← All stories
● Covered by 3 sources · 3 reportsMedium impact3 neutral

Linus Torvalds Notes AI-Driven Fixes Dominate Linux Kernel 7.4-rc2 Progress

🔄 Updated 4d ago — new reporting from GitHub Blog
New to BrevFeed? We gather this story from every outlet covering it into one summary — ranked by real-world impact, not just the latest headline — so you never miss what matters. What is BrevFeed? →

Key points

  • AI fixes drove much of the Linux kernel 7.4-rc2 progress.
  • BPF section saw more AI-provided fixes than reports.
  • Torvalds supports embracing AI contributions with quality control.
  • Suggests a turning tide for AI in open-source development.
  • Microsoft's MDASH AI system found 59 Linux kernel bugs.
  • One bug found by MDASH was 21 years old.
  • Linux CVEs average 27 per day through Nov. 2, 2026.
  • Windows Patch Tuesday reported 726 CVEs.
  • An ARM engineer and Linux kernel maintainer stepped down from general code review.
  • GitHub and Microsoft conducted the Codename MDASH pilot program.
  • Codename MDASH used AI to identify and suggest fixes for vulnerabilities in six open-source projects.
  • The Codename MDASH initiative resulted in 55 fixes from 99 reports.

AI Contributions in Linux Kernel 7.4-rc2

Linus Torvalds observed that a significant portion of the progress in the Linux kernel's 7.4-rc2 update was driven by AI-generated fixes. He categorized the changes into graphics, networking, and sound drivers; networking and BPF; and miscellaneous changes, noting that "much of this was driven by various AI fixes."

Shift in AI's Role for BPF

Alexei Starovoitov, the BPF maintainer, reported that the Berkeley Packet Filter (BPF) subsection of the kernel experienced a higher rate of AI-provided fixes compared to AI-generated bug reports. This suggests a potential evolution in how AI contributes to open-source projects, moving beyond just identifying issues to actively providing solutions.

Embracing AI with Quality Control

Torvalds' comments underscore his stance that AI-written contributions should be accepted, provided they meet the same quality control standards as human-generated code. This perspective indicates a willingness to integrate AI tools into the development workflow for projects with sufficient resources to manage and vet these contributions.

Implications for Open-Source Projects

While Torvalds noted that other areas of the kernel have not yet reached this point, he views this development as a sign that the "tide is starting to turn" regarding AI's role in open-source. This could offer a positive outlook for other open-source maintainers who have faced challenges with high volumes of low-quality AI-driven bug reports, suggesting that AI's utility may be improving.

Updates

🕒 2026-11-17 · new reporting from GitHub Blog
  • GitHub and Microsoft conducted the Codename MDASH pilot program.
  • Codename MDASH used AI to identify and suggest fixes for vulnerabilities in six open-source projects.
  • The Codename MDASH initiative resulted in 55 fixes from 99 reports.
🕒 2026-11-14 · new reporting from ZDNET
  • Microsoft's MDASH AI system found 59 Linux kernel bugs.
  • One bug found by MDASH was 21 years old.
  • Linux CVEs average 27 per day through Nov. 2, 2026.
  • Windows Patch Tuesday reported 726 CVEs.
  • An ARM engineer and Linux kernel maintainer stepped down from general code review.

✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →

The daily brief

One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.

One email a day. Unsubscribe in one click, any time.

Today's brief

Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.

~4 min · 3 stories · Nov 21

▶ Play today's brief Listen on Spotify

New every morning, and the back catalogue is archived by date.

How outlets covered it

GitHub and Microsoft conducted a pilot program, Codename MDASH, which used AI to identify and suggest fixes for vulnerabilities in six open-source projects. The initiative aimed to reduce the burden on maintainers by providing verified reports with proposed solutions, resulting in 55 fixes from 99 reports.

Microsoft's AI system, MDASH, identified 59 Linux kernel bugs, including a 21-year-old flaw, contributing to a surge in bug reports. This influx, largely from AI programmers, is overwhelming Linux kernel maintainers and Windows developers, who struggle to review and fix them. The increased volume led one ARM engineer and Linux kernel maintainer to step down from general code review.

Linus Torvalds stated that AI-generated fixes contributed significantly to the progress in the Linux kernel's 7.4-rc2 update, particularly in the Berkeley Packet Filter (BPF) section. This indicates a potential shift where AI is providing more solutions than just bug reports, suggesting a maturing of AI contributions in well-resourced open-source projects.