Three AI Coding Stories, Three Numbers to Read
What happened
过去几天 AI 编程圈出了三件事。ZCode 被发现在后台把整个项目连同 Git 历史打包加密，排队往云端传，快照里 .git 对象占了 86.6%，但官方说数据会立即销毁，目前没有第三方验证。HarnessTax 的评测把同一个模型 Claude Fable 5 装进不同框架跑题，官方 Claude Code 和极简框架 Pi 成功率几乎一样（97....
Coverage
Follow the reports to see the story from different sides.
- Computing Life · Share · YagePickThree AI Coding Stories, Three Numbers to Read
ZCode was caught silently packaging entire Git histories for cloud upload, with .git objects making up 86.6% of snapshots. HarnessTax benchmarked Claude Fable 5 across frameworks: Claude Code and minimal Pi achieved near-identical success rates but a 2x cost gap. A Microsoft architect replaced multi-model agent loops with a single model reading skill docs and calling tools directly—halving API calls but increasing total tokens by 22%. Each story unpacks one number and a reminder to check which layer a metric actually measures.