<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>LLM on yishiashia's Blog</title><link>https://yishiashia.github.io/tags/llm/</link><description>Recent content in LLM on yishiashia's Blog</description><generator>Hugo -- gohugo.io</generator><language>zh-TW</language><copyright>Copyright © 2023 yishiashia@gmail.com. All rights reserved.</copyright><lastBuildDate>Mon, 07 Sep 2026 20:00:00 +0800</lastBuildDate><atom:link href="https://yishiashia.github.io/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>[AI 軟體工程] Harness Engineering 介紹：用驗證與治理讓 AI Agent 的產出更可靠</title><link>https://yishiashia.github.io/posts/harness-engineering-governance/</link><pubDate>Mon, 07 Sep 2026 20:00:00 +0800</pubDate><guid>https://yishiashia.github.io/posts/harness-engineering-governance/</guid><description>當基礎模型逐漸商品化，AI Agent 的競爭重心正從「模型多聰明」上移到模型外的骨架 —— harness。本文介紹 harness engineering 的概念，說明為什麼「驗證與治理」是這層骨架裡最難被複製的一塊，並提出從「相信 agent」轉向「驗證結果」的治理主線與四支柱框架。</description></item></channel></rss>