How I audit AI-written code — and the bug that proved why

<p>I build most of my software as an AI-augmented solo developer. I write the spec, I own the architecture, and I drive Claude Code and Cursor through the implementation. But there is one rule I never break: <strong>I audit what actually ships, not what the model tells me it produced.</strong></p> <p>Here is the bug that turned that rule into a habit.</p> <h2> The symptom that shouldn't exist </h2

Read the source →