YunLab.ai / Personal AI Lab

An ordinary AI workbench.

一个普通人的 AI 工作台

I’m Yun.Z. Not an AI professional, not a programmer. YunLab records how AI tools, agents, and knowledge systems enter real tasks, then turns the public-safe parts into notes I can return to.

Find notes How to read All notes
31 notes Filed archive Source notes Back to context

How to read

Read it like an open notebook.

Some posts are same-day calls. Some are notes I wrote after the dust settled. Start where the thread feels useful, then follow it back to the source.

Latest The Model I Praised Yesterday Is Gone Today Start with what I was wrestling with most recently. Archive All notes Tools, agents, knowledge systems, and retrospectives live here. About Why I keep this site The notes make more sense once you know where this workbench comes from.

Start Here

New here? Read these two first.

01 Knowledge My Knowledge Model What I eventually figured out: the dangerous thing in an AI project isn't forgetting — it's remembering wrong and continuing to build on it. My Knowledge Model isn't about storing more material; it's about compressing the site into judgments, rules, and handoff entries that next time can actually use. 02 YunLab From Internal Engineering Notes to Public Writing Potholes I hit while turning internal engineering material into public YunLab articles: the issue isn't just redaction. It's separating the working backstage from the experience that can actually be left in public.

Latest Notes

31 notes in archive

All notes
  1. 4 min YunLab The Model I Praised Yesterday Is Gone Today 我昨天还在夸的模型，今天没了 Fable 5 was pulled by the US government three days after launch. One export-control directive, and Anthropic disabled its two most powerful models worldwide the same day. I'm writing this on Opus 4.8 — and adding one new lesson.
  2. 5 min YunLab I Swapped the Model, and It Lost Its Mind 换了个模型，它当场就疯了 Fable 5 got pulled, so I switched the model back to Opus 4.8 to keep running my Lin Lu video work. Its first night on the job it had a breakdown: threw out its own outputs as fake, drifted from Chinese into Japanese, decided out of nowhere I wanted to buy a 512G Mac Studio, and deleted 57 directories. A field log of one model-handoff incident.
  3. 8 min YunLab What Was I Doing for the Past 35 Hours? 过去 35 小时，我在干什么 I pulled 35 hours of Claude Code session logs, git commits, and the token bill: 85 sessions, ~400 instructions, 5,200+ tool operations, 52 commits across 5 repos. And an honest answer to one question: what actually makes Fable 5 strong.
  4. 7 min Learning Notes Prompt Isn't a Magic Phrase, It's a Task Contract — Reattributing a Month of Failures After One Lesson My last post: Linlu spent a month and still produced no video. Today I read a lesson called "What Prompt Actually Is," and looking back — most of those failures weren't the AI's fault. They were mine, for treating prompts as "the right phrase to coax the AI" instead of "a task contract between me and the AI." This lesson made me reattribute everything.
  5. 9 min OpenClaw Asking Linlu to Make a Single Lin Daiyu Scene: One Month, Three Teardowns, Still No Finished Clip Linlu is the multimedia AI in my OpenClaw system. I asked her to produce a 45-second video of Lin Daiyu arriving at the Jia Mansion — not for this one clip, but to validate she could run the whole pipeline herself. A month later, I've torn it down three times: Codex was patching one specific video instead of building capability, every middle node was unchecked, the machine said PASS but I saw mosaic. Still fixing tonight.
  6. 5 min Tools Two Small Tools I Built on the Side: An AI Quota Dashboard + a Task Board One because I lost track of where my AI tool spend goes and how much is left. One because I had no idea whether the cron jobs on my Mac actually ran today. Both pull state scattered across many places into one visible spot.

About

A regular person,
learning from scratch.

一个普通人，重新学习。

Who I am

I’m Yun.Z — a 44-year-old middle manager. Not a programmer, not an AI expert. YunLab.ai is my public workbench: where I keep what I learn, try, get wrong, fix, and reflect on.

Why I write in public

My daily AI work has become messy — a judgment lives in a chat, a verification result in a terminal, a design decision in a local file. On the day itself I know how they connect; a few days later only a pile of material is left. What I lack is not more AI, but a place to collect the experience.

The workbench

A personal AI lab is not a research institute. It is a long-term workbench — tools and half-finished things on the table, and above all a record of what was tried, what went wrong, and what is worth keeping.

Full story on the About page ›