<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Legacy on Wercstat</title><link>https://www.wercstat.com/en/blog/tags/legacy/</link><description>Recent content in Legacy on Wercstat</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Mon, 22 Jun 2026 17:53:30 +0200</lastBuildDate><atom:link href="https://www.wercstat.com/en/blog/tags/legacy/index.xml" rel="self" type="application/rss+xml"/><item><title>The AI math for legacy software has fundamentally changed</title><link>https://www.wercstat.com/en/blog/ai-math-for-legacy-software/</link><pubDate>Mon, 22 Jun 2026 00:00:00 +0000</pubDate><guid>https://www.wercstat.com/en/blog/ai-math-for-legacy-software/</guid><description>AI has become much better in recent months at understanding and generating complex code. .NET architect David Tielke rebuilt a legacy application entirely with AI: up to 93x faster and for € 25,000 instead of an estimated € 2 million. With the necessary nuance for large enterprise software, the boundary is unmistakably shifting, and with it the math for modernising outdated custom software.</description></item></channel></rss>