<?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>Open Source on Antonio V. Franco</title><link>https://antoniovfranco.com/tags/open-source/</link><description>Recent content in Open Source on Antonio V. Franco</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 04 May 2026 12:00:00 -0300</lastBuildDate><atom:link href="https://antoniovfranco.com/tags/open-source/index.xml" rel="self" type="application/rss+xml"/><item><title>Why Specialized SLMs Are the Standard From 2026 Onward</title><link>https://antoniovfranco.com/posts/2026/slm-specialized-2026/</link><pubDate>Mon, 04 May 2026 12:00:00 -0300</pubDate><guid>https://antoniovfranco.com/posts/2026/slm-specialized-2026/</guid><description>Specialized Small Language Models (SLMs) are replacing giant commercial LLMs as the standard for enterprise AI in 2026. Open-source SLMs deliver superior domain accuracy, lower infrastructure costs, and full data sovereignty — while LLM quality has plateaued.</description></item></channel></rss>