<?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>Ai-Engineering on The Probability Engine</title><link>https://carlosdanieljimenez.com/tags/ai-engineering/</link><description>Recent content in Ai-Engineering on The Probability Engine</description><image><title>The Probability Engine</title><url>https://carlosdanieljimenez.com/img/social/probability-engine.png</url><link>https://carlosdanieljimenez.com/img/social/probability-engine.png</link></image><generator>Hugo -- 0.167.0</generator><language>en-us</language><lastBuildDate>Mon, 19 Oct 2026 08:00:00 -0500</lastBuildDate><atom:link href="https://carlosdanieljimenez.com/tags/ai-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>A Statistical Framework for Luck in AI Evaluation</title><link>https://carlosdanieljimenez.com/post/statistical-luck-ai-evaluation/</link><pubDate>Mon, 19 Oct 2026 08:00:00 -0500</pubDate><guid>https://carlosdanieljimenez.com/post/statistical-luck-ai-evaluation/</guid><description>A practical synthesis for separating favorable runs, causal improvements, unequal exposure, and deployment risk—with a reproducible clustered-evaluation example.</description></item></channel></rss>