<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>How-I-Ai on AI Engineer Guide</title><link>https://aiengineerguide.com/tags/how-i-ai/</link><description>Recent content in How-I-Ai on AI Engineer Guide</description><generator>Hugo</generator><language>en-US</language><copyright>Copyright © 2024-2026, Nesin Technologies LLP.</copyright><lastBuildDate>Mon, 03 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://aiengineerguide.com/tags/how-i-ai/feed.xml" rel="self" type="application/rss+xml"/><item><title>Why I Manually Type LLM-Generated Code</title><link>https://aiengineerguide.com/til/manually-retyping-llm-generated-code/</link><pubDate>Mon, 03 Aug 2026 00:00:00 +0000</pubDate><guid>https://aiengineerguide.com/til/manually-retyping-llm-generated-code/</guid><description>&lt;p>Ankur Sethi has written about his approach on how he uses AI to generate the code but he manually writes them.&lt;/p>
&lt;blockquote>
&lt;p>As I manually type every single line of LLM generated code into my editor, I build up a mental model of how it works and fits into my existing codebase. If I don&amp;rsquo;t understand an API or algorithm, I can stop to look it up, or just ask the LLM to explain it.&lt;/p></description></item></channel></rss>