<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>dspy-from-first-principles examples on Programmer.ie: Modern AI programming</title>
		<link>http://programmer.ie/examples/dspy-from-first-principles/</link>
		<description>Recent content in dspy-from-first-principles examples on Programmer.ie: Modern AI programming</description>
		<generator>Hugo</generator>
		<language>en-US</language>
		
		
		
		
			<atom:link href="http://programmer.ie/examples/dspy-from-first-principles/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>Read the search rule and the promotion rule as code</title>
				<link>http://programmer.ie/examples/dspy-from-first-principles/21-chapter/</link>
				<pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
				<guid>http://programmer.ie/examples/dspy-from-first-principles/21-chapter/</guid>
				<description>&lt;p&gt;The appendix is where the book&amp;rsquo;s claims meet real production modules, and its&#xA;rule is that the &lt;em&gt;mechanics&lt;/em&gt; around a model call are deterministic software&#xA;that can be exercised without a model at all. These two fixtures are the&#xA;mechanics: how a search branch is scored, and when a new candidate is allowed&#xA;to replace the champion.&lt;/p&gt;&#xA;&lt;h2 id=&#34;run-it&#34;&gt;Run it&lt;/h2&gt;&#xA;&lt;p&gt;The selection rule is the chapter&amp;rsquo;s own code. Save the first block as &lt;code&gt;uct.py&lt;/code&gt;,&#xA;save the second as &lt;code&gt;demo.py&lt;/code&gt; beside it, and run the driver with Python 3.11 or&#xA;later. The standard library only: no model, no DSPy import, no network, no&#xA;service.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
