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

191–200 of 329 posts

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

#191

Post by lawlessone »

silverlake wrote: post #187
pluc wrote: post #68

To all the AI apologists here I'd like to submit a simple scenario to you and hear your answer: you use AI to create a keynote speech on a topic you needed to use AI to write. At the end of your speech, people ask you questions about the contents of your speech. What do you say? This is the same.

Hi, AI apologist here. This scenario is a problem with or without AI. You can’t drop a 13k line PR you don’t understand without prior discussion. There are many ways to use AI. Your scenario (keynote speech) is a bad way to use it. Instead, a PR where you understand every line, whether you or an AI wrote it, should be fine. It would be indistinguishable from human generated code. AI is a tool like any other. I hire a…

>You can’t drop a 13k line PR you don’t understand without prior discussion.

How common was that before AI coding?

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

#192

Post by pjmlp »

menaerus wrote: post #162
nsagent wrote: post #138

Earlier quoted context omitted.

It's clear Claude adapted code directly from the OxCaml implementation (the PR author said he pointed Claude at that code [1] and then provides a ChatGPT analysis [2] that really highlights the plagiarism, but ultimately comes to the conclusion that it isn't plagiarized). Either that highlights someone who is incompetent or they are willfully being blasé. Neither bodes well for contributing code while respecting copy…

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.

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

#193

Post by mncharity »

torben-friis wrote: post #94
benterix wrote: post #62

Did these Ocaml maintainers undergo some special course for dealing with difficult people? They show enormous amounts of maturity and patience. I'd just give the offender Torvalds' treatment and block them from the repo, case closed.

I honestly reread the whole thread in awe. Not due to the submitter, as clickbaity as it was, but reading the maintainers and comparing their replies with what I would have written in their place. That was a masterclass of defending your arguments rationally, with empathy, and leaving negative emotions at the door. I wish I was able to communicate like this. My only doubt is whether this has a good or bad effect over…

Years back I attended someone doing an NSF outreach tour in support of Next Generation Science Standards. She was breathtaking (literally - bated breath on "how is that question going to be handled?!?"). Heartfelt hostile misguided questions, too confused to even attain wrong, somehow got responses which were, not merely positive and compassionate, but which managed to gracefully pull out constructive insights for the audience and questioner. One of those "How do I learn this? Can I be your apprentice?" moments.

The Wikipedia community (at least 2 decades back) was also notable. You have a world of nuttery making edits. The person off their meds going article by article adding a single letter "a". And yet a community ethos that emphasized dealing with them with gentle compassion, and as potential future positive contributors.

Skimming a recent "why did perl die" thread, one thing I didn't see mentioned... The perl community lacked the cultural infrastructure to cope with the eternal-September of years of continuous newcomer questions, becoming burned out and snarky. The python community emphasized it's contrast with this, "If you can't answer with friendly professionalism, we don't need your reply today" (or something like that).

Moving from tar files with mailing lists, to now community repos and git and blogs/slack/etc, there's been a lot of tech learned. For example, Ruby's Gems repo was explicitly motivated by "don't be python" (then struggling without a central community repo). But there's also been the social/cultural tech learned, for how to do OSS at scale.

> My only doubt is whether this has a good or bad effect overall

I wonder if a literature has developed around this?

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

#194

Post by mrguyorama »

mnming wrote: post #168
benterix wrote: post #62

Did these Ocaml maintainers undergo some special course for dealing with difficult people? They show enormous amounts of maturity and patience. I'd just give the offender Torvalds' treatment and block them from the repo, case closed.

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.

The constructive outcome is the spammer fucks off or learns how to actually code.

Lots of people all over the world learn some basics of music in school, or even learn how to play the recorder, but if you mail The Rolling Stones with your "suggestions" you aren't going to get a response and certainly not a response that encourages you to keep spamming them with "better" recommendations.

The maintainers of an open source project are perfectly capable of coercing an LLM into generating code. You add nothing by submitting AI created code that you don't even understand. The very thought that you are somehow contributing is the highest level of hubris and ego.

No, there's is nothing you can submit without understanding code that they could not equally generate or write, and no, you do not have an idea so immensely valuable that it's necessary to vibe code a version.

If you CAN understand code, write and submit a PR the standard way. If you cannot understand code, you are wasting everyone's time because you are selfish.

This goes for LLM generated code in companies as well. If it's not clear and obvious from the PR that you went through and engineered the code generated, fixed up the wrong assumptions, cleaned up places where the LLM wasn't given tight enough specs, etc, then your code is not worth spending any time reviewing.

I can prompt Claude myself thank you.

