<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM on FX Backtest Diary</title><link>https://etherpoc.com/en/tags/llm/</link><description>Recent content in LLM on FX Backtest Diary</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 21 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://etherpoc.com/en/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Measuring 'it comes down to discretion' to death: 88 conditions and an AI eye</title><link>https://etherpoc.com/en/posts/discretion-final/</link><pubDate>Tue, 21 Jul 2026 00:00:00 +0000</pubDate><guid>https://etherpoc.com/en/posts/discretion-final/</guid><description>&lt;p&gt;Every strategy video has the same closing line: &amp;ldquo;in the end, it comes down to discretion&amp;rdquo;. Show mechanically that the rules lose, and this one sentence resets the whole debate. Discretion cannot be put into words, therefore cannot be measured, therefore cannot be refuted. So the story goes.&lt;/p&gt;
&lt;p&gt;Does it hold? I decided discretion becomes measurable the moment you redefine it as information: the ability to select better-than-average trades out of a candidate stream. Then I measured every route that information could travel: 88 verbalizable conditions, cross-market context, the entire multi-timeframe combination space, machine learning, state-of-the-art vision AI, and my own blind-test performance.&lt;/p&gt;</description></item></channel></rss>