<?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 Robles.dev</title>
    <link>https://roblesdev.com/blog/llm/</link>
    <description>Recent content in LLM on Robles.dev</description>
    <generator>Hugo</generator>
    <language>en-US</language>
    <copyright>Copyright © 2024, Marcos Robles.</copyright>
    <lastBuildDate>Tue, 08 Apr 2025 21:10:27 +0100</lastBuildDate>
    <atom:link href="https://roblesdev.com/blog/llm/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>LLM caretaker</title>
      <link>https://roblesdev.com/llm-caretaker/</link>
      <pubDate>Tue, 08 Apr 2025 21:10:27 +0100</pubDate>
      <guid>https://roblesdev.com/llm-caretaker/</guid>
      <description>&lt;p&gt;A common practice in the last year has been using LLMs to write code. For this purpose, multiple ways to feed the data to the moodel have been developed. Probably the most common one is to just copy and paste exactly what is failing or what you need, but this is missing a lot of information. A more complete way to do this is to feed the whole code, but even doing so is missing some important information. A common way to feed the information in a comfortable way is to use applications like Cursor or adaptations of VScode, but again, essential information is missing.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
