda-sorta tones down the proclivity to worry about backwards compatibility and slight edge cases where if someone has edited some template and the new code doesn't support it.

Re:AI;DR (AI; Didn't Read) by Uptrenda on Tuesday August 18, 2026 @06:46AM (#49343774)
I remember when I was updating some formats for my apps data files and it ended up writing v2 and laying it on top of the old one. Ended up just telling it to delete the entire feature and start again. I do think claude.md instructions help though.
Re:AI;DR (AI; Didn't Read) by tehlike on Tuesday August 18, 2026 @10:55AM (#49346550)
They do. But you need to remember.
Re:AI;DR (AI; Didn't Read) by masto on Tuesday August 18, 2026 @05:45AM (#49343410)
There needs to be a pithy name for this. I have been calling it context leak.
Re:AI;DR (AI; Didn't Read) by chester_r on Tuesday August 18, 2026 @06:42AM (#49343740)
Re:AI;DR (AI; Didn't Read) by npip99 on Tuesday August 18, 2026 @07:55PM (#49354652)
just add to markdown instructions to check that this failure mode isn't happening in its diff before yielding back to human review. Any issue that occurs more than once, you can just put in the review markdown instructions so you don't need to look at it twice.