Linux kernel engineer introduces Sashiko code review system
Jump to main content
Search
REG AD
AI + ML
Sashiko: AI code review system for the Linux kernel spots bugs humans miss
Beats getting roasted on the mailing list
Richard Speed
Richard<br>Speed
Published<br>fri 20 Mar 2026 // 09:30 UTC
AI is coming to the Linux kernel in the form of a code review system - not code submissions.
Announced on LinkedIn by Roman Gushchin, a Linux kernel engineer at Google, Sashiko is a tool written in Rust for spotting bugs and screening code.
Gushchin said: "In my measurement, Sashiko was able to find 53 percent of bugs based on a completely unfiltered set of 1,000 recent upstream issues based on 'Fixes:' tags (using Gemini 3.1 Pro). Some might say that 53 percent is not that impressive, but 100 percent of these issues were missed by human reviewers."
REG AD
The use of AI in code submissions is controversial in the open source community, however, a tool like Sashiko could go some way toward easing the burden on maintainers dealing with a wave of code reviews.
REG AD
MORE CONTEXT
Systemd 260 kills SysV, tells AI not to misbehave
Linux Foundation kicks off effort to shield FOSS maintainers from AI slop bug reports
Bcachefs creator insists his custom LLM is female and 'fully conscious'
Godot maintainers struggle with 'draining and demoralizing' AI slop submissions
Sashiko works by ingesting patches from a mailing list. It analyzes them then gives feedback to the maintainers and developers. According to its authors, "the quality of reviews is high... the rate of false positives is harder to measure, but based on limited manual reviews it's well within 20 percent range, and the majority of it is a gray zone."
The authors are upfront about the privacy and code-sharing aspects. Sashiko sends data and code to whatever LLM provider it has been configured for. It has been most tested with Gemini Pro 3.1, but should work with Claude and other LLMs. However, there are costs involved in running it. In the case of the Linux Kernel Mailing List, Google is footing the bill.
Gushchin said: "We've been using it internally at Google for some time, and it helped to discover a large number of real issues."
Sashiko belongs to the Linux Foundation and looks like a useful tool – an application of agentic AI that may provoke less handwringing than code submissions. ®
software<br>linux<br>ai and ml<br>ai
REG AD
Networks
Telegram founder accuses Meta of sabotaging access in India with BGP hijacks
Allegations of fake routes are fake news, says Indian telco Jio
Security
Everything's bigger and better in Texas – even data breaches
Hunting and fishing license incident catches 3M residents
ZTE and China Telecom Guangdong advance cross‑vendor IP network simulation pilots, paving the way for intelligent network operations
PARTNER CONTENT: Leveraging >95% digital twin fidelity and multi-vendor collaboration to eliminate network change risks and achieve zero-error O&M
DevOps
Vercel debuts eve open source agent framework, tries to fix shadow AI with Passport
Cost premium of using AWS indirectly via Vercel is mitigated by more efficient use of compute resources, CTO claims
PAAS AND IAAS
Graviton 5 impresses, but please, for the love of all that's holy, stop calling them 'AI chips'
AWS better at running chip fabs than their mouths
PERSONAL TECH
Microsoft's latest Windows bug belongs in the Recycle Bin
File deletion dialog swaps recognizable names for internal gibberish
MOST POPULAR
security
Feds freaked over Fable 5 after simple 'fix this code' prompt, not jailbreak, says researcher
ON-PREM
Amazon owns up to using 2.5bn gallons of H2O in its bit barns last year
science
AI and brain-computer interface allow speechless ALS patient to work a full-time job
PUBLIC SECTOR
Capita is about to sail past deadline to fix civil service pensions scheme
virtualization
Tesco is sprinting to quit VMware and Broadcom despite rapid migration risks
AI
DEvops
Vercel debuts eve open source agent framework, tries to fix shadow AI with Passport
Cost premium of using AWS indirectly via Vercel is mitigated by more efficient use of compute resources, CTO claims
security
Rights groups brand Home Office's AI age guesser for asylum-seekers as biased and inaccurate
Campaigners say tech is unable to reliably distinguish between kids and adults at the boundary where use is planned
ai and ml
Devs in the trenches are stressed from the mandate to automate everything, but Render thinks it can help
San Francisco plays host to hosting company's Localhost conference
ai + ml
Midjourney pivots from AI image generation to body scanning medical spa where patients bathe in 'golden light'
The underlying technology is real...and borrowed from a partner the company failed to mention
AI AND ML
Committed skeptic finds himself warming to new Amazon AI products that actually don't suck
Ed's note to Corey: Blink once if you're safe, twice if you're in...