- Linus Torvalds says he does not recommend AI-assisted coding for kernel development
- V”ibe coding” helps beginners to complete tasks they cannot do independently
- Torvalds says that vibe coding creates long-term maintenance problems in core systems
Linus Torvalds has addressed the use of AI-assisted coding, offering a measured attitude that separates experimentation from production development.
The Linux godfather acknowledged that some developers may already be exploring such tools for kernel work, though he doesn’t personally use or test them.
Torvalds says AI tools have caused disruption through crawlers that collect source code from kernel.org, leading to fabricated reports of vulnerabilities and bugs.
“Vibe coding” as an entry point, not a foundation 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 supportive of so-called “vibe coding” when it helps users learn programming or perform tasks they couldn’t do without help.
He contrasted this with his early experiences writing programs from print magazines and argued that computing is now far more complex.
However, he reiterated that this approach should not be applied to kernel systems such as the Linux kernel, where it could create long-term maintenance problems, and suggested using vibe coding in such environments would be a poor choice, even if it seems appealing for rapid development.
Torvalds also noted the load created by automated crawlers, which not only pull code arbitrarily, but also generate low-quality reports that core maintainers must address.
He expressed frustration with links leading to irrelevant or misleading content. During the discussion, he noted that he rarely replies to emails, although he typically reads messages sent to him.
The conversation further expanded to include Rust integration into the core, the evolution of his role over two decades, and occasional friction with maintainers resistant to new language adoption.
When asked about layoffs in software technology attributed to AI, Torvalds called the issue complex and suggested that meaningful results may only be clear years from now.
“It’s a complicated question…AI is just another tool, in the same way that compilers freed people from writing assembly code by hand and increased productivity enormously, but did not make programmers disappear,” Torvalds said.
He suggested that the industry may eventually normalize artificial intelligence and treat it as routine infrastructure used with cloud hosting environments and cloud storage systems rather than a subject that attracts constant attention.
His comments suggest that software development can be divided into exploratory workflows and deeply constrained production pipelines.
The expectation is that mission-critical code can remain tightly controlled while rapid experimentation gains traction elsewhere.
Long-term use may depend on whether automated systems deliver consistent accuracy rather than superficial output.
Via the registry
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews and opinions in your feeds. Be sure to click the Follow button!
And of course you can too follow TechRadar on TikTok for news, reviews, video unboxings, and get regular updates from us on WhatsApp also.
