Linux and Git inventor Linus Torvalds discussed AI in software development in an interview earlier this month, describing himself as “fairly positive” about vibe coding, but as a way into computing, not for production coding where it would likely be horrible to maintain.
Torvalds was interviewed by Dirk Hohndel, head of open source at Verizon, at the Linux Foundation Open Source Summit in Seoul, South Korea, earlier this month.
Torvalds is technical lead and maintainer of the Linux kernel, but said that “for the last almost 20 years, I’ve not been a programmer.” As for Git, which he invented, “I really just look at it from the side.”
for a quick script to automate a task I really don’t see a problem, if you can directly see if the result is the good one, even if you don’t understand the script itself, but don’t try to publish something you don’t understand
Writing tests too. My recommendation to everyone interested in vibe coding who asks me is to instruct the AI to write the tests before the implementation.
Using it for writing tests is attractive because the way we generally test software sucks. Programs are written abstractly for an unimaginably large number of cases, but only tested for a finite few. It’s so ugly and boring and inexact. I’d be so giddy if a language/system came along that did formal methods properly, enabling me to formally prove correctness in every case. Programming is fun. Proofs are fun. Tests are not fun. And I’m here on Earth to have the most fun.
This is all to say that using LLMs to do the boring work of writing tests is a suboptimal solution for testing software. It fits a general pattern. Yes, you can learn X by having a conversation with an LLM, but I believe it will be a subpar experience compared to forcing yourself to read a professionally-written book on the subject.