<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM on Mi&amp;Bee Blog</title><link>/en/tags/llm/</link><description>Recent content in LLM on Mi&amp;Bee Blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>蓝宝石的傻话</managingEditor><lastBuildDate>Tue, 16 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="/en/tags/llm/rss.xml" rel="self" type="application/rss+xml"/><item><title>The Evolution of AI Engineering Paradigms: Four Shifts from Prompt Engineering to Loop Engineering</title><link>/en/posts/aihelper/ai-engineering-paradigms-overview/</link><pubDate>Tue, 16 Jun 2026 00:00:00 +0000</pubDate><guid>/en/posts/aihelper/ai-engineering-paradigms-overview/</guid><description>&lt;h2 id="why-understanding-these-four-stages-matters"&gt;Why Understanding These Four Stages Matters&lt;/h2&gt;
&lt;p&gt;The development of AI engineering is happening at a breathtaking pace. If you only master Prompt Engineering, you&amp;rsquo;re already behind by an entire era. From 2022 to now, in just four short years, AI engineering has undergone four profound paradigm shifts, each one transcending and including the previous one.&lt;/p&gt;
&lt;p&gt;Imagine learning programming: if you only learn print statements but don&amp;rsquo;t know about functions, classes, and frameworks, can you really write meaningful programs? The same applies to AI engineering. These four stages form a complete capability ladder—skip any step, and you&amp;rsquo;ll struggle in practical applications.&lt;/p&gt;</description></item><item><title>Prompt Engineering: Learning to Talk to AI Is Lesson One</title><link>/en/posts/aihelper/prompt-engineering-basics/</link><pubDate>Mon, 20 Nov 2023 00:00:00 +0000</pubDate><guid>/en/posts/aihelper/prompt-engineering-basics/</guid><description>&lt;h2 id="what-is-prompt-engineering"&gt;What is Prompt Engineering?&lt;/h2&gt;
&lt;p&gt;The core definition of Prompt Engineering is: &lt;strong&gt;Designing natural language inputs to guide Large Language Model outputs toward specific results&lt;/strong&gt;.&lt;/p&gt;
&lt;p&gt;This concept seems simple, but it hides a profound assumption: &lt;strong&gt;The same model, different prompts → completely different outputs&lt;/strong&gt;.&lt;/p&gt;
&lt;p&gt;Imagine you have an incredibly smart assistant with zero background knowledge. This assistant can perfectly understand and execute any instruction, but it lacks prior knowledge and has no memory. Prompt engineering is the art of learning how to converse with such an assistant.&lt;/p&gt;</description></item></channel></rss>