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

AI has a deep understanding of how this code works

github.com

Post reply on HN
Print view View original

221–230 of 329 posts

Re: AI has a deep understanding of how this code works

#221

Post by jacquesm »

mrguyorama wrote: post #197
armchairhacker wrote: post #61

Earlier quoted context omitted.

The point is that one-off LLM-generated projects don’t get support. If a vibe-coder needs to solve a problem and their LLM can’t, they can hire a real developer. If a vibe-coded project gets popular and starts breaking, the people who decided to rely on it can pool a fund and hire real developers to fix it, probably by rewriting the entire thing from scratch. If a vibe-coded project becomes so popular that people sta…

But none of that matters. If LLMs can one shot a mostly working patch of some sort for your use case, and you can't be assed to take the effort to go through it and make sure it's rock solid and up to spec, then do not submit a PR with that code because that's stupid, and literally any other human being with a claude subscription can also one shot a mostly working patch for their needs AI PRs are worthless, because i…

I agree fully and I think it can be condensed quite a bit further: you get paid to code, so code. And if it is free work for instance in an open source context realize that dumping trash into the workflow has a negative cost so the effect is much the same, even if you didn't get paid others also don't get paid to review your junk.

Re: AI has a deep understanding of how this code works

#222

Post by everybodyknows »

fzaninotto wrote: post #45

I've closed my share of AI-generated PRs on some OSS repositories I maintain. These contributors seem to jump from one project to another, until their contribution is accepted (recognized ?). I wonder how long the open-source ecosystem will be able to resist this wave. The burden of reviewing AI-generated PRs is already not sustainable for maintainers, and the number of real open-source contributors is decreasing. Si…

Does your own experience align with that of the maintainer who wrote:

> in my personal experience, reviewing AI-written code is more taxing that reviewing human-written code

Re: AI has a deep understanding of how this code works

#223

Post by menaerus »

pjmlp wrote: post #192
menaerus wrote: post #162

Earlier quoted context omitted.

Sorry, this is just ridicilous and shows how people fragile really are. This whole topic and whole MR as well. I am routinely looking into the folly implementation, sometimes into the libstdc++, sometimes into libc++, sometimes into boost or abseil etc. to find inspiration for problems that I tackle in other codebases. By the same standards, this should also be plagiarism, no? I manufacture new ideas by compiling exi…

Yes? That is why some people are forbidden to contribute to projects if their eyes have read projects with incompatible licenses, in case people go to copyright court.

Yes what? Both oxcaml and ocaml have compatible LGPL licenses so I didn't get your argument.

But even if that hadn't been the case, what exactly would be the problem? Are you saying that I cannot learn from a copyrighted book written by some respected and known author, and then apply that knowledge elsewhere because I would be risking to be sued for copyright infringement?

Re: AI has a deep understanding of how this code works

#224

Post by water2424 »

joelreymont wrote: post #210

I'm the author of the PR. No, I'm not AI or bot, etc. Yes, my resume is genuine and is even more weird than what was listed (see https://joel.id/resume ). Oh, and I live in Kyiv. As for the PR itself, it was a PR stunt that I regret now as the code works and solves a real problem (at least for me!). I'll probably redo it, once I have spare Claude $$$ which I'm using for other projects now ( https://joel.id/build-your…

[dead]

Re: AI has a deep understanding of how this code works

#225

Post by nsagent »

DrammBA wrote: post #206
menaerus wrote: post #179

Earlier quoted context omitted.

Can you give an example what exactly was copied? I ask because I took a look into MR and original repo, and the conclusion is that the tool only copy-pasted the copyright header but not the code. So I am still wondering - what's wrong with that (it's a silly mistake even a human can make), and where is the copyright infringement everyone is talking about?

> copy-past[ing] the copyright header but not the code [is] a silly mistake even a human can make Do you mind showing me some examples of that? That seems so implausible to me Just for reference, here's another example of AI adding phantom contributors and the human just ignoring it or not even noticing: https://github.com/auth0/nextjs-auth0/issues/2432

Oh wow. That's just egregious. Considering the widespread use of Auth0, I'm surprised this isn't a bigger story.

