<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI on My New Hugo Project</title><link>https://example.org/en/ai/</link><description>Recent content in AI on My New Hugo Project</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Blog Author</copyright><lastBuildDate>Wed, 19 Aug 2026 09:00:00 +0800</lastBuildDate><atom:link href="https://example.org/en/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Getting Started with RAG</title><link>https://example.org/en/ai/rag-intro/</link><pubDate>Wed, 19 Aug 2026 09:00:00 +0800</pubDate><guid>https://example.org/en/ai/rag-intro/</guid><description>&lt;h2 class="relative group"&gt;Why RAG&#10; &lt;div id="why-rag" class="anchor"&gt;&lt;/div&gt;&#10; &#10; &lt;span&#10; class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;&#10; &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#why-rag" aria-label="Anchor"&gt;#&lt;/a&gt;&#10; &lt;/span&gt;&#10; &#10;&lt;/h2&gt;&#10;&lt;p&gt;LLM knowledge has a cutoff date and can&amp;rsquo;t cover private documents. &lt;strong&gt;Retrieval-augmented generation (RAG)&lt;/strong&gt; first retrieves relevant content from a knowledge base, then has the model answer based on it — sharply reducing hallucinations.&lt;/p&gt;</description></item><item><title>Prompt Engineering in Practice</title><link>https://example.org/en/ai/prompt-engineering/</link><pubDate>Tue, 18 Aug 2026 09:00:00 +0800</pubDate><guid>https://example.org/en/ai/prompt-engineering/</guid><description>&lt;h2 class="relative group"&gt;What is prompt engineering&#10; &lt;div id="what-is-prompt-engineering" class="anchor"&gt;&lt;/div&gt;&#10; &#10; &lt;span&#10; class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;&#10; &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-is-prompt-engineering" aria-label="Anchor"&gt;#&lt;/a&gt;&#10; &lt;/span&gt;&#10; &#10;&lt;/h2&gt;&#10;&lt;p&gt;A prompt is the interface to a large language model. &lt;strong&gt;Prompt engineering&lt;/strong&gt; designs that input so the model reliably produces high-quality output.&lt;/p&gt;</description></item><item><title>AI Technology Overview</title><link>https://example.org/en/ai/ai-overview/</link><pubDate>Mon, 17 Aug 2026 10:00:00 +0800</pubDate><guid>https://example.org/en/ai/ai-overview/</guid><description>&lt;h2 class="relative group"&gt;Machine learning and deep learning&#10; &lt;div id="machine-learning-and-deep-learning" class="anchor"&gt;&lt;/div&gt;&#10; &#10; &lt;span&#10; class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;&#10; &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#machine-learning-and-deep-learning" aria-label="Anchor"&gt;#&lt;/a&gt;&#10; &lt;/span&gt;&#10; &#10;&lt;/h2&gt;&#10;&lt;p&gt;Machine learning lets programs learn patterns from data automatically; deep learning uses multi-layer neural networks to excel at vision, speech, and text tasks.&lt;/p&gt;</description></item></channel></rss>