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

对比三种写课程介绍的策略：完全AI、AI辅助、完全人肉。发现人类写作自然流露的张力与感染力是AI外交式疏离风格所缺乏的，选择不用AI本身也是对用户的尊重。

Compares three approaches to writing a course introduction—fully AI, AI-assisted, and fully human. Reveals that human writing conveys tension and engagement that AI's diplomatic, detached style lacks, and choosing not to use AI can itself show respect to users.

Prompt Engineering实战指南：匹配任务与AI能力、上下文窗口管理、知识查询可靠性提升、数学计算与机器人控制等场景下利用Agent增强能力的方法。

A practical guide to prompt engineering: matching tasks to LLM capabilities, managing context windows, using web search for reliability, and leveraging agents for domains like math and robotics.

观察到AI使编程从"没办法才用"变成解决问题的首选方法，同时支持个性化的实战学习。认为AI对IT的深远影响体现在编程民主化和学习方式的根本变革，让更多人能高效掌握技术技能。

Observes that AI elevates programming from last resort to first-class problem-solving method and enables personalized, hands-on learning. Argues AI's impact on IT is democratization of programming and transformation of how we acquire technical skills.

记录将AI接入天文摄影机器人系统的实验。探讨安全性与灵活性的权衡，通过Python类封装、AST解析和沙箱机制，在防止恶意代码的同时让AI安全地控制望远镜设备。

Documents an experiment connecting AI to astrophotography robotics. Explores the security-flexibility tradeoff, using Python with class encapsulation, AST parsing, and sandboxing to safely let AI control telescope equipment while preventing malicious code execution.

天文摄影自动对焦算法思考：用信息熵代替星点拟合描述对焦质量，加权曲线拟合优先考虑合焦点附近数据，实现稳定精确的自动对焦。

Apple Vision Pro深度体验评测：分析其作为VR设备的真实定位，探讨适合与不适合的使用场景，以及在日常工作和创作中的实用价值。