I don't want your PRs anymore

https://dpc.pw/posts/i-dont-want-your-prs-anymore/

cross-posted from: https://lemmy.bestiver.se/post/1062108

Comments

-9 points · 8 comments · view on lemmy.world

8 Comments

amio@lemmy.world · 18 pts · 114d (3 replies)

"I used to have to check PRs and with LLMs I implicitly trust there's no malicious shit in them"???

Yeah ok bro

coolie4@lemmy.world · 16 pts · 114d (1 reply)

I mean... I think they're right though. LLMs aren't intentionally malicious. They're just incompetent.

onlinepersona@programming.dev · 7 pts · 114d

End result is the same.

CameronDev@programming.dev · 0 pts · 114d

While I still need to review LLM-generated code, I generally don't have to worry about it being malicious the way an unknown contributor's code could be.

AceSLS@ani.social · 14 pts · 114d

Prefering a LLM's code over a Human's is just a wild statement lmao

ultimate_worrier@lemmy.dbzer0.com · 12 pts · 114d
[ removed ]
aev_software@programming.dev · 6 pts · 114d

How much time does it take to reject a pull request because you don't understand it?

We see a project like curl outright banning AI-made / assisted PRs due to the overwhelming burden those put on the human reviewers. It's a DDoS aimed at people, either to shut them down or to force them into using yet another LLM to automate reviews and merges.

The danger is real. Overwhelming the people who have maintained the backbones of our digital infrastructure will result in a total collapse of that infrastructure. How can ad brokers continue to profit if there's no way to get the ad displayed to prospective consumers? How can totalitarian regimes sway public opinion in a foreign nation if they can't share their memes and propaganda?

remon@ani.social · 6 pts · 114d

That's a lot of text for saying "I suck at code reviews".

aev_software@programming.dev · 1 pts · 114d

How much time does it take to reject a pull request because you don't understand it?

We see a project like curl outright banning AI-made / assisted PRs due to the overwhelming burden those put on the human reviewers. It's a DDoS aimed at people, either to shut them down or to force them into using yet another LLM to automate reviews and merges.

The danger is real. Overwhelming the people who have maintained the backbones of our digital infrastructure will result in a total collapse of that infrastructure. How can ad brokers continue to profit if there's no way to get the ad displayed to prospective consumers? How can totalitarian regimes sway public opinion in a foreign nation if they can't share their memes and propaganda?