理解成为新的瓶颈
本文是Geoffrey Litt在2026年AI Engineer大会上的演讲文字版。作者提出一个尖锐观点:尽管AI代理能编写大量代码,但理解这些代码仍然至关重要——理解正成为新的瓶颈。文章探讨了在AI辅助编程时代,人类开发者对代码的深度理解为何不仅没有被削弱,反而变得更加关键。
本文是Geoffrey Litt在2026年AI Engineer大会上的演讲文字版。作者提出一个尖锐观点:尽管AI代理能编写大量代码,但理解这些代码仍然至关重要——理解正成为新的瓶颈。文章探讨了在AI辅助编程时代,人类开发者对代码的深度理解为何不仅没有被削弱,反而变得更加关键。
AI-generated code creates "cognitive debt"—code produced faster than humans can understand it. The author proposes a ledger system with microcertifications tracking who understands what code, verified by domain experts. Every line of code would be cognitive debt until certified as part of a living mental model.
Cognitive debt in software development is as harmful as technical debt but lacks an accounting system to track it. Without measurement, teams unknowingly accumulate mental strain that reduces productivity and code quality. The author calls for formal methods to record and address cognitive debt.
Simon Willison reflects on a talk by Geoffrey Litt at AIE, who argued that when collaborating with coding agents, developers must understand the code deeply enough to remain active participants in the creative process, avoiding cognitive debt from drifting understanding.
Software teams need a formal system to track "cognitive debt"—the mental burden from complex code, poor abstractions, and unclear logic. Like technical debt, it slows development and causes errors and burnout. The article calls for explicit measurement and management of cognitive load in codebases.