<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Gen-Ai on Minimum Viable Blog</title>
    <link>http://isaaclyman.com/blog/tags/gen-ai/</link>
    <description>Recent content in Gen-Ai on Minimum Viable Blog</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <managingEditor>map[host:isaaclyman.com username:blog] (Isaac Lyman)</managingEditor>
    <webMaster>map[host:isaaclyman.com username:blog] (Isaac Lyman)</webMaster>
    <copyright>© 2026 by Isaac Lyman. No AI-generated content has ever appeared on this blog.</copyright>
    <lastBuildDate>Fri, 30 Oct 2026 09:18:11 -0600</lastBuildDate>
    <atom:link href="http://isaaclyman.com/blog/tags/gen-ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Why do people say AI codegen has improved?</title>
      <link>http://isaaclyman.com/blog/posts/why-people-say-ai-has-improved/</link>
      <pubDate>Fri, 30 Oct 2026 09:18:11 -0600</pubDate><author>map[host:isaaclyman.com username:blog] (Isaac Lyman)</author>
      <guid>http://isaaclyman.com/blog/posts/why-people-say-ai-has-improved/</guid>
      <description>Since at least 2023, there’s been a persistent trend of people saying that “AI code generation is much better now than it was six months ago.” There are multiple possible reasons why someone might say this, and a neutral observer should consider all of them.&#xA;I don’t believe the phenomenon can be fully explained by any one reason. Rather, I believe all of these reasons have, to varying extents, played a role.</description>
    </item>
    <item>
      <title>Four essential laws of programming</title>
      <link>http://isaaclyman.com/blog/posts/essential-laws/</link>
      <pubDate>Mon, 21 Sep 2026 09:49:10 -0600</pubDate><author>map[host:isaaclyman.com username:blog] (Isaac Lyman)</author>
      <guid>http://isaaclyman.com/blog/posts/essential-laws/</guid>
      <description>There are two distinct kinds of software:&#xA;Software as a tool is designed to make a given task faster, simpler, safer, cheaper, or more reliable. Software as a financial asset is designed grow the wealth of its investors. Much as it seems like these goals should be aligned, all real-world evidence points to them being incompatible. The second type of software tends to be worse by every measure of the first (if it exists as a usable product at all) and tends to get steadily worse over time.</description>
    </item>
    <item>
      <title>The parable of the bowling machine</title>
      <link>http://isaaclyman.com/blog/posts/bowling/</link>
      <pubDate>Sun, 26 Jul 2026 12:23:52 -0600</pubDate><author>map[host:isaaclyman.com username:blog] (Isaac Lyman)</author>
      <guid>http://isaaclyman.com/blog/posts/bowling/</guid>
      <description>My friend Larry is getting on in age. I notice it most when he smiles. His thick, round glasses magnify the wrinkles around his eyes, a pattern of lines so familiar I&amp;rsquo;d recognize them in a dry riverbed. In his prime he was a semi-professional bowler—he laughs when he says it because he mostly did charity events. But his team paid him a modest stipend for travel, which is more than most people get.</description>
    </item>
    <item>
      <title>There is no genius</title>
      <link>http://isaaclyman.com/blog/posts/there-is-no-genius/</link>
      <pubDate>Tue, 19 May 2026 11:27:17 -0600</pubDate><author>map[host:isaaclyman.com username:blog] (Isaac Lyman)</author>
      <guid>http://isaaclyman.com/blog/posts/there-is-no-genius/</guid>
      <description>A paradox: when we try to applaud work, we often efface it. Authors are asked where they get their ideas. Athletes are described in terms of raw talent. Film directors are called geniuses and visionaries. This implies that people who rise to the top have won an invisible lottery: they were born or gifted with a difference, a lucky advantage, and if someone else had gotten it, they would be there too.</description>
    </item>
    <item>
      <title>Five laws of generative AI</title>
      <link>http://isaaclyman.com/blog/posts/five-laws-of-ai/</link>
      <pubDate>Mon, 20 Apr 2026 07:40:11 -0600</pubDate><author>map[host:isaaclyman.com username:blog] (Isaac Lyman)</author>
      <guid>http://isaaclyman.com/blog/posts/five-laws-of-ai/</guid>
      <description>These laws have some exceptions, but I&amp;rsquo;ve found them broadly useful for navigating the current hype wave, and nearly always correct.&#xA;AI is a firehose of mediocrity. AI&amp;rsquo;s advantages can&amp;rsquo;t be disentangled from its flaws. It&amp;rsquo;s never &amp;ldquo;just&amp;rdquo; AI. The term is more important than the definition. The promise is more important than the reality. For the purposes of this post, &amp;ldquo;AI&amp;rdquo; means generative AI.&#xA;I&amp;rsquo;ve added a few brief thoughts on each law below.</description>
    </item>
    <item>
      <title>Myth vs. Fact: why is code review so hard?</title>
      <link>http://isaaclyman.com/blog/posts/code-review/</link>
      <pubDate>Mon, 23 Mar 2026 16:32:19 -0600</pubDate><author>map[host:isaaclyman.com username:blog] (Isaac Lyman)</author>
      <guid>http://isaaclyman.com/blog/posts/code-review/</guid>
      <description>A lot of teams procrastinate code review, phone it in, or get stuck in endless back-and-forth on every PR. Let&amp;rsquo;s talk about why.&#xA;Myth #1 Myth: Code review is difficult because it&amp;rsquo;s boring and pull requests are too long.&#xA;Fact: Code review is difficult because it duplicates the cognitive work of programming without all the intermediate steps.&#xA;Engineers tend to dislike reviewing code. Instead of just accepting it as an unpleasant part of the job, we should ask why.</description>
    </item>
    <item>
      <title>Coding without AI: a revolutionary new way to work</title>
      <link>http://isaaclyman.com/blog/posts/coding-without-ai/</link>
      <pubDate>Sat, 14 Mar 2026 10:52:44 -0600</pubDate><author>map[host:isaaclyman.com username:blog] (Isaac Lyman)</author>
      <guid>http://isaaclyman.com/blog/posts/coding-without-ai/</guid>
      <description>For the last 20 years or so I&amp;rsquo;ve been trying out a new way of programming, one that (surprisingly) doesn&amp;rsquo;t use any LLMs or AI coding agents at all. It&amp;rsquo;s just me, a keyboard, and an IDE or text editor, writing code line by line—literally typing things like functions and curly braces.&#xA;I realize this sounds eccentric. What am I, some kind of minimalist? Actually, I&amp;rsquo;m what you might call an &amp;ldquo;early adopter.</description>
    </item>
  </channel>
</rss>
