Skip to content

docs(zhihu): refresh part0b numbers; rewrite part4 to avoid overlap #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
willamhou merged 1 commit into from
May 27, 2026
Merged

docs(zhihu): refresh part0b numbers; rewrite part4 to avoid overlap #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions docs/zhihu/part0b-ai-workflow.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@ git 历史诚实地反映了这一点。早期的 commit 是杂乱的大块头
- **构建命令**：每个 `make` 目标对应什么功能、开启什么编译选项
- **内存布局**：hypervisor、guest 内核、设备，每一段地址的用途
- **关键坑位**："用 HPFAR_EL2 不要用 FAR_EL2"、"永远不要改 guest 的 SPSR_EL2（处理器状态寄存器），否则内核自旋锁死锁"、"inject_spi() 不能拿 DEVICES 锁，否则死锁"
- **测试清单**：33 个测试套件，每个有多少断言
- **测试清单**：34 个测试套件，每个有多少断言

这个文件是怎么长出来的？模式永远一样：

Expand Down Expand Up @@ -177,10 +177,10 @@ AI 对此毫无感觉。它看到测试绿了就认为搞定了。**人的职责
30 天的粗略统计：

- **193 个 commit**（平均每天 6.4 个）
- **约 282 个测试断言**，分布在 33 个测试套件里
- **约 457 个测试断言**，分布在 34 个测试套件里
- **人的贡献**：约 30%——架构决策、翻 ARM 手册、调试集成问题、review 每一行 AI 生成的代码
- **AI 的贡献**：约 70%——代码生成、写测试、模板代码、初步调试方向
- **CLAUDE.md**：从 0 行增长到 500 多行
- **CLAUDE.md**：从 0 行长到 500 多行，后期回头精简压到 ~280 行（信息密度优先）

但 30/70 这个比例有误导性。那 30% 的人类工作承担了不成比例的**承重**——就像一座桥，70% 的材料是混凝土，但承重的是那 30% 的钢筋。如果钢筋不对，混凝土再多也会塌。

Expand Down
Loading
Loading