<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Evaluation on 时影</title><link>https://huggingaha.github.io/tags/evaluation/</link><description>Recent content in Evaluation on 时影</description><generator>Hugo -- gohugo.io</generator><language>zh-cn</language><managingEditor>huggingaha@gmail.com (时影)</managingEditor><webMaster>huggingaha@gmail.com (时影)</webMaster><copyright>© 2026 时影</copyright><lastBuildDate>Sat, 12 Sep 2026 03:00:00 +0800</lastBuildDate><atom:link href="https://huggingaha.github.io/tags/evaluation/index.xml" rel="self" type="application/rss+xml"/><item><title>Great Evals 十讲：Madhu Guru 的 Eval 建设方法论</title><link>https://huggingaha.github.io/posts/how-to-build-great-evals/</link><pubDate>Sat, 12 Sep 2026 03:00:00 +0800</pubDate><author>huggingaha@gmail.com (时影)</author><guid>https://huggingaha.github.io/posts/how-to-build-great-evals/</guid><description/></item><item><title>解析 AI Agent 评估</title><link>https://huggingaha.github.io/posts/demystifying-evals-for-ai-agents/</link><pubDate>Mon, 12 Jan 2026 00:00:00 +0000</pubDate><author>huggingaha@gmail.com (时影)</author><guid>https://huggingaha.github.io/posts/demystifying-evals-for-ai-agents/</guid><description/></item></channel></rss>