Understanding is the new bottleneck: why you still need to read your agent's code

Understanding is the new bottleneck

Geoffrey Litt argues that as agents write more code, human understanding shifts from verification to participation—you need a rich mental model to drive the next creative iteration. He borrows three techniques from education: auto-generated explainer docs that teach background and intuition before code, self-quizzes to check real understanding, and interactive micro-worlds for hands-on exploration. The post doesn't quantify how much these techniques improve outcomes, but frames the cost of skipping them as 'cognitive debt' that compounds over time.

Why it matters: Geoffrey Litt's AI Engineer talk introduces 'cognitive debt' as a framework, which resonates directly with developers using coding agents. It's a sharp concept, not generic commentary. The cap at 78 reflects that this is a personal blog transcript, not a product launch or rese...