Conversation
James Morris
jmorris
Anyone using Claude for kernel / system level development? How do you make the most of it?
I like the idea of having something which can do deep code review - eg. does this code actually do what I specified? Are there any bugs? Obviously - but also not so obviously in a complex system. Have I broken layering abstractions? Is the code maintainable? What does the maintainer of this subsystem expect? Etc.
I like the idea of having something which can do deep code review - eg. does this code actually do what I specified? Are there any bugs? Obviously - but also not so obviously in a complex system. Have I broken layering abstractions? Is the code maintainable? What does the maintainer of this subsystem expect? Etc.
2
0
1
@jmorris
Personally I use it to rephrase/proofread text or quickly look something up (as a first resort before grepping through git history or mailing list archive). I heard AUTOSEL uses LLMs to determine whether a patch should be backported to -stable or not.
But at this point, I really hope no one sends any code written or guided by AI to the mailing list. It might be fine to get shallow reviews of human-written code from LLMs, but I doubt they're capable of writing sane kernel code or offering deep reviews.
Personally I use it to rephrase/proofread text or quickly look something up (as a first resort before grepping through git history or mailing list archive). I heard AUTOSEL uses LLMs to determine whether a patch should be backported to -stable or not.
But at this point, I really hope no one sends any code written or guided by AI to the mailing list. It might be fine to get shallow reviews of human-written code from LLMs, but I doubt they're capable of writing sane kernel code or offering deep reviews.
0
0
1