Toward a policy for machine-learning tools in kernel development

machine-learning tools in kernel development

they mean LLMs for code generation. For a moment I was hoping something a bit more interesting like self-tuning kernel optimizations or such.

Two things I’ve found particularly interesting. First, some rough stats on the usefulness of automated code review:

Alexei Starovoitov said that, within Meta, automated tools have been producing good reviews about 60% of the time, with another 20% having some good points. Less than 20% of the review comments have been false positives.

And it looks like AI assisted patches are expected to make it to the kernel?

Torvalds, though, pointed out that developers have long been complaining about a lack of code review; LLMs may just solve that problem. They are not writing code at this point, he said, though that will likely happen at some point too. Once these systems start submitting kernel code, we will truly need automated systems to review all that code, he said.