提示词也是一种技术债务
本文指出，在AI驱动的软件开发中，提示词（prompts）同样会像传统代码一样积累技术债务。提示词往往缺乏可维护性、可测试性和清晰的版本控制，随着系统演进，晦涩的提示词会导致调试困难、行为不可预测，进而拖累开发效率。作者呼吁将提示词视为一等代码资产，建立相应的管理规范。
相关报道
Prompts for AI coding tools are a form of technical debt that decays silently with each model upgrade, unlike code. The author advises against investing heavily in bespoke agentic setups, recommending instead using third-party tools with minimal configuration and keeping custom prompts limited to concrete project facts.
Gary Marcus scrutinizes recent claims from OpenAI and Anthropic, urging readers to examine the underlying details and math behind their headline-grabbing announcements rather than taking them at face value.
Adding assumptions to a formal property makes it logically weaker—guaranteed to work in fewer cases. Engineers add assumptions when stronger properties are impossible, too costly, or unverifiable. These assumptions often involve factors outside the program, like the operating environment or external dependencies.