- Linus Torvalds says he does not recommend AI-assisted coding for kernel development
- V”ibe coding” helps beginners perform tasks that they cannot complete independently
- Torvalds says vibration coding creates long-term maintenance problems in core systems
Linus Torvalds has addressed the use of AI-assisted coding, offering a measured stance that separates experimentation from production development.
The godfather of Linux acknowledged that some developers may already be exploring such tools for kernel work, although he is not using or testing them personally.
Torvalds says AI tools have caused outages through crawlers scraping source code from kernel.org, leading to fabricated reports of vulnerabilities and bugs.
“Vibe coding” as an entry point, not a basis for critical code
While Torvalds noted that these issues affect the Linux kernel, he suggested that the situation is more serious for other projects, citing curl as an example.
Torvalds described himself as a proponent of so-called “vibration coding” when it helps users learn to program or execute tasks they couldn’t complete without help.
He contrasted this with his early experiences writing print magazine programs, arguing that computing is now much more complex.
However, he reiterated that this approach should not be applied to mainframe systems such as the Linux kernel, where it could create long-term maintenance problems, and suggested that using vibe coding in such environments would be a poor choice, even if it seems attractive for rapid development.
Torvalds also noted the tension created by automated crawlers, which not only indiscriminately extract code but also generate low-quality reports that kernel maintainers must address.
He expressed frustration with links leading to irrelevant or misleading content. During the discussion, he noted that he rarely responds to emails, although he typically reads messages sent to him.
The conversation expanded further to include the integration of Rust into the kernel, the evolution of its feature over two decades, and occasional friction with maintainers who resist the adoption of new languages.
When asked about software engineering layoffs attributed to AI, Torvalds called the problem complex and suggested that significant results might not be clear for a few years.
“It’s a complicated question…AI is just another tool, in the same way that compilers free people from writing assembly code by hand and greatly increase productivity, but they don’t make programmers go away,” Torvalds said.
He suggested that the industry could eventually normalize AI and treat it as routine infrastructure used alongside hosting environments and cloud storage systems, rather than a topic that attracts constant attention.
His comments imply that software development could bifurcate into deeply limited exploratory workflows and production pipelines.
The expectation is that mission-critical code can remain tightly controlled, while rapid experimentation gains traction elsewhere.
Long-term adoption may depend on whether automated systems deliver consistent accuracy rather than superficial results.
Through registration
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Be sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
