<?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>Human-Feedback on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/human-feedback/</link><description>Recent content in Human-Feedback on 兜忆轩 | Cedric's Compiler Notes</description><image><title>兜忆轩 | Cedric's Compiler Notes</title><url>https://douyixuan.github.io/images/papermod-cover.png</url><link>https://douyixuan.github.io/images/papermod-cover.png</link></image><generator>Hugo -- 0.146.0</generator><language>en-us</language><lastBuildDate>Sat, 29 Aug 2026 08:00:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/human-feedback/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Native Digest 2026-08-29</title><link>https://douyixuan.github.io/posts/ai-native/2026-08-29/</link><pubDate>Sat, 29 Aug 2026 08:00:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-native/2026-08-29/</guid><description>今天两篇都在回答 Agent 如何持续变强：JIT-Agent 把 harness 从人工维护的固定脚手架变成按任务动态生成、可修复、可演化的机器生成程序；Warp 则给出一个非常简单的生产实践，用 base skill + improver skill + human feedback，把 code review、spec 和 issue triage 的反馈持续折叠回可版本化的 Agent Skills。</description></item></channel></rss>