遗留代码库中的人类优势：Mob编程与AI的局限
原标题：Podcast: The Human Edge: Why Brownfield Codebases Need Mob Programming, Not Just AI Vibes
AI 摘要
SpareBank 1 Utvikling 的开发者 Asgaut Mjølne Söderbom 和 Ola Hast 在播客中分享了他们团队采用 mob 和 pair programming 的经验，并讨论了 Claude Code 在复杂遗留代码库中的局限性。他们强调通过持续协作和 TDD 提高代码质量，并指出 AI 工具在缺乏隐性上下文时可能产生低质量代码。该团队与 SINTEF 合作进行了七项实验，验证了协作工作方式的引入效果。
正文节选
Asgaut Mjølne Söderbom and Ola Hast discuss the evolution of their software engineering practices past continuous deployment and pair engineering. The conversation continues where it left off in the previous episode and focuses on the experiments in adopting Claude Code and the reasons why they consider it good for everything else, but not coding. Key Takeaways - Extending mob and pair programming to all team tasks, even documentation and analysis, serves as the foundation for high-quality, high