AI

March 2026 Thought Notes 468 entries this month | Recorded: March 1 — March 31, 2026 Monthly Theme: Angkor Wat · AI Agent · Self-Narrative Core Topics: Gewu/AI (~53), Gewu/Cambodia (~38), Gewu/Angkor Wat (~23), Gewu/Hinduism (~15), Guanwo (~14), Gewu/Vietnam (~11) Daily Notes Archive March 1, 2026 Sunday (29 entries) Northeast China’s Direct Culture: How Labor Independence Shapes Non-Draining Relationship Patterns 2026-03-01 10:35:04 Women’s status in Northeast China is slightly dominant. ...

“Software is eating the world.” — Marc Andreessen, 2011 “Now AI is eating software—and the question for the rest of us is: what’s left for one human, alone, in front of a screen?” — me, asking myself one night in 2026. Prologue: How Big Does One Person Need to Be? In February 2026, I ran my first complete overnight agent. I set a prompt, dropped it into Claude Code in a loop, and went to sleep. At 7 a.m. the next morning, what I saw on the screen was: 6 commits, 4 PRs, 3 auto-rolled-back failures, and a research brief I hadn’t even read myself. ...

“Most Agent projects die in the unmapped wilderness between PoC and production.” I wrote that line while reading through the Relay project documentation. Relay is an open-source AI Agent system for job searching — not a demo built on three lines of LangChain plus GPT-4, but a project with complete architectural documentation, 172 engineering tasks, a hybrid tech stack, and explicit counterexamples for every major design decision. It is not fully running yet. The Agent layer code is still being written. That is exactly why I think this article is worth writing: this is a system that has thought very deeply at the design level, and those deep thoughts — regardless of where this project ultimately lands — are valuable references for everyone doing Agent engineering. ...

“We are not really writing prompts. We are furnishing a room for the model — deciding what gets carried in, where it sits, when it gets moved out. The wording is just a sticky note on the desk. What we are actually doing is the interior work.” If you had asked me in 2024 “how do I use AI well,” I would most likely have talked to you about prompts: how to phrase instructions, how to set a role, how to give examples. But if you asked me the same question today, my answer would be completely different. ...

“The agent loop is 10 lines of code. Agent engineering is 100,000 lines of code.” The first time I read that, I paused — and the more I sat with it, the sharper it cut. It punctures the single biggest illusion in this whole field: people think building an agent means writing a good prompt and wiring up an LLM API. But the actual work of pushing a demo to production — of running safely, unattended, all night long — is 99% not in that loop. ...

Agent Identity: From Locke to OpenClaw On the engineering practice and philosophical framework of AI agent identity continuity 0. Introduction: An Engineering Problem Misdiagnosed as Philosophy The cost of agent amnesia is systematically underestimated. Not because users are annoyed—though they are. But because statelessness breaks the foundation of the trust account. Every session, the agent starts from zero. It doesn’t know who you are, why you got angry last time, whether that promise from three months ago was kept. From an economics perspective, it’s like rebuilding your credit score for every transaction—transaction costs explode, and there’s no learning accumulation. ...

Pascal wrote in the 17th century: “All of humanity’s problems stem from one thing: man’s inability to sit quietly in a room alone.” Three hundred years later, I thought of this sentence late at night in Lhasa, and added one more: They’re not sure who exactly is the one sitting in that room. Introduction: The 3 AM Emptiness For a while, I woke up almost every day at 3 AM. ...

This project is an ongoing process — learning AI open source projects one day at a time, building real-world skills by combining hands-on practice with AI tooling, and documenting the journey. notion List Basic Information: Project Name: GitHub URL: Primary Tech Stack: Related Articles Stages of Growth in Open Source A Complete Guide to Open Source Contribution (For First-Timers) My Practice Notes: Designing Standards for Open Source Communities How to Ask Questions in Open Source Communities

This project is an ongoing journey — learning AI open-source projects one step at a time, building real skills through hands-on practice, and using AI tools to sharpen the ability to tackle complex problems. Everything gets documented along the way. Notion List Basic Information: Project Name: GitHub URL: Primary Tech Stack: Related Articles A Stage-by-Stage Growth Guide for Open Source A Complete Guide to Open Source Contribution (A Primer for First-Time Contributors) My Practical Summary: Designing Norms for Open Source Communities Learning How to Ask Questions in Open Source Communities

This project is an ongoing journey — learning AI open-source projects one step at a time, building real skills through hands-on practice, and using AI tools to sharpen the ability to tackle complex problems. Everything gets documented along the way. Notion List Basic Information: Project Name: GitHub URL: Primary Tech Stack: Related Articles A Stage-by-Stage Growth Guide for Open Source A Complete Guide to Open Source Contribution (A Primer for First-Time Contributors) My Practical Summary: Designing Norms for Open Source Communities Learning How to Ask Questions in Open Source Communities