Articles
All English articles, arranged by date.
2026
Why I Don’t Treat Investing as an Escape When My Capital Is Small
A personal framework for investing with a small account: why cash flow, emergency savings, risk …
WeChat Official Account Cold Start: Recommendation Traffic, Search, and Monetization
Field notes from WeChat Official Account operators on cold starts: recommendation traffic, …
Two AI Frontend Design Experiments: GPT vs Gemini vs Claude vs Kimi vs Grok vs GLM vs MiniMax
Two low-constraint HTML design experiments comparing GPT, Gemini, Claude, Kimi, Grok, GLM, and …
ChatGPT Plus vs Team/Business: A Real-World Usage Capacity Test
A historical May 2026 usage-snapshot test comparing one ChatGPT Plus account with two …
Bitget Wallet Card Guide: Fiat24 Setup, Top-Up, Alipay, WeChat Pay, and Google Pay
A hands-on Bitget Wallet Card / Fiat24 guide covering application and KYC, activation and …
Tencent Cloud Lighthouse Has No Automatic Snapshots: My Two-Slot Rotation with systemd
Tencent Cloud Lighthouse does not provide automatic server snapshots, and my instance only has …
Why I Self-Host Waline on a VPS with SQLite
Why I chose Waline for a Hugo blog, self-hosted it on my own VPS, and kept comments in SQLite: …
Slock Is Now Raft: Installation, Agent Setup, and Common Problems
A hands-on guide to Raft, formerly Slock: installation and machine connection, agent runtimes, …
Enterprise AI Agents Don’t Always Need Multi-Agent Architectures
A practical enterprise agent architecture based on a real AI reception system: use SOPs, state …
Multi-Agent Collaboration Patterns: Chat, Issue-Driven, SOP, and Hybrid Workflows
A practical comparison of multi-agent collaboration patterns from Slock/Raft, Multica, and …
Multica Guide: Issues, Agent Workflows, and Multi-Agent Collaboration
A hands-on guide to Multica: starting with verifiable Issues, organizing Agent roles, handling …
OpenCLI for AI Agents: Turning Browser Workflows into Reusable CLI Commands
A practical OpenCLI guide for deciding when a browser workflow should become a reusable CLI, …
Does Multica Reduce Work or Add More? Lessons from a Real Squad Workflow
A hands-on review of Multica Squad in a real multi-agent workflow: where it reduces coordination …
I Used 1.05 Billion Tokens in Cursor: What a 93.31% Cache Hit Rate Taught Me
Real Cursor Usage Events from 80 days: 1.05 billion tokens, a 93.31% cache hit rate, …
Fix Codex App instructions_required 400 Behind CLIProxyAPI
A real fix for Codex App 400 instructions_required behind CLIProxyAPI (CPA): why filtering …
How to Connect a Local stdio MCP Server to ChatGPT Web with OpenAI Secure MCP Tunnel
A hands-on setup and troubleshooting guide for bridging a local stdio MCP server into ChatGPT …