{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiebczfhdhajx5i7coagly67qsrxuavbinahf4csbzejk5ufriuuje",
"uri": "at://did:plc:b3tz6srl4ochk2wxn6dv6xpy/app.bsky.feed.post/3mijh3t7pe4w2"
},
"path": "/Articles/1065971/",
"publishedAt": "2026-04-02T13:27:33.000Z",
"site": "https://lwn.net",
"tags": [
"a blog\npost",
"the recent debate"
],
"textContent": "Brian \"bex\" Exelbierd has published a blog\npost exploring follow-up questions raised by the recent debate about the use of the LLM-based review tool Sashiko in the memory-management subsystem. His main finding is that Sashiko reviews are bi-modal with regards to whether they contain reports about code not directly changed by the patch set — most do not, but the ones that do often have several such comments.\n\n> **Hypothesis 1: Reviewers are getting told about bugs they didn't create.** Sashiko's review protocol explicitly instructs the LLM to read surrounding code, not just the diff. That's good review practice — but it means the tool might flag pre-existing bugs in code the patch author merely touched, putting those problems in their inbox.\n>\n> **Hypothesis 2: The same pre-existing bugs surface repeatedly.** If a known issue in a subsystem doesn't get fixed between review runs, every patch touching nearby code could trigger the same finding. That would create a steady drip of duplicate noise across the mailing list.\n>\n> I pulled data from Sashiko's public API and tested both.",
"title": "Exelbierd: What's actually in a Sashiko review?"
}