<?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>lean on Terry's Latent Space</title><link>https://taot.github.io/tags/lean/</link><description>Recent content in lean on Terry's Latent Space</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 21 Nov 2026 13:52:46 -0500</lastBuildDate><atom:link href="https://taot.github.io/tags/lean/index.xml" rel="self" type="application/rss+xml"/><item><title>Formal Verification: What It Is, Why AI Makes It Practical, and What a Proof Does Not Tell You</title><link>https://taot.github.io/posts/2026/11/formal-verification/</link><pubDate>Sat, 21 Nov 2026 00:00:00 +0000</pubDate><guid>https://taot.github.io/posts/2026/11/formal-verification/</guid><description>Why tests miss bugs, how AI makes proofs cheap, how Lean, Verus, TLC and Kani find bugs (down to the SAT clauses), what I saw when an agent used five tools on one spec, and why a proof is only as good as its spec.</description></item></channel></rss>