Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Did Claude increase bugs in rsync?

alexispurslane.github.io

Post reply on HN
Print view View original

161–170 of 611 posts

Re: Did Claude increase bugs in rsync?

#161

Post by Aurornis »

matheusmoreira wrote: post #155
Aurornis wrote: post #149

Earlier quoted context omitted.

You don't need an AI attribution tag to recognize slop. In my experience reviewing PRs, the slop-pushers are most aggressive about stripping the AI attribution anyway. It's the normal devs who use a little bit of AI who leave it in. The tag is helpful because AI authorship is different than the human authorship. When you work with a project or team for long enough you start to trust certain people and their intuition…

> I don't know why you're so defensive. Check it out: https://lobste.rs/s/29pm2f/llm_generated_submissions_should_... https://lobste.rs/s/ytim7h/collection_small_low_stakes_low_e...

I'm not interesting in joining into some argument you're having with someone on lobste.rs

Re: Did Claude increase bugs in rsync?

#162

Post by matheusmoreira »

Hammershaft wrote: post #152
matheusmoreira wrote: post #143

Earlier quoted context omitted.

And why do you want to know that? So you can call our projects slop? Ostracize us?

Because LLMs are not humans, and the code they produce will have a different distribution of failure modes than human written code, so attribution is useful info while reviewing?

> while reviewing

As I said, disclosure is polite when contributing code to third party projects which will undergo human review.

No need for such things in one's own projects.

Re: Did Claude increase bugs in rsync?

#163

Post by matheusmoreira »

Aurornis wrote: post #161
matheusmoreira wrote: post #155

Earlier quoted context omitted.

> I don't know why you're so defensive. Check it out: https://lobste.rs/s/29pm2f/llm_generated_submissions_should_... https://lobste.rs/s/ytim7h/collection_small_low_stakes_low_e...

I'm not interesting in joining into some argument you're having with someone on lobste.rs

You're not supposed to join. You said you didn't know why I was defensive. I showed you those posts as evidence of the stigma attached to LLMs and their usage. Now you know why.

Re: Did Claude increase bugs in rsync?

#164

Post by skeledrew »

grey-area wrote: post #148
skeledrew wrote: post #124

Earlier quoted context omitted.

Well, I got the meaning in the article fine, and have no complaints. > Also, LLMs often generate text that is plausible, but wrong, in ways big and small. So do humans. Always have, always will.

Humans acting with intention do it a lot less. The difference is that LLMs don’t act with intention.

No, the difference is in the education/experience of any given human, which is mostly gated by age. Like you'd generally expect someone young to make a lot of mistakes, and as time went on they'd learn and make fewer. Pretty much the same with LLMs, which have been around for... a bit over 5 years now? What would you expect of a 5 year old acting with intention? Or 10? Or even a 15 year old?

Re: Did Claude increase bugs in rsync?

#165

Post by PunchyHamster »

aesthesia wrote: post #95

I don't have a dog in this fight, but a few points that look a little suspicious: - The release with the highest number of attributed bugs is the release _right before_ the first release with Claude-coauthored commits, released in January; is there a chance that unattributed LLM-authored commits made it into this release? - The release attribution methodology is not great, since it will tend to attribute bugs introdu…

Let's start with most outright alarming error - the claude statistics are taken out of whole 2 data points

Re: Did Claude increase bugs in rsync?

#166

Post by logicprog »

PunchyHamster wrote: post #165
aesthesia wrote: post #95

I don't have a dog in this fight, but a few points that look a little suspicious: - The release with the highest number of attributed bugs is the release _right before_ the first release with Claude-coauthored commits, released in January; is there a chance that unattributed LLM-authored commits made it into this release? - The release attribution methodology is not great, since it will tend to attribute bugs introdu…

Let's start with most outright alarming error - the claude statistics are taken out of whole 2 data points

That's sort of the point. There isn't enough data to extrapolate, and yet that's exactly what those outraged about AI were doing, and when you do do the very minimal types of analyses (permutation tests, and looking at distributions, mostly) that are actually valid, safe, standard, and useful to do on such low amounts of date, again, no evidence for the outrage shows up, and the two releases look so normal that it sort of shows no one would've cared if they hadn't known or found out that Claude was involved.

I really think this a much better standard of evidence — limited though it is — to outrage-fueled cherry-picked anecdotes, which is what has been driving this whole thing. If you disagree, and think the outrage should go one when I've shown there's an absence of evidence entirely for it (although of course, that's not evidence of absence; maybe I'll have to eat my words 5 releases down the line, but appealing to that now feels like a Russell's Teapot), would you care to explain why?

Re: Did Claude increase bugs in rsync?

#168

Post by Groxx »

matheusmoreira wrote: post #162
Hammershaft wrote: post #152

Earlier quoted context omitted.

Because LLMs are not humans, and the code they produce will have a different distribution of failure modes than human written code, so attribution is useful info while reviewing?

> while reviewing As I said, disclosure is polite when contributing code to third party projects which will undergo human review. No need for such things in one's own projects.

>which will undergo human review

This can be largely assumed to be true for any open source code. It's kinda the point of open source.

Re: Did Claude increase bugs in rsync?

#169

Post by bakugo »

logicprog wrote: post #160
mwkaufma wrote: post #157

Smokescreen of highly-contingent analysis and appeals to authority over a premotivated-conclusion.

[flagged]

Your analysis was so thorough, rigorous, and objective, that you couldn't be bothered to write it yourself.

Do you genuinely believe an article written by AI defending itself is going to convince anyone who wasn't already on your side? All you're doing is giving more fuel to the "anti-AI crowd" you hate so much.

Post reply on HN