Sashiko
Hacker ApprovedRanked 7 of 17 code review tools by recommenders
Google's agentic AI reviewer for Linux kernel patches; people praise its focus on real bugs like race conditions and few opinion-based comments. Common caveat: it burns through many tokens.
Google's agentic AI reviewer for Linux kernel patches; people praise its focus on real bugs like race conditions and few opinion-based comments. Common caveat: it burns through many tokens.
18 people gave an opinion
- recommend it
- 14
- criticize it
- 4
- approval share
- 78%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 14 people recommend itNeeds 10 or more, met.
- 3.5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 5 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Useful, good results overall
“That is both really useful and a great example of why they should have stopped writing code in C decades ago.”
Comment from 18 Mar 2026 in “Google Engineers Launch "Sashiko" for Agentic AI Code Review of the Linux Kernel” “The kernel now has AI tooling heavily integrated into patch review workflows as well with quite good results.”
Comment from 15 Oct 2026 in “Libreboot 26.10 "Ominous Olive" released with UEFI, Chromebook support” “It's very good, but it eats tokens like crazy.”
Comment from 11 Sep 2026 in “Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra” - Comment from 22 Apr 2026 in “Linus Torvalds on AI code review: Anybody who thinks all AI is slop is in denial”
Catches race conditions and obscure bugs
“It can detect very obscure race conditions, stack leaks and other bugs that could cause a kernel panic.”
Comment from 19 Jun 2026 in “Linux Maintainer Greg Kroah-Hartman Says AI Tools Now Useful, Finding Real Bugs” “Sashiko gets the big picture and its main concerns are race conditions”
Comment from 26 Jun 2026 in “Linux Maintainer Greg Kroah-Hartman Says AI Tools Now Useful, Finding Real Bugs”
What people warn about
Each mark is one comment
Burns through many tokens
“Sashiko is a great system, but it can burn through tokens like there's no tomorrow.”
Comment from 9 Oct 2026 in “Why isn't the industry freaking out about DeepSeek 4.1 Flash?” “It's very good, but it eats tokens like crazy.”
Comment from 11 Sep 2026 in “Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra”
Other code review tools people recommend
The four most recommended other code review tools, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| GitHub Stacked PRs | 64 | 63 | 50% | 3 | — | — |
| Gerrit | 60 | 12 | 83% | 12 | — | Approved |
| Graphite code review | 52 | 16 | 76% | 9 | — | Approved |
| CodeRabbit | 34 | 32 | 52% | 11 | — | — |
| SashikoThis page | 14 | 4 | 78% | 5 | — | Approved |
What people said
All 21 comments that mention it, newest first. Each links to the original comment.
“The kernel now has AI tooling heavily integrated into patch review workflows as well with quite good results.”
“Sashiko is a great system, but it can burn through tokens like there's no tomorrow.”
“a connection that drops mid-response is treated as a permanent error rather than retried”
“It's very good, but it eats tokens like crazy.”
“AI code review sucks. It does a bad job.”
“Sashiko gets the big picture and its main concerns are race conditions”
“It can detect very obscure race conditions, stack leaks and other bugs that could cause a kernel panic.”
“Sashiko tends to be quite good.”
“that direction actually seems to be helping”
“a new tool to transfer people's skill - which have to be paid - into Google's models - which they can sell”
“with the main bottleneck being false positives”
“This tool is built by actual Google devs who are active on the kernel mailing list”
“I'd bet 90% of the actual useful work this agent does is just dumb pattern-matching”
“Looks like a great new tool to help ship less bugs!”
“the demo video sold me more than the text”
“I think it's just a dashboard, not meant to be used as is.”
“Looks cool, but this site is a bit difficult for me to grok.”
“That is both really useful and a great example of why they should have stopped writing code in C decades ago.”
“My experience with using the prototype is that it very rarely comments with "opinions" it only identifies functional issues.”
“I'm very glad they're not spamming the mailing list.”
“This looks like it's doing style and structure changes, which for a codebase this size is going to add drag”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.