Using Claude Code to modernize a 25-year-old kernel driver – Dmitry Brant
Using Claude Code to modernize a 25-year-old kernel driver – Dmitry Brant
10 comments
-
And a few seconds latter you get this. Looks like the person using it have at least some idea of what they are doing, so I hope for the best. And might actually end up using this work at some point.
-
Looks like the person using it have at least some idea of what they are doing
This is something which I have been saying from a year back, albeit a different form -- "I only ask questions to LLMs if I already know the answer".
They are not supposed to replace coders, but kind of boost their productivity.
This usecase is also quite good.
- It's not critical; not many people are using QICs
- It's not hard, but just boring
- No existing human solution
-
"I only ask questions to LLMs if I already know the answer"
Not a developer here. I've been thinking about this because I hoped LLMs would be able to help me learn things at first, like a patient tutor I can ask all my stupid questions and it'll never get annoyed with me. Since it can't do that though, because it lies all the time, I don't think I have a use case for it at all... About all it can do for me is rewrite or summarise English, and it doesn't even do a particularly good job of that most of the time so I end up saving time by doing that work myself anyway. I suppose it's pretty good at translating, but I haven't tried it for that as I don't have a lot of call to speak foreign languages.
-
I'm pretty sure bugs were accepted into the Linux kernel well before the existence of LLMs.
-
But using a bug generator is a new low.
-
-
10 comments