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.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
More to read
Lumaril, which develops AI software for optimizing industrial production by connecting to existing control systems, raised a $66M Series A at a $400M valuation
Techmeme 3 h ago
DeepSeek open sources Super-Agent as a research prototype, a proactive coding agent it says can monitor group chats for coding issues and suggest solutions
Techmeme 4 h ago
Insurance software maker Guidewire agrees to acquire Hyperexponential, which makes AI-powered insurance underwriting and pricing software, for $1.7B in cash
Techmeme 4 h ago
One word for AI agents in 2027
Nate Herk 8 h ago