别再数 Token：按合并的拉取请求衡量 AI 编码成本

发生了什么

文章主张，企业应按每个合并拉取请求的成本来衡量 AI 编码成本，并同时关注返工和缺陷，而不是依赖 Token 数量或使用上限。文中介绍了将常规编码任务分配给开放权重模型，把前沿模型留给更难的工作。在 HPE，一套混合平台将 150 多个内部应用的工作负载路由到本地部署的开放权重模型，据报告，Token 成本降低了 30% 到 50%。

接下来读什么

• 今日还有哪些重要变化TypeSafe AI 与 Treg 发布由 Jev 驱动的开源人物搜索工具

这件事到目前为止

An MIT Technology Review article recommends measuring AI coding costs per merged pull request rather than relying on token counts or usage caps, and reports that HPE has reduced token costs by 30 to 50% through a hybrid model platform. The proposed measure divides total AI-assisted development costs by the number of changes that pass review and are merged, with rework and defects tracked alongside it. The article describes routing routine coding tasks to open-weight models and reserving frontier models for harder work. At HPE, the platform routes workloads from more than 150 internal applications to on-premises open-weight models; the reported savings apply to token costs.