A full on disengage brain vibe coder. Amazing

Repeatedly using AI to answer questions about the legitimacy of commits from an AI, to people who are clearly skeptical is breathtakingly dense. At least they're open about it.

I did love the ~"I'll help maintain this trash mountain, but I'll need paying". Classy.

>>> Beats me. AI decided to do so and I didn't question it.

Really sums the whole thing up...

If you want to behave like a spam bot don't complain when people treat you like a spam bot.

Oh, wow. They're being way too tolerant IMO; I'd have just blocked him from the repo at about that point.

This is the same.

https://github.com/ocaml/ocaml/pull/14369/commits/ce372a60bd...

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.

Side note: discovering the discussions in this PR is exactly why I love HN. It's like witnessing the changes in our trade in real time.

Found this part hilarious - git ignoring all of the claude planning MD files that it tends to spit out, and including that in the PR

Lazy AI-driven contributions like this are why so many open source maintainers have a negative reaction to any AI-generated code

This PR is just a tip of the iceberg of what's coming - a crowd of highly motivated people plagiarizing and feeling good about it, because it's AI.

"The webpage credits another author: Native binary debugging for OCaml (written by Claude!) @joelreymont, could you please explain where you obtained the code in this PR?"

That pretty much sums up the experience of coding with LLMs. They are really damn awesome at regurgitating someone else's source code. And they have memorized all of GitHub. But just like how you can get sued for using Mickey Mouse in your advertisements (yes, even if AI drew it), you can get sued for stealing someone else's source code (yes, even if AI wrote it).

in response to someone asking about why the author name doesn't match the contributor's name. Incredible response.

The fact that this was said as what seems to be a boast or a brag is concerning. As if by the magic of my words the solution appeared on paper. Instead of noticing that the bulk of the code submitted was taken from someone else.

I generally like AI coding using CC etc, but this forced me to remember that these generated code ultimately came from these stolen (spiritually, not necessarily legally) pieces.

In fairness, the author claims to have learned - quoting from his portfolio page

So... 1 down, 6.9 billion to go.

Why is the person who made this AI-generated pull request (joelreymont) so insistent that his PR gets merged?

If I created some pull request and this pull request got rejected for reasons that I consider to be unjust, I would say: "OK, I previously loved this project and thus did such an effort to make a great improvement PR for it. If you don't want my contribution, so be it: reject it. I won't create PRs anymore for this project, and I hope that a lot of people will see in this discussion how the maintainers unfairly rejected my efforts, and thus will follow my example and from now on won't waste their time anymore to contribute anything to this project. Goodbye."

I think this is a good point, that publishing a library (when possible, not sure if it's possible in this case) or module both reduces/removes the maintenance burden and makes it feel like more of an opt-in.

(Not so)interestingly, the PR author even advertised this work on HN.

Our glorious AI-driven future in a nutshell.

> Damn, I can’t debug OCaml on my Mac because there’s no DWARF info…But, hey, there’s AI and it seems to one-shot fairly complex stuff in different languages, from just a Github issue…My needs are finally taken care of!

So I do believe using an LLM to generate a big feature like OP did can be very useful, so much that I’m expecting to see such cases more frequently soon. Perhaps in the future, everyone will be constantly generating big program/library extensions that are buggy except for their particular usecase, could be swapped with someone else’s non-public extensions that they generated for the same usecase, and must be re-generated each time the main program/library updates. And that’s OK, as long as the code generation doesn’t use too much energy or cause unforeseen problems. Even badly-written code is still useful when it works.

What’s probably not useful is submitting such code as a PR. Even if it works for its original use-case, it almost certainly still has bugs, and even ignoring bugs it adds tech debt (with bugs, the tech debt is significantly worse). Our code already depends on enough libraries that are complicated, buggy, and badly-written, to the extent that they slow development and make some feasible-sounding features infeasible; let’s not make it worse.

> > Here's my question: why did the files that you submitted name Mark Shinwell as the author?

>Beats me. AI decided to do so and I didn't question it.

I'm howling

> Different naming conventions (DW_OP_* vs DW_op_*)

Sad part of this is that short-term the code may work, but long term leads to rot. Incentives at orgs are short-term oriented. If you wont be around to clean things up when shit hits the fan, why not let AI do all the code ?

One thing I never really liked about professional software development is the way it can stall at big movements because we reject large PRs. Some stuff just won't happen if you have a simple heuristical position on this (IMO obviously).

Welcome to 2025!

I guess the proponents are right. We'll use LLMs one way or another, after all. They'll become one.

One of the biggest problems is the fact that the public nature of Github means that fixes are worth "Faux Internet Points" and a bunch of doofuses at companies like Google made "social contribution" part of the dumbass employee evaluation process.

Forcing a person to sign up would at least stop people who need "Faux Internet Points" from doing a drive-by.

Feels a.but like snobbism and projection of fear that what they do is becoming less valuable. In this case, how DARE a computer progeam write such code!

It's interesting how this is happening. And in the future it will be amazing seeing the turning point when the.machine generated code cannot ne ignored.

Kind of like chess/Go players: First they laughed at a computer playing chess/Go, but now, they just accept that there's NO way they could beat a computer, and keep playing other humans for fun.

Discussions about AI/LLM code being a problem solely because AI/LLM is not generally a productive conversation.

Better is to critique the actual PR itself. For example, needs more tests, needs to be broken up, doesn't follow our protocols for merging/docs, etc.

Additionally, if there isn't a code of conduct, AI policy, or, perhaps most importantly, a policy on how to submit PRs and which are acceptable, it's a huge weakness in a project.

In this case, clearly some feathers were ruffled but cool heads prevailed. Well done in the end..