<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Llms on vnykmshr</title><link>https://blog.vnykmshr.com/writing/tags/llms/</link><description>Recent content in Llms on vnykmshr</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 07 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.vnykmshr.com/writing/tags/llms/index.xml" rel="self" type="application/rss+xml"/><item><title>Garbage context in, garbage code out</title><link>https://blog.vnykmshr.com/writing/garbage-context-garbage-code/</link><pubDate>Sat, 07 Mar 2026 00:00:00 +0000</pubDate><guid>https://blog.vnykmshr.com/writing/garbage-context-garbage-code/</guid><description>&lt;p&gt;LLMs are exactly as good as what you feed them.&lt;/p&gt;
&lt;p&gt;Experienced engineers feel like the gap between them and everyone else just got smaller. Someone with six months of prompting can ship something that looks like what took years to learn how to build. That&amp;rsquo;s the wrong read.&lt;/p&gt;
&lt;p&gt;The output looks the same if you don&amp;rsquo;t look closely. The architecture doesn&amp;rsquo;t. The failure modes don&amp;rsquo;t. When traffic spikes and that generated code hits a path nobody thought about, the years show up.&lt;/p&gt;</description></item><item><title>Hello world, printf</title><link>https://blog.vnykmshr.com/writing/hello-world-printf/</link><pubDate>Mon, 16 Feb 2026 00:00:00 +0000</pubDate><guid>https://blog.vnykmshr.com/writing/hello-world-printf/</guid><description>&lt;p&gt;Printf wasn&amp;rsquo;t always there. Before it, you wrote to stdout directly. Before stdout, a syscall. Before the syscall, you poked bytes into a memory-mapped display buffer. Before the memory map, you flipped switches on a front panel and watched lights blink back.&lt;/p&gt;
&lt;p&gt;Every layer down, someone built something so the next person wouldn&amp;rsquo;t have to. That&amp;rsquo;s the whole field. Languages we didn&amp;rsquo;t design, compilers we didn&amp;rsquo;t write, protocols we didn&amp;rsquo;t invent. We&amp;rsquo;ve always stood on a stack of other people&amp;rsquo;s work and called the output ours. Nobody ever had a problem with that.&lt;/p&gt;</description></item></channel></rss>