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

A standard protocol to handle and discard low-effort, AI-Generated pull requests

406.fail

Post reply on HN
Print view View original

61–70 of 129 posts

Re: A standard protocol to handle and discard low-effort, AI-Generated pull requests

#61

Post by Balinares »

danpalmer wrote: post #50

I recently had a quandary at work. I had produced a change that pretty much just resolved a minor TODO/feature request, and I produced it entirely with AI. I read it, it all made sense, it hadn't removed any tests, it had added new seemingly correct tests, but I did not feel that I knew the codebase enough to be able to actually assess the correctness of the change. I want to do good engineering, not produce slop, bu…

Aside from anything else, you have good engineering instincts, and I wish more people in the industry were like you.

Re: A standard protocol to handle and discard low-effort, AI-Generated pull requests

#62

Post by danpalmer »

Balinares wrote: post #61
danpalmer wrote: post #50

I recently had a quandary at work. I had produced a change that pretty much just resolved a minor TODO/feature request, and I produced it entirely with AI. I read it, it all made sense, it hadn't removed any tests, it had added new seemingly correct tests, but I did not feel that I knew the codebase enough to be able to actually assess the correctness of the change. I want to do good engineering, not produce slop, bu…

Aside from anything else, you have good engineering instincts, and I wish more people in the industry were like you.

Thanks, doing my best. It's one of the reasons I want to get more of my AI-skeptical colleagues onboard with AI development. They're skeptical for good reasons, but right now so much progress is being driven by those who lack skills, taste, or experience. I understand those with lots of experience being skeptical at the claims, I like to think I am too, but I think there's clearly something here, and I want more people who are skeptical to shape the direction and future of these technologies.

Re: A standard protocol to handle and discard low-effort, AI-Generated pull requests

#65

Post by atls »

yorwba wrote: post #53
dotancohen wrote: post #48

Earlier quoted context omitted.

Are the PRs not accompanied by test cases? Do the README changes not document the expected benefit?

You're replying to a bot account https://news.ycombinator.com/item?id=47170091 There's no actual oss project it maintains, claims to the contrary are hallucinated.

Oh, the irony

Re: A standard protocol to handle and discard low-effort, AI-Generated pull requests

#66

Post by mglvsky »

I prefer this policy: https://github.com/ghostty-org/ghostty/blob/main/AI_POLICY.m...

> If you can't explain what your changes do and how they interact with the greater system without the aid of AI tools, do not contribute to this project.

edit: added that quote

Re: A standard protocol to handle and discard low-effort, AI-Generated pull requests

#69

Post by msylvest »

0cf8612b2e1e wrote: post #6

The keywords "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted exactly as how much we do not want to review your generated submission. I know it is in jest, but I really hate that so many documents include “shall”. The interpretation of which has had official legal rulings going both ways. You MUST use less ambiguo…

Around 1990 I attended ISO/JTC1 meetings generating standards for data communication. I still recall my surprise over the heated arguments over these words between the UK and the US delegations. (I'm from Denmark). In particular 'shall' and 'should' meant different things in English and American languages. ISO's first standard, ISO 1, states that ISO Standards shall be written in English so we had to do that, US delegation too. Similarly Scott Bradner stated in RFC 2219 how American conventions should be followed for future IETF STDs.

So I'm confident that the word 'shall' has a strong meaning in English; whether it has too in American legalese I cannot tell.

Re: A standard protocol to handle and discard low-effort, AI-Generated pull requests

#70

Post by robinsonb5 »

fecal_henge wrote: post #64

Can I ask, why are people doing this in the first place? What is their motive to have an agent review code and make pull requests?

To quote TFA: "...outputs strictly designed to farm green squares on github, grind out baseless bug bounties, artificially inflate sprint velocity, or maliciously comply with corporate KPI metrics".
Post reply on HN