<?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 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/llm/</link><description>Recent content in LLM 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>Sun, 20 Sep 2026 12:21:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>007 · 断言能被证明，就等于安全语义被保留了吗？</title><link>https://douyixuan.github.io/posts/ai-silicon-papers/2026-09-20/</link><pubDate>Sun, 20 Sep 2026 12:21:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-silicon-papers/2026-09-20/</guid><description>AutoTrans 用信号约束、编译与形式化验证移植 RISC-V 安全断言；它能筛掉错误和空洞断言，但‘可证明’与‘忠实保留原安全意图’仍是两个命题。</description></item></channel></rss>