An engineering notebook on AI, systems, and everyday experiments.

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.

用Skyfield库模拟行星位置，通过可见性、直线排列度和黄经集中度三项指标量化评估行星连珠现象，实现天体排列的定量分析与预测。

A quantitative approach to identifying planetary alignments using orbital mechanics and Skyfield library, combining visibility, linear alignment, and longitude clustering metrics to search decades of astronomical data.

通过模拟购车场景实测OpenAI Deep Research，展示其如何大幅提升调研效率、解放脑力进行更深层思考，以及重新定义问题边界的认知炼金能力。

A hands-on exploration of OpenAI Deep Research through a simulated car-buying scenario, demonstrating how AI elevates research efficiency and enables deeper strategic thinking about negotiation and decision-making.

不要从AutoGen、LangGraph等框架入手学习Agentic AI——它们会锁定你的世界观。在领域快速演变期，应该从第一性原理出发自己构建。

Don't start Agentic AI with frameworks like AutoGen or LangGraph—they lock you into a worldview. Build from first principles while the field is still evolving rapidly.

对比GPT-4o和o1评测DeepSeek r1，发现其在指令遵循和思维深度上不及第一梯队，但在中文表达和创意写作方面展现出独特优势。

A critical review of DeepSeek r1 comparing it to GPT-4o and o1, finding it lacking in instruction following and reasoning depth, but exceptional in Chinese language mastery and creative writing.