AI Coding

提出用户生成软件需要新的范式。软件公司不再交付成品，而是交付"生成内核"——包括核心套件、引导知识和杠杆工具集，专为AI使用而设计，最大化表达范围、意图保真和生成效率。

Proposes that User-Generated Software requires a new paradigm. Instead of finished products, companies deliver "Generative Kernels"—core kits, guiding knowledge, and leverage tools designed for AI to use, maximizing expressive range, intent fidelity, and generation efficiency.

Claude Code是被低估的AI Native软件开发关键拼图，推动Library as a Service模式，帮助AI有效对接企业级代码库。

Claude Code is the overlooked key to AI-native software development, enabling Library as a Service (LaaS) and bridging AI with existing enterprise codebases.

通过分离Planner和Executor、强制文档沟通、用o1当Planner三项改造，解决Cursor鬼打墙问题，实现质量显著提升的多智能体系统。

How separating Planner and Executor roles, enforcing document-based communication, and using o1 as Planner transformed Cursor from a simple assistant into a multi-agent system.

在上一篇文章中，我们提到了Devin这种可以全自动进行编程的Agentic AI。相比于其他Agentic AI工具，比如Cursor和Windsurf，它有几个核心优势，尤其是流程规划、自我进化、更多的工具使用和全自动的工作方式。这让Devin显得是一个下一代的工具，和现有的Agentic AI工具拉开了一个身位。但是在用了它一段时间之后，我的Builder's Mindset又开始蠢蠢欲动，驱使我魔改了Windsurf和Cursor，让它们也能实现Devin 90%的功能。

In the previous article, we discussed Devin, an Agentic AI capable of fully automated programming. Compared to other Agentic AI tools like Cursor and Windsurf, it has several core advantages, particularly in process planning, self-evolution, expanded tool usage, and fully automated operation. This makes Devin appear to be a next-generation tool, setting itself apart from existing Agentic AI tools.

提出AI辅助编程的核心从数据结构和算法转向注释和DocString的质量。类比管理AI与管理人类团队，强调了解能力边界、任务分解、委托和质量检查等开发经理式的思维方式。

Argues that effective AI-assisted programming shifts focus from data structures and algorithms to writing detailed comments and DocStrings. Draws parallels between managing AI and managing human teams, emphasizing delegation, context provision, and quality checks.