Building ambitious software — Jonathan Kelley, Dioxus Labs & Cognition
Jonathan Kelley from Dioxus Labs describes his experience using AI coding agents for his Rust framework.
His team maxed out subscriptions and generated tens of thousands of lines of code, but almost nothing was worth merging—Kelley calls it becoming a "slop cannon". He discovered that AI is actually good at handling Rust's difficult rules (borrow checker), making the language's steep learning curve an advantage rather than a problem. The agents performed well with integration tasks and documentation, but wrote poor unit tests. Kelley's conclusion: code is cheap now, but quality and architecture still require human time and judgment.
Open on YouTube →
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
