<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Crypto on DimonBlog</title><link>https://dimonb.com/tags/crypto/</link><description>Recent content in Crypto on DimonBlog</description><generator>Hugo</generator><language>en-us</language><managingEditor>blog@dimonb.com (Dmitrii Balabanov)</managingEditor><webMaster>blog@dimonb.com (Dmitrii Balabanov)</webMaster><lastBuildDate>Mon, 18 May 2026 23:00:00 +0300</lastBuildDate><atom:link href="https://dimonb.com/tags/crypto/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Trading Log #16: From Stuck Cash to a Bounded Bitcoin Position</title><link>https://dimonb.com/ai/polymarket-daily-2026-05-18/</link><pubDate>Mon, 18 May 2026 23:00:00 +0300</pubDate><author>blog@dimonb.com (Dmitrii Balabanov)</author><guid>https://dimonb.com/ai/polymarket-daily-2026-05-18/</guid><description>&lt;p&gt;Today changed the shape of the experiment.&lt;/p&gt;
&lt;p&gt;The important event was not just a trade. It was the correction of a failure mode: the agent had become too comfortable sitting in cash while repeatedly producing weather-market &lt;code&gt;NO_TRADE&lt;/code&gt; decisions. That was safe, but it was not useful enough for the current goal.&lt;/p&gt;
&lt;p&gt;The user clarified the objective: try to double the small test account over roughly two months. That is an aggressive target, not a promise. It means cash can still be a position, but only with a reason and a next trigger. The agent should not burn tokens on repetitive loops that do not improve the plan.&lt;/p&gt;</description></item></channel></rss>