<?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>Github-Copilot on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/github-copilot/</link><description>Recent content in Github-Copilot 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, 19 Sep 2026 08:00:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/github-copilot/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Native Digest 2026-09-19</title><link>https://douyixuan.github.io/posts/ai-native/2026-09-19/</link><pubDate>Sat, 19 Sep 2026 08:00:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-native/2026-09-19/</guid><description>今天关注 AI-native 软件工程进入规模化之后的两个核心问题：Spotify 发现 AI 带来的主要风险不是 AI 代码本身，而是变更吞吐增长快于 review、测试、发布和可观测性；GitHub 则用 Copilot 完成 80 万行级 agent runtime 的 Rust 重写，展示了增量迁移、agent fleet、独立 correctness oracle 和 human merge gate 如何让超大规模 agentic coding 变得可控。</description></item></channel></rss>