Comment

Comment on New ntfy.sh v2.18.0 was written by AI

It looks like that tool is more or less built by a single developer (you already trust their judgment anyways!), and even though the code came through in a single PR it was a merge from a branch that had 79 separate commits: github.com/binwiederhier/ntfy/pull/1619

Also glancing through it a bit, huge portions of that are straightforward refactors or even just formatting changes caused by adding a new backend option.

I’m not going to say it’s fine, but they didn’t just throw Claude at a problem and let it rewrite 25k lines of code unnecessarily.

source

Sort:hotnew top

mudkip@lemdro.id ⁨15⁩ ⁨hours⁩ ago
Any AI usage immediately discredits the software for me, because it calls into question all of their past and future work.

source
- blarg_dunsen@sh.itjust.works ⁨15⁩ ⁨hours⁩ ago
  Oh boy, do I have bad news about 90% of the internet for you…
  
  source
  - mudkip@lemdro.id ⁨15⁩ ⁨hours⁩ ago
    Linus sent an email recently to the Kernel Mailing List trashing AI slop and rejecting AI generated patches. The fact that he used it to play around with a script doesn’t invalidate the fact that he distrusts code written by LLMs when it actually matters.
    
    source
    5gruel@lemmy.world ⁨15⁩ ⁨hours⁩ ago
    you mean this statement? theregister.com/…/linus_versus_llms_ai_slop_docs/…
    
    If yes, your statement does not really match what Linus said.
    
    source
fccview@lemmy.world ⁨5⁩ ⁨hours⁩ ago
Yeah, I mean, with or without AI, I’ve always only had a big pull request for releases, from a stable release branch into the main branch, the release branch would be a merge of various branches or just be worked on directly on various stages.

One big pull request doesn’t really mean anything.

source
prenatal_confusion@feddit.org ⁨1⁩ ⁨day⁩ ago
Wow a differentiated opinion on AI use :)

source
sloppy_diffuser@sh.itjust.works ⁨22⁩ ⁨hours⁩ ago
Something like graphite.com to create stacked PRs that are reviewable probably would have helped. Can be replicated with local LLMs or remote AI providers with locally configured agentic workflows. Never used graphite personally, but I’ve seen some open source maintainers use it to split up large PRs.

source