<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Thinking AI on AIBussin — AI applications, systems and books</title><link>https://aibussin.com/tags/thinking-ai/</link><description>Recent content in Thinking AI on AIBussin — AI applications, systems and books</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Mon, 23 Jun 2025 11:10:59 +0100</lastBuildDate><atom:link href="https://aibussin.com/tags/thinking-ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Thoughts of Algorithms</title><link>https://aibussin.com/post/thoughts/</link><pubDate>Mon, 23 Jun 2025 11:10:59 +0100</pubDate><guid>https://aibussin.com/post/thoughts/</guid><description>&lt;blockquote&gt;&#10;&lt;p&gt;How a self-evolving AI learns to reflect, score, and rewrite its own reasoning&lt;/p&gt;&#10;&lt;/blockquote&gt;&#10;&lt;h2 id="-summary"&gt;🧪 Summary&lt;/h2&gt;&#10;&lt;p&gt;What if an AI could think not just solve problems, but reevaluate its beliefs in the face of new information?&lt;/p&gt;&#10;&lt;p&gt;In this post, we introduce a system that does exactly that. At the core of our pipeline is a lightweight scoring model called MR.Q, responsible for evaluating ideas and choosing the best ones. But when it encounters a new domain, a new goal, or a shift in task format, it doesn’t freeze it adapts.&lt;/p&gt;</description></item></channel></rss>