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

I don't want your PRs anymore

dpc.pw

Post reply on HN
Print view View original

11–20 of 148 posts

Re: I don't want your PRs anymore

#11

Post by stavros »

lou1306 wrote: post #2

> On top of that, there are a lot of personal and subjective aspects to code. You might have certain preferences about formatting, style, structure, dependencies, and approach, and I have mine. 95% of this is covered by a warning that says "I won't merge any PR that a) does not pass linting (configured to my liking) and b) introduces extra deps" > With LLMs, it's easier for me to get my own LLM to make the change and…

No. When code is cheaper to generate than to review, it's cheaper to take a (well-written) bug report and generate the code yourself than to try to figure out exactly what the PR does and whether it has any subtle logical or architectural errors.

I find myself doing the same, nowadays I want bug reports and feature requests, not PRs. If the feature fits in with my product vision, I implement and release it quickly. The code itself has little value, in this case.

Re: I don't want your PRs anymore

#12

Post by porphyra »

Maybe instead of submitting PRs, people should submit "prompt diffs" so that the maintainer can paste the prompt into their preferred coding agent, which is no doubt aware of their preferred styles and skills, and generate the desired commit themselves.

Re: I don't want your PRs anymore

#16

Post by OkayPhysicist »

lou1306 wrote: post #2

> On top of that, there are a lot of personal and subjective aspects to code. You might have certain preferences about formatting, style, structure, dependencies, and approach, and I have mine. 95% of this is covered by a warning that says "I won't merge any PR that a) does not pass linting (configured to my liking) and b) introduces extra deps" > With LLMs, it's easier for me to get my own LLM to make the change and…

> 95% of this is covered by a warning that says "I won't merge any PR that a) does not pass linting (configured to my liking) and b) introduces extra deps"

Maybe I'm not up to date with the bleeding edge of linters, but I've never seen one that adequately flags

    let out = []
    for(let x of arr){
      if(x > 3){
        out.append(x + 5)
      }
    }
Into

   let out = arr
             .filter(x => x > 3)
             .map(x => x + 3)
There's all sorts of architectural decisions at even higher levels than that.

Re: I don't want your PRs anymore

#17

Post by acedTrex »

porphyra wrote: post #12

Maybe instead of submitting PRs, people should submit "prompt diffs" so that the maintainer can paste the prompt into their preferred coding agent, which is no doubt aware of their preferred styles and skills, and generate the desired commit themselves.

Why would anyone bother doing this, prompts are not code, they are not shareable artifacts that give the same results.

Re: I don't want your PRs anymore

#18

Post by LostMyLogin »

pydry wrote: post #6
jerkstate wrote: post #3

Thats fine, the cost for me to re-implement your code is nearly zero now, I don’t have to cajole you into fixing problems anymore.

Given the supposed quality of top flight models there ought to be a lot more people forking open source projects, implementing missing features and releasing "xyz software that can do a and b". Somehow it's not really happening.

Because it still requires the desire to do it.

Re: I don't want your PRs anymore

#19

Post by teach »

stavros wrote: post #11
lou1306 wrote: post #2

> On top of that, there are a lot of personal and subjective aspects to code. You might have certain preferences about formatting, style, structure, dependencies, and approach, and I have mine. 95% of this is covered by a warning that says "I won't merge any PR that a) does not pass linting (configured to my liking) and b) introduces extra deps" > With LLMs, it's easier for me to get my own LLM to make the change and…

No. When code is cheaper to generate than to review, it's cheaper to take a (well-written) bug report and generate the code yourself than to try to figure out exactly what the PR does and whether it has any subtle logical or architectural errors. I find myself doing the same, nowadays I want bug reports and feature requests, not PRs. If the feature fits in with my product vision, I implement and release it quickly. T…

I definitely trust my local LLM where I know the prompt that was used. Even if the code generated ends up being near-identical, it'll be way faster to review a PR from someone or something I trust than from some rando on the Internet
Post reply on HN