The primary problem with these tools is that assholes are so utterly convinced that their time is infinitely valuable and my time is valueless because these people have stupidly overinflated egos. They believe their trash, unworkable, unmaintainable slop puked out by an LLM is so damn valuable, because that's just how smart they are.

Imagine going up to the Civil Engineer building a bridge and handing them a printout from ChatGPT when you asked it "How do you build a bridge" and feeling smug and successful. That's what this is.

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

#195

Post by silverlake »

lawlessone wrote: post #191
silverlake wrote: post #187

Earlier quoted context omitted.

Hi, AI apologist here. This scenario is a problem with or without AI. You can’t drop a 13k line PR you don’t understand without prior discussion. There are many ways to use AI. Your scenario (keynote speech) is a bad way to use it. Instead, a PR where you understand every line, whether you or an AI wrote it, should be fine. It would be indistinguishable from human generated code. AI is a tool like any other. I hire a…

>You can’t drop a 13k line PR you don’t understand without prior discussion. How common was that before AI coding?

Enough that stacked PRs are a thing. At my job people sometimes build large features on a branch for 6 months. Then it’s a massive PR and no one can review it.

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

#196

Post by silverlake »

pluc wrote: post #189
silverlake wrote: post #187

Earlier quoted context omitted.

Hi, AI apologist here. This scenario is a problem with or without AI. You can’t drop a 13k line PR you don’t understand without prior discussion. There are many ways to use AI. Your scenario (keynote speech) is a bad way to use it. Instead, a PR where you understand every line, whether you or an AI wrote it, should be fine. It would be indistinguishable from human generated code. AI is a tool like any other. I hire a…

That's a fair answer. How do you stop people from doing it though? How do you stop it from becoming every lazy person's first reflex instead of every smart person's third?

I don’t know. But at least you’ve identified the real problem: lazy people generating trash code. AI isn’t bad, people are.

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

#197

Post by mrguyorama »

armchairhacker wrote: post #61
squigz wrote: post #48

Earlier quoted context omitted.

> cause unforeseen problems This is literally the point of having software developers, PR reviews, and other such things. To help prevent such problems. What you're describing sounds like security hell, to say nothing of the support nightmare.

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 if they are that good, nobody needs to share anything anymore anyway! If they aren't that good, they are spam.

The reason people keep committing giant LLM PRs is that they are deluded and morons, and somehow believe that both their ideas are magically important, LLMs trivially turn those ideas into quality output, and somehow nobody else can do that as well.

It's just ego. Believing that only YOU can contribute something produced by a machine that takes natural human language as input is asinine. Anyone can produce it. And if anyone can produce it, nobody needs YOU to submit a PR.

If you prompted an LLM to produce code, then so can the maintainers of the project. Why are you so full of yourself that you think they require you to generate a PR for them? Do you think OSS programmers don't know how to use LLMs?

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

#198

Post by AnimalMuppet »

owenversteeg wrote: post #182

I've seen a lot of AI-generated PRs but I think this one is actually a very unique and interesting case. Most of these are written by novices, don't work, are for less-technical projects, and there isn't any real conversation or changing opinions. This was completely different; it was complex and actually worked, the poster Joel Reymont has 30 years of software experience and not exactly on simple bullshit either (fr…

So, what, this is better than others? SMH...

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

#199

Post by yoyohello13 »

mrguyorama wrote: post #194
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.

The constructive outcome is the spammer fucks off or learns how to actually code. Lots of people all over the world learn some basics of music in school, or even learn how to play the recorder, but if you mail The Rolling Stones with your "suggestions" you aren't going to get a response and certainly not a response that encourages you to keep spamming them with "better" recommendations. The maintainers of an open sou…

> The maintainers of an open source project are perfectly capable of coercing an LLM into generating code. You add nothing by submitting AI created code that you don't even understand. The very thought that you are somehow contributing is the highest level of hubris and ego.

Thank you! I was struggling to articulate why AI generated PRs annoy me so much and this is exactly it.

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

#200

Post by arresin »

jodrellblank wrote: post #131
hypeatei wrote: post #87

Earlier quoted context omitted.

It's clear some people have had their brain broken by the existence of AI. Some maintainers are definitely too nice, and it's infuriating to see their time get wasted by such delusional people.

> " It's clear some people have had their brain broken by the existence of AI. " The AI wrote code which worked, for a problem the submitter had, which had not been solved by any human for a long time, and there is limited human developer time/interest/funding available for solving it. Dumping a mass of code (and work) onto maintainers without prior discussion is the problem[1]. If they had forked the repo, patched i…

You are under a delusion. I’m serious.
Post reply on HN