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.”
It’s also useful for prototyping. Put something together quickly as a proof of concept and then do it the proper way. That is how I mostly use it at least.
important context:
Regarding vibe coding, Torvalds described himself as “fairly positive” – but not for kernel development. Computers have become more complicated than when he learned to code and was “typing in programs from computer magazines.” Vibe coding, he said, is a great way for people to “get computers to do something that maybe they couldn’t do otherwise.”
This is despite the fact that vibe coding “may be a horrible, horrible idea from a maintenance standpoint.”
This is exactly the brand of low-key shade I’ve come to expect from him
That sounds about right.
Here is the full interview: https://www.youtube.com/watch?v=tWx769t1JKg
deleted by creator
Pretty reasonable take IMO
I can see how it can be a useful tool to get people into dev
You need to back that up with real learning though
If you can’t/don’t review and completely understand every line of code you submit to a project yourself, you should not be surprised if the project owner tells you to take a long walk towards the Mariana trench
As someone who is not a great coder. I can help in cases of double checking in addition to learning.
I made a USB HID report & device descriptor, it works fine everywhere except it causes KDE settings Game Controller menu to segfault when identifying USB devices.
I know there is a 99% chance that it is due to my descriptor being wrong. AI found my mistake of carrying over the logical min/max number of bits to the report size and my logical minimum was 1 too small. Haven’t had a chance to test yet, but maybe I saved the KDE maintainers annoyance of a false alarm bug report.
But sounds like there is still a bug, KDE settings shouldn’t segfault with malformed reports/descriptors. Might want to write a bug report or do PR yourself.
And that issue existed before vibr coding too.
deleted by creator
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.
