<?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>Inference on Show Me the Inference</title><link>https://showmetheinference.com/tags/inference/</link><description>Recent content in Inference on Show Me the Inference</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 29 Sep 2026 05:32:00 -0700</lastBuildDate><atom:link href="https://showmetheinference.com/tags/inference/index.xml" rel="self" type="application/rss+xml"/><item><title>604,649 Tokens and Not a Single Line of Code</title><link>https://showmetheinference.com/posts/604649-tokens-and-not-a-single-line-of-code/</link><pubDate>Tue, 29 Sep 2026 05:32:00 -0700</pubDate><guid>https://showmetheinference.com/posts/604649-tokens-and-not-a-single-line-of-code/</guid><description>Suitcase AI ran 604,649 tokens and guardrails read green. But the local agent was stuck in a thought loop while a cloud supervisor wrote all the code.</description></item><item><title>Why I Spent $5,000 on Hardware Instead of Tokens</title><link>https://showmetheinference.com/posts/why-i-spent-5000-on-hardware-instead-of-tokens/</link><pubDate>Thu, 17 Sep 2026 09:38:00 -0700</pubDate><guid>https://showmetheinference.com/posts/why-i-spent-5000-on-hardware-instead-of-tokens/</guid><description>Why I bought a $5,000 local inference box instead of burning a monthly cloud token budget, and how local hardware changes the way you build AI agents.</description></item><item><title>Show Me the Inference</title><link>https://showmetheinference.com/posts/show-me-the-inference/</link><pubDate>Fri, 28 Aug 2026 12:00:00 -0700</pubDate><guid>https://showmetheinference.com/posts/show-me-the-inference/</guid><description>I have not written more than a few lines of code in more than a year—and I am having more fun solving problems by directing an agent staff than I have had in a decade.</description></item></channel></rss>