An editor that keeps the prompt, not the code, as the record of intent

Vaughn built an experimental editor where a prompt is first written as declarative pseudocode, then compiled into code, with a source map linking each generated line back to the pseudocode that produced it. The pseudocode stays in the repository next to the generated code rather than getting discarded once the code lands. In his own words: "before AI arrived on the scene, source code was a single artifact that directly expressed the intended behavior of a piece of software as it currently exists. After AI, the artifact is still there, but it's no longer the true record of human intent... The real value is in persisting your expressed intent." The Hacker News discussion reached 160 points and 87 comments within three hours of posting, with commenters pointing to older prior art in the same spirit: Steve McConnell's Program Design Language from Code Complete, and architectural decision records.

Why it matters: most teams treat a prompt as disposable, typed into a chat window and thrown away once the code ships. Vaughn's bet inverts that: the prompt is the artifact worth keeping, and the code is closer to a compiled output. It's a single developer's project, not a proven practice, but it's a concrete answer to a question a lot of teams are stuck on: how do you explain, months later, why an AI-generated section of a codebase does what it does.