<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>模型评估 on ByF (BaiFan) · 每日深度思考</title><link>https://blog.baifan.site/tags/%E6%A8%A1%E5%9E%8B%E8%AF%84%E4%BC%B0/</link><description>Recent content in 模型评估 on ByF (BaiFan) · 每日深度思考</description><generator>Hugo -- gohugo.io</generator><language>zh-cn</language><managingEditor>blog@baifan.site (ByF (BaiFan))</managingEditor><webMaster>blog@baifan.site (ByF (BaiFan))</webMaster><copyright>CC BY-NC 4.0</copyright><lastBuildDate>Sun, 20 Sep 2026 13:00:00 +0800</lastBuildDate><atom:link href="https://blog.baifan.site/tags/%E6%A8%A1%E5%9E%8B%E8%AF%84%E4%BC%B0/index.xml" rel="self" type="application/rss+xml"/><item><title>分类器又成了救世主</title><link>https://blog.baifan.site/the-classifier-returns/</link><pubDate>Sun, 20 Sep 2026 13:00:00 +0800</pubDate><author>blog@baifan.site (ByF (BaiFan))</author><guid>https://blog.baifan.site/the-classifier-returns/</guid><description>&lt;p&gt;在任何一家号称“全面接入 AI”的企业技术团队里，最不能细看的账单通常不是生产环境的推理开销，而是那一堆为了自欺欺人而跑出来的&lt;strong&gt;评估流水线（Eval Pipelines）&lt;/strong&gt;。&lt;/p&gt;</description></item></channel></rss>