<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Stochasticity on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/stochasticity/</link>
    <description>Recent content in Stochasticity on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <atom:link href="http://programmer.ie/tags/stochasticity/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Introduction to LLM Agents</title>
      <link>http://programmer.ie/books/agent-architectures/01-chapter/</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      <guid>http://programmer.ie/books/agent-architectures/01-chapter/</guid>
      <description>&lt;h3 id=&#34;what-is-an-llm-agent&#34;&gt;What Is an LLM Agent?&lt;/h3&gt;&#xA;&lt;p&gt;An &lt;strong&gt;LLM agent&lt;/strong&gt; is a software system built around a language model that can pursue a goal through context, state, tool use, feedback, and repeated interaction.&lt;/p&gt;&#xA;&lt;p&gt;The model is important, but it is not the whole agent. The larger system supplies the prompt, chooses what context the model sees, exposes tools, records state, retrieves memory, validates actions, handles errors, and decides when the work is finished. When people say that an agent &amp;ldquo;remembers,&amp;rdquo; &amp;ldquo;plans,&amp;rdquo; or &amp;ldquo;uses a tool,&amp;rdquo; the precise mechanism usually belongs to this surrounding runtime, not to the model by itself.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Methodologies and Core Patterns</title>
      <link>http://programmer.ie/books/agent-architectures/02-chapter/</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      <guid>http://programmer.ie/books/agent-architectures/02-chapter/</guid>
      <description>&lt;h3 id=&#34;five-core-shifts-in-the-ai-human-paradigm&#34;&gt;Five Core Shifts in the AI-Human Paradigm&lt;/h3&gt;&#xA;&lt;p&gt;Chapter 1 introduced agents as systems built around language models, not as models alone. This chapter looks at the working patterns that make those systems useful.&lt;/p&gt;&#xA;&lt;p&gt;The patterns are not complicated. They are easy to miss because they do not look like traditional programming. You converse, inspect, revise, compare, preserve, and try again. The loop is simple, but its consequences are large.&lt;/p&gt;&#xA;&lt;p&gt;Five shifts sit underneath that loop.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
