<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Stewart Jamieson</title><description>Stewart Jamieson — Head of Technology at Themis AI. Writing on risk-aware, uncertainty-aware AI: technical deep-dives and AI strategy &amp; systems.</description><link>https://www.stewartjamieson.com/</link><language>en-us</language><item><title>Acting on Low Confidence: Hedge, Abstain, or Escalate</title><link>https://www.stewartjamieson.com/writing/acting-on-low-confidence/</link><guid isPermaLink="true">https://www.stewartjamieson.com/writing/acting-on-low-confidence/</guid><description>When a system is unsure, the cost of being wrong — not the confidence score — should decide whether it hedges, abstains, or calls a human.</description><pubDate>Tue, 23 Jun 2026 00:00:00 GMT</pubDate><category>uncertainty</category><category>escalation</category><category>selective prediction</category></item><item><title>Building Reliable Systems from Uncertainty-Aware Components</title><link>https://www.stewartjamieson.com/writing/reliable-systems-from-uncertain-components/</link><guid isPermaLink="true">https://www.stewartjamieson.com/writing/reliable-systems-from-uncertain-components/</guid><description>Reliable AI systems come from how you handle uncertainty across components — not from making any single component better. A short field guide.</description><pubDate>Mon, 22 Jun 2026 00:00:00 GMT</pubDate><category>uncertainty</category><category>reliability</category><category>ai systems</category></item></channel></rss>