O God, I could be bounded in a nutshell, and count myself a king of infinite space, were it not that I have bad dreams. — William Shakespeare, Hamlet, Act 2, Scene 2
I write about practical AI engineering, knowledge workflows, forecasting, quantitative research, and the tools I use along the way.
This site collects project notes, research questions, reading notes, and small interactive experiments.
Selected Writing
- Workspace-first Personal AI - Building Small, Independent Bots with OpenCode and cc-connect — 用 OpenCode、cc-connect 与独立工作目录搭建个人 AI Bot。
- Building KnowledgeBase with Opencode — 从 OpenCode Web 与 Git 出发，搭建知识库内容生产工作台。
- Why Multicollinearity Gets Less Attention in Time Series Forecasting — 从线性模型到机器学习，理解共线性问题的变化。
- Backtesting and Strategy Validation — 回测、模拟盘和实盘分别能提供哪些证据。
- Lightweight cicd for intranet saas-copilot — 内网项目的轻量交付实践。
Explore by Topic
- AI & Agents — Agent and Skills Development · AI Coding in a Tiny Team · Conversation First or Workspace First
- Knowledge Workflows — OpenCode 知识库系列：Building KnowledgeBase with Opencode → Building KnowledgeBase with OpenCode 2 - Docker and SFTPGo → Building KnowledgeBase with OpenCode 3 - CC Connect
- Forecasting & Quant — Forecasting Principles and Practice 3rd · freqtrade · Common Traders in Backtest
- Engineering & Tools — uv Quick Start · GitFlow · WSL Command Cheat Sheet
- Reading & Notes — How to Read and Note · Book Reader Skills 1 - Reading Beyond Summaries · Book Reader Skills 2 - From Tools to Methodology
Interactive Lab
Small interactive experiments built with AI.