<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Stan Tyan</title><description>Technical writing from stantyan.com.</description><link>https://stantyan.com/</link><lastBuildDate>Tue, 21 Jul 2026 13:00:00 GMT</lastBuildDate><item><title>Why AI Abstention Matters More Than Accuracy in Production AI Memory</title><link>https://stantyan.com/blog/ai-abstention-matters-more-than-accuracy/</link><guid isPermaLink="true">https://stantyan.com/blog/ai-abstention-matters-more-than-accuracy/</guid><description>AI abstention separates trustworthy AI memory from confident fabrication. Why a real &apos;no evidence found&apos; response is harder to engineer than retrieval.</description><pubDate>Tue, 21 Jul 2026 13:00:00 GMT</pubDate></item><item><title>AI Model Radar #1</title><link>https://stantyan.com/blog/ai-model-radar-1/</link><guid isPermaLink="true">https://stantyan.com/blog/ai-model-radar-1/</guid><description>Kimi K3 leads July 2026&apos;s radar, with Thinking Machines Inkling, Tencent Hy3, NVIDIA Audex-2B, and Ternary Bonsai 27B. What is verified and what to try first.</description><pubDate>Mon, 20 Jul 2026 19:00:00 GMT</pubDate></item><item><title>Portable AI Memory or Permanent Lock-In: The Architectural Choice That Will Define AI&apos;s Next Decade</title><link>https://stantyan.com/blog/portable-ai-memory-or-permanent-lock-in/</link><guid isPermaLink="true">https://stantyan.com/blog/portable-ai-memory-or-permanent-lock-in/</guid><description>AI memory is the new vendor lock-in. Open formats from one vendor are not enough - the category needs a neutral interchange standard, and regulation agrees.</description><pubDate>Tue, 14 Jul 2026 13:00:00 GMT</pubDate></item><item><title>Why AI Agents Forget by Design</title><link>https://stantyan.com/blog/why-ai-agents-forget/</link><guid isPermaLink="true">https://stantyan.com/blog/why-ai-agents-forget/</guid><description>AI agent memory failures aren&apos;t a bug. Statelessness is the architecture every major LLM provider chose, and the bill for that decision shows up every month.</description><pubDate>Tue, 07 Jul 2026 13:00:00 GMT</pubDate></item><item><title>Subscription Metrics That Actually Drive Decisions</title><link>https://stantyan.com/blog/subscription-metrics/</link><guid isPermaLink="true">https://stantyan.com/blog/subscription-metrics/</guid><description>A practitioner&apos;s reference to the subscription metrics that connect recurring revenue, retention, LTV, and unit economics into a system you can act on.</description><pubDate>Wed, 25 Mar 2026 00:00:00 GMT</pubDate></item><item><title>10 Machine Learning Algorithms You&apos;ll Actually Use in Production</title><link>https://stantyan.com/blog/machine-learning-algorithms-production/</link><guid isPermaLink="true">https://stantyan.com/blog/machine-learning-algorithms-production/</guid><description>The 10 ML algorithms that solve most real-world problems - when to use each, what breaks in production, and runnable Python code for every one.</description><pubDate>Mon, 16 Mar 2026 00:00:00 GMT</pubDate></item><item><title>The Science of Entrepreneurship</title><link>https://stantyan.com/blog/entrepreneurship/</link><guid isPermaLink="true">https://stantyan.com/blog/entrepreneurship/</guid><description>What data, frameworks, and eight years of startup research actually tell us about building ventures that survive - from Lean Startup to AI-native teams.</description><pubDate>Sat, 07 Dec 2019 00:00:00 GMT</pubDate></item><item><title>The Statistics Behind A/B Testing</title><link>https://stantyan.com/blog/statistics-behind-ab-testing/</link><guid isPermaLink="true">https://stantyan.com/blog/statistics-behind-ab-testing/</guid><description>A practitioner&apos;s walkthrough of the math that powers A/B tests - conversion rates, confidence intervals, Z-scores, and when to trust your results.</description><pubDate>Sat, 17 Aug 2019 00:00:00 GMT</pubDate></item><item><title>How A/B Testing Works</title><link>https://stantyan.com/blog/ab-testing/</link><guid isPermaLink="true">https://stantyan.com/blog/ab-testing/</guid><description>A/B testing compares two versions of something to see which performs better. Here&apos;s how it works, why confidence intervals matter, and how to avoid common mistakes.</description><pubDate>Wed, 10 Jul 2019 00:00:00 GMT</pubDate></item><item><title>Get Hired as a Data Scientist with Five Quick Tips</title><link>https://stantyan.com/blog/5-tips-to-get-hired-as-data-scientist/</link><guid isPermaLink="true">https://stantyan.com/blog/5-tips-to-get-hired-as-data-scientist/</guid><description>Five tips for getting hired as a data scientist or data analyst by making the hiring decision easier.</description><pubDate>Thu, 02 May 2019 00:00:00 GMT</pubDate></item></channel></rss>