<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Resources on Amir Hadifar</title>
    <link>https://hadifar.net/categories/resources/</link>
    <description>Recent content in Resources on Amir Hadifar</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 20 Jul 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://hadifar.net/categories/resources/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Modern Software Developer course</title>
      <link>https://hadifar.net/posts/modern-software-developer-course/</link>
      <pubDate>Mon, 20 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://hadifar.net/posts/modern-software-developer-course/</guid>
      <description>&lt;p&gt;&lt;a href=&#34;https://themodernsoftware.dev/&#34;&gt;The Modern Software Developer&lt;/a&gt; is a Stanford course
(CS146S) that covers most of what you need to know about agentic coding — prompting
techniques, AI IDEs, patterns, and more.&lt;/p&gt;
&lt;h2 id=&#34;why-its-worth-it&#34;&gt;Why it&amp;rsquo;s worth it&lt;/h2&gt;
&lt;p&gt;I highly recommend this course: it covers the foundations you need, from the ground up.&lt;/p&gt;
&lt;p&gt;It starts by introducing LLMs and different prompting strategies — K-shot, chain-of-thought,
self-critique, and others — before moving on to the tooling and patterns of agentic
coding.&lt;/p&gt;</description>
    </item>
    <item>
      <title>YC guide to vibe coding</title>
      <link>https://hadifar.net/posts/yc-guide-to-vibe-coding/</link>
      <pubDate>Thu, 16 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://hadifar.net/posts/yc-guide-to-vibe-coding/</guid>
      <description>&lt;p&gt;These are the notes from talks at &lt;em&gt;Y Combinator&lt;/em&gt;.&lt;/p&gt;
&lt;h2 id=&#34;general-rule-of-thumb&#34;&gt;General rule of thumb&lt;/h2&gt;
&lt;p&gt;The best technique is to do what a professional software engineer already does. &lt;strong&gt;Small code&lt;/strong&gt;, &lt;strong&gt;modularity&lt;/strong&gt;, and
&lt;strong&gt;abstraction&lt;/strong&gt; are your friends — they help both you and the LLM reason about the project.&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;Note: this advice will likely shift over the next few months. As models
get more capable, some of these guardrails will loosen.&lt;/p&gt;
&lt;/blockquote&gt;
&lt;h2 id=&#34;plan-before-you-build&#34;&gt;Plan before you build&lt;/h2&gt;
&lt;p&gt;Don&amp;rsquo;t ask the model to one-shot the whole project. Instead, create a planning file (a
&lt;code&gt;CLAUDE.md&lt;/code&gt; or a plain markdown file) that lays out step by step what you want to build.
Iterate on it over time and revise it whenever your understanding changes. You can even
use a Planner agent to help revise it.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
