<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Differential-Testing on Tokenise</title><link>https://tokenise.rosvetic.com/tags/differential-testing/</link><description>Recent content in Differential-Testing on Tokenise</description><generator>Hugo</generator><language>en-gb</language><lastBuildDate>Mon, 26 Oct 2026 16:03:00 +0000</lastBuildDate><atom:link href="https://tokenise.rosvetic.com/tags/differential-testing/index.xml" rel="self" type="application/rss+xml"/><item><title>Microsoft's agent migration recipe: approve the rules, not the fixes, and let a differential test grade the result</title><link>https://tokenise.rosvetic.com/posts/differential-tests-migration-knowledge-base/</link><pubDate>Mon, 26 Oct 2026 16:03:00 +0000</pubDate><guid>https://tokenise.rosvetic.com/posts/differential-tests-migration-knowledge-base/</guid><description>&lt;p&gt;The hard part of an agent-driven migration stopped being the translation a while ago. It&amp;rsquo;s the review. A migration that touches 400 files produces 400 diffs, and a human who reads them one at a time either gives up around file 60 or starts approving on rhythm. Microsoft&amp;rsquo;s Command Line publication &lt;a href="https://commandline.microsoft.com/agentic-software-engineering-large-scale-code-migration-language-modernization-spec-driven-development/" target="_blank" rel="noopener noreferrer"&gt;published the first post of a series on this on 26 October 2026&lt;/a&gt;&#10;, covering how its teams use agents to move very large codebases to new toolchains and from legacy C and C++ to Rust. Its answer to the review problem is worth copying at a much smaller scale.&lt;/p&gt;</description></item></channel></rss>