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

LLM policy?

github.com

Post reply on HN
Print view View original

91–100 of 145 posts

Re: LLM policy?

#91

Post by theshrike79 »

troupo wrote: post #67
lynx97 wrote: post #46

Earlier quoted context omitted.

Just happened to me yesterday. I realized I'd really like to watch a long-form video on Huygens Clock. Something between a short (god damnit) and Quicksilver. Thought there must be something detailed. Nope, at least Youtube let me down. Or the search algo, who knows. Since they removed the "20+ minutes" button it has become basically useless to search on YT.

> Since they removed the "20+ minutes" button it has become basically useless to search on YT. A few days ago I definitely got into an A/B test where the search results were: - 5 shorts one under another - new section with one or two videos and one or two shorts - new section with five or more shorts in a horizontal layout - new section with videos of which 20-30% were shorts It's insane

They're pushing Shorts so fucking hard it makes me sick.

Even worse is that we're banning TikTok because it's bad for the kids (short form algorithmic content), Snapchat (similar thing + strangers creeping) and Instagram Stories (algorithm again).

BUT there is NO WAY for a parent to allow their kid to use Youtube AND block Shorts. (yes there are browser plugins etc, but how do you enforce them on a child?)

And from what I've seen the AI slop on Shorts is so fucking bad that it seems we just collectively forgot about Elsagate...

Re: LLM policy?

#92

Post by brabel »

It will be more interesting to see if and when AI becomes better than humans at coding, which seems to be coming close to reality, some projects may start accepting only AI contributions :D.

Re: LLM policy?

#93

Post by theshrike79 »

komali2 wrote: post #65
ddxv wrote: post #25

I've seen an interesting politically motivated one. It didn't appear to be a bot, just a user from China: https://github.com/umami-software/umami/pull/3678 The goal is "Taiwan" -> "Taiwan, Province of China" but via the premise of updating to UN ISO standards, which of course does not allow Taiwan. The comment after was interesting with how reasonable it sounds: "This is the technical specification of the ISO 3166-1…

One of these days I need to make a bot that scans FOSS repos for this kind of little pink nonsense behavior. The insecurity of wanting to call a place "country name, province of different country name" should alone be mocked. Imagine, "Ukraine, province of Russia," or "India, colony of The United Kingdom." Absurd on its face.

It's just information warfare, sign of the times.

Every little thing counts, even if it's just changing names in an open source app like that.

Re: LLM policy?

#94

Post by alyxya »

Maybe the solution is to counteract LLM pull requests with LLM first pass reviews. Obviously not a perfect solution, but LLMs should be good enough at detecting spam. This only needs to apply to first time contributors who haven't yet proven themselves.

Re: LLM policy?

#95

Post by theshrike79 »

kijin wrote: post #41

I have a simple rule: whenever I receive an issue or PR from an unfamiliar account, I skim the text and/or code and post 1-2 quick questions. If the submitter responds intelligently, then the issue warrants a more in-depth investigation. If not, the submitter clearly doesn't think that the issue is worth following up on, so it's not worth my time, either. The more code a PR contains, the more thorough knowledge of it…

> I have a simple rule: whenever I receive an issue or PR from an unfamiliar account, I skim the text and/or code and post 1-2 quick questions. If the submitter responds intelligently, then the issue warrants a more in-depth investigation. If not, the submitter clearly doesn't think that the issue is worth following up on, so it's not worth my time, either.

And if the submitter responds with "Great question! ...", what then? :D

Re: LLM policy?

#96

Post by imiric »

kijin wrote: post #41

I have a simple rule: whenever I receive an issue or PR from an unfamiliar account, I skim the text and/or code and post 1-2 quick questions. If the submitter responds intelligently, then the issue warrants a more in-depth investigation. If not, the submitter clearly doesn't think that the issue is worth following up on, so it's not worth my time, either. The more code a PR contains, the more thorough knowledge of it…

That's a reasonable first step, but a human can just as well feed your questions to the LLM, and post the responses. So you really have to be vigilant throughout your interactions with the author, or, if the PR is unsalvagable, save yourself some time and effort and reject it from the start.

> I'd rather talk with an intelligent LLM

There's no such thing.

Re: LLM policy?

#97

Post by SkiFire13 »

NamlchakKhandro wrote: post #82

Wouldn't you provide LLM friendly guidance material in your repo instead of spending effort on a pointless endeavor to ban them ?

If you plan to accept LLM contributions then a lot more effort will have to be spent on reviewing them.

Re: LLM policy?

#98

Post by brabel »

rester324 wrote: post #85
NamlchakKhandro wrote: post #82

Wouldn't you provide LLM friendly guidance material in your repo instead of spending effort on a pointless endeavor to ban them ?

I think OP wanted to have a proof that the submitter can demonstrate understanding of both the system and the code in the PR. So how would a guidance solve that? Also OP didn't want to ban them I believe

> I think OP wanted to have a proof that the submitter can demonstrate understanding of both the system and the code in the PR.

LLMs are really good at writing these. IF they think this will prove the author is human, they're mistaken.

Re: LLM policy?

#99

Post by SkiFire13 »

wilya7 wrote: post #80
o11c wrote: post #49

Earlier quoted context omitted.

If people can't make a good (PR, story, or whatever) without AI, they certainly can't do it with AI, because using the AI is strictly more difficult - it requires all the original skill, plus the skill to work around the AI's quirks. This is arguably isomorphic to Kernighan's Law: > Everyone knows that debugging is twice as hard as writing a program in the first place. So if you’re as clever as you can be when you wr…

Are you sure about that? Can you make the opposite case and steel-man it? Until you can, a stupid LLM will be smarter than you are. I can write a PR now. I can code now. Probably not as good as you can, but before LLMs I couldn't. I tried for decades learning to code. My brain is a Top-down network, I can see the big picture very quickly, but I cannot maintain focus to build bottom-up. Now I don't have to. I use LLMs…

It seems either your LLM is 10x better than anything I've ever used or your standards are 10x lower.

Re: LLM policy?

#100

Post by w10-1 »

Policy is a decent filter for consensual candidates, but mostly ineffective against incentives and automation.

The issue is exported costs: whether submitters make reviewers work too hard for the contribution value.

The policy/practice should focus first on making reviewer/developer's work easier and better, and second on refining submitter skills to become developers. The same is true for Senior/Junior relations internally.

So the AI company that solves how to pare AI slop down to clean PR's would meet a real and growing need, and probably also help with senior/junior relations as well.

Then you could meet automation with automation, and the incentives are aligned around improving quality of code and of work experience. People would feel they're using AI instead of competing with it.

Post reply on HN