Linus Torvalds Defends AI Coding in Linux Kernel

Linus Torvalds, the creator and top-level maintainer of the Linux kernel, has firmly stated his support for the integration of AI-powered coding tools into the open-source project. In a detailed post on the Linux kernel mailing list this week, Torvalds declared that Linux is "not one of those anti-AI projects." He directly addressed critics, stating, "if somebody has issues with that, they can do the open-source thing and fork it. Or just walk away."

This stance comes amidst ongoing discussions about the use of AI in software development, particularly concerning large language model-generated code. The debate has created divisions between developers who embrace these tools and those who oppose their use in their projects. Torvalds's comments signal a clear direction for the Linux kernel's development, indicating a willingness to adopt AI to enhance the project.

The discussion was particularly highlighted by the use of Sashiko, an "agentic Linux kernel code review system." Its creators claim that in testing, Sashiko can independently identify 53.6 percent of bugs that would typically be addressed by human coders in subsequent commits. However, the tool is also noted for its potential to generate "false positive" bug reports, which can consume maintainers' time. Sashiko's developers estimate that the rate of these false positives falls "well within the 20% range."