On 7/24/26 4:12 AM, Simon Jakobi via ghc-devs wrote:
I'm not sure if there have been any problems with LLM-generated reviews so far? My suggestion would be to drop the responsibility requirement for clearly marked LLM-generated MR reviews.
The linux kernel has been using an LLM patch review system called "sashiko". It definitely finds bugs, although not everything it highlights is a real bug. There has been some debate about who should pay the cost of checking its output -- patch approvers (maintainers) or patch submitters -- and whether a response to the review by submitters is optional or required. Sashiko sometimes find bugs in adjacent code, but submitters don't want to have to fix bugs they didn't create. See: "Debating the role of large language models in the kernel community" -- there's a section called "Email from Sashiko" https://lwn.net/SubscriberLink/1083275/d5518174ec4dcbcb/ -BenRI