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

501–510 of 729 posts

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

#501

Post by kqr »

eru wrote: post #457
kristjansson wrote: post #417

Earlier quoted context omitted.

And the tests. Oh god the tests. Personal recent favorite: I asked for some changes to a Dockerfile, which it did ably, and then promptly tested by writing a pytest module that traversed up to the root, read the Dockerfile, and checked that the added lines were present.

Try property based testing perhaps.

Code-generating robots are pretty bad at property-based testing, in my experience. They can do it but they still need a lot of hand-holding. They often regress to writing a mirror implementation as the oracle and trying to enumerate a fixed set of examples they find meaningful.

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

#502

Post by roarcher »

hexasquid wrote: post #468
dag11 wrote: post #451

Earlier quoted context omitted.

You could say it landed cleanly.

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.

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

#503

Post by kqr »

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…

I think your last sentence is getting close to the truth. You're no longer the audience for those descriptions. Other robots are.

I'm not saying that's good or bad because I don't know, but I think that's the idea of dumping all that junk into PR descriptions.

However, annoyingly, we still need to review those descriptions very closely, because the robots are trained to put a lot of weight into things they read in the documentation. And they tend tospresent loose speculation as fact. They often end up documenting some assumption that isn't true, then end up writing code as if it were.

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

#504

Post by geysersam »

aaaronic wrote: post #252
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…

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!

shudder

I wish they trained the bots to be a notch more relaxed and less hysterical. Less is more.

But maybe that's just a consequence of the RL training being essentially AI torture to make them do what we want.

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

#505

Post by kstenerud »

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…

[flagged]

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

#506

Post by Alephinitesimal »

I once spent two days on a pr and got an obviously AI generated review that contradicted what we agreed one before. So I had AI respond to it. The next day he asked if I'd used AI. I used the same justification he'd used for his review. Fight magic with magic. He never reviewed my pr that way again.

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

#507

Post by yoz-y »

dbspin wrote: post #50

"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.)." Hell no. Sourcing ideas? From AI? Are you kidding? Essentially guaranteeing they won't be original? Refining prose? Making it much more likely it'll be generic as hell. Call me old fashioned, but while I can certainly understand asking LLMs concre…

Sourcing ideas just seems so weird… if you don’t have an idea about what to make, then just don’t ?

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

#508

Post by geysersam »

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.

Omg the "backwards compatible fix" in a one-off script, I feel my ptsd coming on ...

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

#509

Post by gspr »

ithkuil wrote: post #274
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…

Don't get me wrong, I loathe the AI style as the next person. But I don't buy your argument: if a person used AI to produce a text it doesn't mean they haven't steered the I in the direction they wanted the conversation to go and (hopefully) review the output. That's an added value Yes, it would be nice if it was also pleasant to read

Steered it?! If I'm gonna read it, I want someone to have written it, not bloody "steered" it!

"Why are you upset with this restaurant meal? Okay it wasn't actually cooked here per se, but the chef certainly reheated it and carefully monitored the microwave oven while doing so!"

This crap just needs to end. "Steering" words at another human being is incredibly disrespectful.

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

#510

Post by doix »

foolserrandboy wrote: post #430
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.

Oh no, you said "landed"! It's dug into our brains!

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

Post reply on HN