<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Training on Zero Day AI Labs</title><link>https://www.zero-day.ai/training/</link><description>Recent content in Training on Zero Day AI Labs</description><generator>Hugo</generator><language>en-us</language><atom:link href="https://www.zero-day.ai/training/index.xml" rel="self" type="application/rss+xml"/><item><title>Agents in Production</title><link>https://www.zero-day.ai/training/agents-in-production/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.zero-day.ai/training/agents-in-production/</guid><description>&lt;h2 id="who-it-is-for"&gt;Who it is for&lt;/h2&gt;&#10;&lt;p&gt;You have agents that work in a demo. You need them to run every day, for many&#10;users, without a person watching each one. You have to answer for what they&#10;did afterwards.&lt;/p&gt;</description></item><item><title>Attacking and Defending AI Agents</title><link>https://www.zero-day.ai/training/attacking-and-defending-ai-agents/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.zero-day.ai/training/attacking-and-defending-ai-agents/</guid><description>&lt;h2 id="who-it-is-for"&gt;Who it is for&lt;/h2&gt;&#10;&lt;p&gt;You defend, or will defend, agents that read the web, hold credentials, and&#10;run tools. You want to know what an attacker does first, and what a control&#10;must refuse for that attack to fail. You bring an agent you run today, or you&#10;use ours.&lt;/p&gt;</description></item><item><title>LLM Infrastructure on Kubernetes</title><link>https://www.zero-day.ai/training/llm-infrastructure-on-kubernetes/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.zero-day.ai/training/llm-infrastructure-on-kubernetes/</guid><description>&lt;h2 id="who-it-is-for"&gt;Who it is for&lt;/h2&gt;&#10;&lt;p&gt;You run, or are about to run, models on your own hardware or your own cloud&#10;account. You know Kubernetes. You have not yet put a GPU node pool, a training&#10;scheduler, and a serving layer into one cluster and kept it up.&lt;/p&gt;</description></item></channel></rss>