Your AI Coding Agent Follows the Rules — But Does It Know When It’s Wrong?
中文摘要
探讨AI编程代理在遵循TDD时的局限性，分析其在执行指令时是否能识别自身的错误。
English Summary
This article explores the limits of AI coding agents and TDD, questioning if agents can recognize errors while strictly following provided rules.
Original Excerpt
What a smart e-waste system taught us about TDD, AI agents, and the limits of “just write tests first” Continue reading on Medium »