I mean, read into what they wrote about:
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.