<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Machine-Learning on Rafael Zago</title><link>https://www.rafaelvzago.com/en/tags/machine-learning/</link><description>Recent content in Machine-Learning on Rafael Zago</description><generator>Hugo</generator><language>en-US</language><copyright>© Rafael Zago</copyright><lastBuildDate>Fri, 24 Jul 2026 16:16:10 -0300</lastBuildDate><atom:link href="https://www.rafaelvzago.com/en/tags/machine-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>How an AI works when you talk to it</title><link>https://www.rafaelvzago.com/en/posts/o-que-acontece-quando-voce-conversa-com-uma-ia/</link><pubDate>Wed, 24 Dec 2025 00:00:00 -0300</pubDate><guid>https://www.rafaelvzago.com/en/posts/o-que-acontece-quando-voce-conversa-com-uma-ia/</guid><description>&lt;p>&lt;a href="https://www.rafaelvzago.com/assets/img/headers/o-que-acontece-quando-voce-conversa-com-uma-ia.png" class="img-lightbox" data-lightbox>
	&lt;img src="https://www.rafaelvzago.com/assets/img/headers/o-que-acontece-quando-voce-conversa-com-uma-ia.png" alt="" loading="lazy" decoding="async">
&lt;/a>&lt;/p>
&lt;div style="position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden;">
 &lt;iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" loading="eager" referrerpolicy="strict-origin-when-cross-origin" src="https://www.youtube.com/embed/uhxG2B96k7Q?autoplay=0&amp;amp;controls=1&amp;amp;end=0&amp;amp;loop=0&amp;amp;mute=0&amp;amp;start=0" style="position: absolute; top: 0; left: 0; width: 100%; height: 100%; border:0;" title="YouTube video">&lt;/iframe>
 &lt;/div>

&lt;h2 id="unpacking-large-language-models">Unpacking large language models&lt;/h2>
&lt;p>When you type a message to ChatGPT or Claude, what happens on the other side is simpler than it looks—but it runs at a scale that is hard to picture.&lt;/p>
&lt;h2 id="the-essence-a-digital-football-commentator">The essence: a digital football commentator&lt;/h2>
&lt;p>Picture this: World Cup final, Brazil vs Argentina, last minutes of the match. Galvão Bueno is calling the game, the ball reaches the Brazilian striker, he beats one defender, then another&amp;hellip; and suddenly the audio cuts out. The broadcast keeps rolling, but the commentator&amp;rsquo;s voice is gone.&lt;/p></description></item><item><title>InstructLab and Skupper: local AI without exposing data</title><link>https://www.rafaelvzago.com/en/posts/running-local-ai-with-instruct-lab/</link><pubDate>Thu, 01 Aug 2024 00:00:00 -0300</pubDate><guid>https://www.rafaelvzago.com/en/posts/running-local-ai-with-instruct-lab/</guid><description>&lt;p>&lt;a href="https://www.rafaelvzago.com/assets/img/headers/instructlab_workshop-skupper-patient-portal.jpg" class="img-lightbox" data-lightbox>
	&lt;img src="https://www.rafaelvzago.com/assets/img/headers/instructlab_workshop-skupper-patient-portal.jpg" alt="" loading="lazy" decoding="async">
&lt;/a>&lt;/p>
&lt;h1 id="welcome-to-the-ollama-pilot">Welcome to the Ollama Pilot.&lt;/h1>
&lt;h2 id="problem-to-solve">Problem to solve&lt;/h2>
&lt;p>&lt;a href="https://www.rafaelvzago.com/assets/instructlab_banner.jpg" class="img-lightbox" data-lightbox>
	&lt;img src="https://www.rafaelvzago.com/assets/instructlab_banner.jpg" alt="contest" loading="lazy" decoding="async">
&lt;/a>&lt;/p>
&lt;p>The main goal of this project is to create a secure connection between two sites, enabling the communication between the engineer machine and an Instruct Lab Model. The merlinite-7b-lab-Q4_K_M.gguf model will be used for the chatbot, and it is available in the Instruct Lab. The license of the model is available in the &lt;a href="https://instructlab.ai/">Instruct Labs&lt;/a>.&lt;/p>
&lt;p>But, why the banner? Well, the engineer needs to know who is better, Lebron or Jordan. The chatbot will be responsible for answering this question. The chatbot will receive the user input and send it to the llama3 model. The response from the merlinite model will be sent back to the user.&lt;/p></description></item><item><title>OpenShift AI and Skupper: insurance fraud prevention</title><link>https://www.rafaelvzago.com/en/posts/ai-com-skupper-para-previnir-fraudes/</link><pubDate>Mon, 17 Jun 2024 00:00:00 -0300</pubDate><guid>https://www.rafaelvzago.com/en/posts/ai-com-skupper-para-previnir-fraudes/</guid><description>&lt;p>&lt;a href="https://www.rafaelvzago.com/assets/img/headers/AI-com-skupper-para-previnir-fraudes.webp" class="img-lightbox" data-lightbox>
	&lt;img src="https://www.rafaelvzago.com/assets/img/headers/AI-com-skupper-para-previnir-fraudes.webp" alt="" loading="lazy" decoding="async">
&lt;/a>&lt;/p>
&lt;h2 id="description">Description&lt;/h2>
&lt;p>This workshop demonstrates how to use Skupper to connect local data services to cloud-based AI/ML environments. The workshop includes a Go application in a podman container that exposes internal data for Skupper connection. The AI/ML model training is performed in an OpenShift AI cluster on AWS using Openshift AI/ML services.&lt;/p>
&lt;h2 id="disclaimer">Disclaimer&lt;/h2>
&lt;p>This lab uses the example from the &lt;a href="https://github.com/rh-aiservices-bu/insurance-claim-processing">AI/ML Workshop&lt;/a> created by the Red Hat AI Services team. The original workshop is available on GitHub and includes all the necessary information to run the lab. The lab was adapted to use Skupper to connect the local data services to the cloud-based AI/ML environment.&lt;/p></description></item></channel></rss>