YunLab.ai Yun.Z’s working notes
Working notes from real AI use.
Not a tutorial, not a review feed. Notes from real use.
I’m Yun.Z. Not an AI professional, not a programmer. This site keeps track of how new tools enter real tasks, what I got wrong, what I fixed later, and what was worth keeping.
An open working notebook.
Start Here
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. 
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
39 notes in archive
- Claude Code Was Marking the Prompt Claude Code 提示词里多了标记 A Chinese security graphic claimed Claude Code had a hidden backdoor for detecting Chinese users. I checked the Chinese mirrors, GitHub issue, technical write-up, official changelog, npm package, and my own machine. The mechanism exists and is reproducible in the package. That is not the same as proving local backdoor behavior.
- Fable 5 Is Unlocked, and I Still Can't Use It Fable 5 已经解锁了，但我用不了 Fable 5 is unlocked again, restored globally on July 1. Yet when I opened the client, it was back in the model list — and clicking it returned Currently unavailable. Here is what Fable 5 went through, why the unlock doesn't reach me, and what you can actually do about it.
- Claude Code Threw Another Fit claude code 又抽风了 Two days building a dashboard, every time it tried to call a tool the format tags broke, the whole thing collapsed into garbage and the work never went out, and I just kept hitting interrupt. I pulled apart all 16 collapses, down to the protocol: the tags it frames structure with, and the content it's carrying, share one stream of text with no escaping — so the moment a stretch of content looks like a tag, the system parses it wrong and cuts the call off. This bug has an old name: delimiter collision.
- It Wasn't Losing Its Mind. Nothing Could Make It Stop. 它不是疯了，是没人能让它停下来 Last time I wrote about how it went crazy. This time I pulled apart that 9-day, 9,195-line conversation to find why. The same 25-minute heartbeat instruction got fed to Fable 5 51 times in a day and it held; swap in Opus 4.8 and 11 was enough to crack it. The model wasn't broken — I'd built a loop with no exit, a strong model held the mine down, and one model swap set it off.
- My Mac Was Cooking — the Culprit Was a Broken .git 我的 Mac 发热到飞起，真凶是个坏掉的 .git Open Codex on the laptop and it runs hot, with syspolicyd and trustd spiking to 160%. I suspected the M4 Max, Computer Use, MCP, hooks — none of it. The real culprit was buried deep: a broken .git. The whole chain, two machines two outcomes, and what the real damage is — not power, not 'reads wearing the SSD,' but heat.
- My Claude Code Sessions Showed Up on All Three Machines 我的 Claude Code 会话，三台电脑都看得见了 Three machines on one account — a Claude Code session I started on the laptop also showed up on the Mac Studio and Windows. At first I thought 'the work moved over.' Wrong. The feature is Remote Control — how to use it, how to use it well, and the 'which machine is it actually running on' part that trips everyone up, sorted out once.
About
A regular person,
learning from scratch.
一个普通人，重新学习。
Who I am
I’m Yun.Z, a regular person learning AI in public. Not a programmer, not an AI expert. YunLab.ai is my working notebook: 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 notebook
This is not a research institute or a polished tech demo. It is a place to keep what was tried, what went wrong, and what is worth keeping.