<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Hey MHK</title><description>A digital third place for thinking out loud about AI, data, and the infrastructure underneath.</description><link>https://hey-mhk.com/</link><item><title>What the Engine Room Taught Me</title><link>https://hey-mhk.com/blog/what-the-engine-room-taught-me/</link><guid isPermaLink="true">https://hey-mhk.com/blog/what-the-engine-room-taught-me/</guid><description>These systems are more comprehensible than marketing suggests, and more limited than hype implies. Both are true simultaneously.</description><pubDate>Thu, 11 Jun 2026 00:00:00 GMT</pubDate></item><item><title>AI Readiness Is a Governance Question</title><link>https://hey-mhk.com/blog/ai-readiness-is-a-governance-question/</link><guid isPermaLink="true">https://hey-mhk.com/blog/ai-readiness-is-a-governance-question/</guid><description>Every AI conversation eventually becomes a data conversation. Every data conversation eventually becomes a governance conversation. The sequence matters.</description><pubDate>Wed, 10 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Working With the Machine</title><link>https://hey-mhk.com/blog/working-with-the-machine/</link><guid isPermaLink="true">https://hey-mhk.com/blog/working-with-the-machine/</guid><description>The most valuable prompting skill isn&apos;t writing better prompts. It&apos;s knowing when prompting isn&apos;t the answer.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Hallucination is a Feature, Not a Bug</title><link>https://hey-mhk.com/blog/hallucination-is-a-feature-not-a-bug/</link><guid isPermaLink="true">https://hey-mhk.com/blog/hallucination-is-a-feature-not-a-bug/</guid><description>Vendors frame hallucination as a bug they&apos;re fixing. It&apos;s actually inherent to how these systems work, which changes the governance question entirely.</description><pubDate>Mon, 08 Jun 2026 00:00:00 GMT</pubDate></item><item><title>UI as the Ultimate Guardrail</title><link>https://hey-mhk.com/blog/ui-as-the-ultimate-guardrail/</link><guid isPermaLink="true">https://hey-mhk.com/blog/ui-as-the-ultimate-guardrail/</guid><description>AI systems speak with uniform confidence whether they&apos;re right or wrong. Interface design determines whether that difference becomes visible.</description><pubDate>Sun, 07 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Why Vectors Aren&apos;t Enough</title><link>https://hey-mhk.com/blog/why-vectors-arent-enough/</link><guid isPermaLink="true">https://hey-mhk.com/blog/why-vectors-arent-enough/</guid><description>Vector search finds what&apos;s similar. Expertise often requires connecting things that aren&apos;t similar at all.</description><pubDate>Sat, 06 Jun 2026 00:00:00 GMT</pubDate></item><item><title>The Tacit Knowledge Bottleneck</title><link>https://hey-mhk.com/blog/the-tacit-knowledge-bottleneck/</link><guid isPermaLink="true">https://hey-mhk.com/blog/the-tacit-knowledge-bottleneck/</guid><description>The most valuable knowledge in any organization is often the hardest to capture, because the people who have it can&apos;t fully explain it.</description><pubDate>Fri, 05 Jun 2026 00:00:00 GMT</pubDate></item><item><title>The Multiplier Effect</title><link>https://hey-mhk.com/blog/the-multiplier-effect/</link><guid isPermaLink="true">https://hey-mhk.com/blog/the-multiplier-effect/</guid><description>Proprietary data isn&apos;t the AI advantage most organizations think it is. What that data connects to is.</description><pubDate>Thu, 04 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Context Windows and Memory</title><link>https://hey-mhk.com/blog/context-windows-and-memory/</link><guid isPermaLink="true">https://hey-mhk.com/blog/context-windows-and-memory/</guid><description>The most common misconception I encounter: people assume these models remember previous conversations. They don&apos;t.</description><pubDate>Wed, 03 Jun 2026 00:00:00 GMT</pubDate></item><item><title>The Efficiency Illusion</title><link>https://hey-mhk.com/blog/the-efficiency-illusion/</link><guid isPermaLink="true">https://hey-mhk.com/blog/the-efficiency-illusion/</guid><description>That benchmark showing the smaller model matches GPT-4? Probably accurate. Also hiding tradeoffs that only surface in production.</description><pubDate>Tue, 02 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Training Economics</title><link>https://hey-mhk.com/blog/training-economics/</link><guid isPermaLink="true">https://hey-mhk.com/blog/training-economics/</guid><description>&quot;Let&apos;s just train a model on our data&quot; sounds straightforward. The actual cost structure tells a different story.</description><pubDate>Mon, 01 Jun 2026 00:00:00 GMT</pubDate></item><item><title>The Attention Mechanism Explained</title><link>https://hey-mhk.com/blog/the-attention-mechanism-explained/</link><guid isPermaLink="true">https://hey-mhk.com/blog/the-attention-mechanism-explained/</guid><description>&quot;Attention&quot; is a brilliant name for what these models do, and also misleading in ways that matter.</description><pubDate>Sun, 31 May 2026 00:00:00 GMT</pubDate></item><item><title>I&apos;ve Heard This Engine Before</title><link>https://hey-mhk.com/blog/ive-heard-this-engine-before/</link><guid isPermaLink="true">https://hey-mhk.com/blog/ive-heard-this-engine-before/</guid><description>I worked on attention mechanisms before ChatGPT made them famous. That perspective has shaped how I separate AI signal from noise.</description><pubDate>Sat, 30 May 2026 00:00:00 GMT</pubDate></item></channel></rss>