Re: AI has a deep understanding of how this code works

#226

Post by kqr »

menaerus wrote: post #216
DrammBA wrote: post #206

Earlier quoted context omitted.

> copy-past[ing] the copyright header but not the code [is] a silly mistake even a human can make Do you mind showing me some examples of that? That seems so implausible to me Just for reference, here's another example of AI adding phantom contributors and the human just ignoring it or not even noticing: https://github.com/auth0/nextjs-auth0/issues/2432

> Do you mind showing me some examples of that? That seems so implausible to me What's so special about it that I need to show you the example?

You are claiming humans copy-and-paste copyright headers without copying the corresponding code. To prove you're correct, you only need to show one (or a few) examples of it happening. To prove you incorrect, someone would have to go through all code in existence to show the absence of the phenomenon.

Hence the burden of proof is on you.

Re: AI has a deep understanding of how this code works

#227

Post by mudkipdev »

joelreymont wrote: post #210

I'm the author of the PR. No, I'm not AI or bot, etc. Yes, my resume is genuine and is even more weird than what was listed (see https://joel.id/resume ). Oh, and I live in Kyiv. As for the PR itself, it was a PR stunt that I regret now as the code works and solves a real problem (at least for me!). I'll probably redo it, once I have spare Claude $$$ which I'm using for other projects now ( https://joel.id/build-your…

What made you become interested in AI (vibe coding?) with already such an impressive resume?

Re: AI has a deep understanding of how this code works

#228

Post by mxschumacher »

joelreymont wrote: post #210

I'm the author of the PR. No, I'm not AI or bot, etc. Yes, my resume is genuine and is even more weird than what was listed (see https://joel.id/resume ). Oh, and I live in Kyiv. As for the PR itself, it was a PR stunt that I regret now as the code works and solves a real problem (at least for me!). I'll probably redo it, once I have spare Claude $$$ which I'm using for other projects now ( https://joel.id/build-your…

you are giving a new meaning to the term "PR stunt"

Re: AI has a deep understanding of how this code works

#229

Post by joelreymont »

mudkipdev wrote: post #227
joelreymont wrote: post #210

I'm the author of the PR. No, I'm not AI or bot, etc. Yes, my resume is genuine and is even more weird than what was listed (see https://joel.id/resume ). Oh, and I live in Kyiv. As for the PR itself, it was a PR stunt that I regret now as the code works and solves a real problem (at least for me!). I'll probably redo it, once I have spare Claude $$$ which I'm using for other projects now ( https://joel.id/build-your…

What made you become interested in AI (vibe coding?) with already such an impressive resume?

Thank you! I was completely unexpected, actually. I was stuck with upgrading XLA [1] and my boss gently pushed me into using ChatGPT. I wish I had used Claude instead.

After that, I found myself with $1000 in Claude credits and decided to go to town, making mistakes along the way.

[1] https://github.com/elodin-sys/elodin/pull/219

Re: AI has a deep understanding of how this code works

#230

Post by thatguysaguy »

joelreymont wrote: post #211
mnming wrote: post #168

Earlier quoted context omitted.

I wonder if it's the best outcome? The contributor doesn't seem to have a bad intention, could his energy be redirected more constructively? E.g. encouraging him to split up the PR, make a design proposal etc.

I think it's for me to redo the PR and break it into smaller pieces. There's value in the PR in that it does not require you to install the separate OxCaml fork from Jane St which doesn't work with all the OCaml packages. Or wasn't when I tried it back in August.

A big part of software engineering is maintenance not just adding features. When you drop a 22,000 line PR without any discussion or previous work on the project, people will (probably correctly) assume that you aren't there for the long haul to take care of it.

On top of that, there's a huge asymmetry when people use AI to spit out huge PRs and expect thorough review from project maintainers. Of course they're not going to review your PR!

Post reply on HN