<?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>Neuro-Symbolic on Pavel Nasovich's Blog</title><link>https://forcewake.me/tags/neuro-symbolic/</link><description>Recent content in Neuro-Symbolic on Pavel Nasovich's Blog</description><generator>Hugo -- 0.157.0</generator><language>en-us</language><copyright>Copyright 2026</copyright><lastBuildDate>Fri, 10 Apr 2026 00:29:11 +0200</lastBuildDate><atom:link href="https://forcewake.me/tags/neuro-symbolic/index.xml" rel="self" type="application/rss+xml"/><item><title>Beyond Pattern Matching: What Formal Reasoning Engines Can Verify Today</title><link>https://forcewake.me/formal-reasoning-engines-verifiable-code/</link><pubDate>Thu, 09 Apr 2026 21:55:16 +0000</pubDate><guid>https://forcewake.me/formal-reasoning-engines-verifiable-code/</guid><description>A technical teardown of modern formal reasoning engines: what Lean- and SMT-backed systems can verify today, where pure LLM proof generation still breaks, and how to ship verifiable code without pretending autocomplete is deduction.</description></item></channel></rss>