Can AI-Written Code Enter the Linux Kernel?
KadriJibraan · x · 2026-07-17
The post debates whether Linus would accept AI-written code into the Linux kernel.
The author's central question: If AI-generated code has been rigorously tested and even meets Linus-level testing and review standards, should it still be rejected?
This fundamentally boils down to two engineering questions:
- Should the acceptance criteria for AI code be based purely on results rather than origin?
- Can AI coding tools truly integrate into the core development workflows of highly rigorous open-source projects?
Related event: Linus Says Linux Kernel Is Not an Anti-AI Project(18 posts)→
More from coding & agent
- Dev turns DJI Mavic into local AI security drone built with Opus 5.5 — alexcovo_eth · 2026-10-27
- Microsoft Research: ForkPilot cuts long-horizon agent compute by up to 59% — EliasEskin · 2026-10-27
- Cursor launches Agent SDK: agents as code with Markdown prompts and TypeScript tools — soleio · 2026-10-27
- Vibecheck, the 'usable formal methods' hackathon, sells out two floors in SF — spikedoanz · 2026-10-27
- How do you verify AI agent outputs beyond unit tests and LLM-as-judge? — Practical_Green5775 · 2026-10-27
- AI agents may soon become the only way to run code, not just write it — IgorCarron · 2026-10-27