Linux

15100 readers

869 users here now

A community for everything relating to the GNU/Linux operating system (except the memes!)

Also, check out:

Original icon base courtesy of lewing@isc.tamu.edu and The GIMP

founded 3 years ago

MODERATORS

Ategon@programming.dev

anzo@programming.dev

dwraf_of_ignorance@programming.dev

The AI Pascal’s Wager: Should you accept contributions generated by LLMs in your Open Source project? (ploum.net)

submitted 2 days ago by ProdigalFrog@slrpnk.net to c/linux@programming.dev

33 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] hendrik@palaver.p3x.de 2 points 2 days ago* (last edited 2 days ago)

Yes. I think that's regularly the reason why I decline AI contribution/assistance. Quality just isn't great. The coding agents just rewrite way too much code. And the reasoning in the PRs or backlog of the agent is regularly missing the bigger picture, or besides the point. It's really hard to get good quality out of an LLM and most people (including me) don't manage to pull it off. At least for more complex stuff. I can do one-off things with AI or cobble a website together with some Javascript included.