<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Llm · rksh</title><link>https://rksh.me/tags/llm/</link><description>Posts in Llm</description><language>en-US</language><copyright>rksh.me</copyright><generator>Hugo 0.166.0</generator><lastBuildDate>Mon, 28 Sep 2026 07:50:00 +0530</lastBuildDate><atom:link href="https://rksh.me/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>What Happens When You Send a Prompt to an AI</title><link>https://rksh.me/blog/what-happens-when-you-send-a-prompt-to-an-ai/</link><pubDate>Mon, 28 Sep 2026 07:50:00 +0530</pubDate><author>contact@rksh.me (Rakesh Gautam)</author><guid>https://rksh.me/blog/what-happens-when-you-send-a-prompt-to-an-ai/</guid><description>&lt;p&gt;You type a question, press enter, and a second later an answer streams back. The experience feels like asking a person who happens to type very fast.&lt;/p&gt;&#10;&lt;p&gt;Underneath, it is a loop that guesses the next fragment of text and runs again, a few hundred times, with several stages of arithmetic between your sentence and the reply.&lt;/p&gt;&#10;&lt;h2 id="your-words-become-tokens"&gt;Your Words Become Tokens&lt;/h2&gt;&#10;&lt;p&gt;The model never sees your sentence as words. Before anything else, a tokenizer chops the text into pieces called tokens and swaps each piece for a number. Those numbers come from a fixed list, the vocabulary, which holds around 200,000 entries.&lt;/p&gt;</description></item></channel></rss>