<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai-Infrastructure on F. Latini - IT Engineer</title><link>https://latini.dev/tags/ai-infrastructure/</link><description>Recent content in Ai-Infrastructure on F. Latini - IT Engineer</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 25 May 2026 08:00:00 +0000</lastBuildDate><atom:link href="https://latini.dev/tags/ai-infrastructure/index.xml" rel="self" type="application/rss+xml"/><item><title>Your LLM Platform Is Repeating Your ML Platform's Mistakes</title><link>https://latini.dev/posts/your-llm-platform-is-repeating-your-ml-platforms-mistakes/</link><pubDate>Mon, 25 May 2026 08:00:00 +0000</pubDate><guid>https://latini.dev/posts/your-llm-platform-is-repeating-your-ml-platforms-mistakes/</guid><description>&lt;p&gt;Every team I talk to is building an LLM platform right now. Some call it that. Some call it &amp;ldquo;the AI gateway&amp;rdquo;, &amp;ldquo;the prompt service&amp;rdquo;, &amp;ldquo;the agent stack&amp;rdquo;. The shape is the same: a layer between application teams and a handful of model providers, plus retrieval, plus evals, plus a slowly growing pile of glue.&lt;/p&gt;
&lt;p&gt;I have seen this movie. We made it five years ago and called it the ML platform. Most of the mistakes that made those platforms painful between 2018 and 2022 are quietly being reintroduced now, with bigger bills, more vendors, and less institutional memory.&lt;/p&gt;</description></item></channel></rss>