Checked who the author was, should have guessed… SJVN. He certainly has a flair for taking something relatively small, that a solution already exists for and suggesting something bureaucratic, unnecessary, and completely outside his technical competence. This is one of those things that the kernel devs can, and will solve when it’s a real problem. Random journalists and armchair experts can wait till they’re called upon.
I’m pleased to announce the release of AUTOSEL, a complete rewrite of the
stable kernel patch selection tool that Julia Lawall and I presented back in
2018[1]. Unlike the previous version that relied on word statistics and older
neural network techniques, AUTOSEL leverages modern large language models and
embedding technology to provide significantly more accurate recommendations.
…
Would be great to hear more. My very subjective feeling is that the last batch of AUTOSEL is much worse than the previous.
Easily 50% of false positives.
Seems the newly rewritten kernel review tools wasn’t what waa expected as an upgrade.
They found 1 (one!) commit in git, and report that’s it’s all over the kernel. Nice journalism.
That’s ZDNET!
Checked who the author was, should have guessed… SJVN. He certainly has a flair for taking something relatively small, that a solution already exists for and suggesting something bureaucratic, unnecessary, and completely outside his technical competence. This is one of those things that the kernel devs can, and will solve when it’s a real problem. Random journalists and armchair experts can wait till they’re called upon.
“it’s one horse and they report that it’s all over troy. nice journalism” - people living in troy
I mean, read into what they wrote about:
…
Seems the newly rewritten kernel review tools wasn’t what waa expected as an upgrade.
https://lists.linaro.org/archives/list/linux-stable-mirror@lists.linaro.org/thread/EJWMRUH2JTI34CPWVZZG62XJ7HMIH5WT/
Have you read the article? It’s also about the tools and general discussion about LLMs in kernel development.