<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>#1MTokens on Home</title>
    <link>https://yakinin.com/en/tags/%231mtokens/</link>
    <description>Recent content in #1MTokens on Home</description>
    <generator>Hugo -- 0.148.2</generator>
    <language>en</language>
    <lastBuildDate>Wed, 13 Aug 2025 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://yakinin.com/en/tags/%231mtokens/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Claude Sonnet 4&#39;s 1M Token Window: A Practical Take for Builders</title>
      <link>https://yakinin.com/en/posts/20250813-claude-sonnet-4-1m-context/</link>
      <pubDate>Wed, 13 Aug 2025 00:00:00 +0000</pubDate>
      <guid>https://yakinin.com/en/posts/20250813-claude-sonnet-4-1m-context/</guid>
      <description>&lt;p&gt;Anthropic just announced a 5x context window increase for Claude Sonnet 4, pushing it to 1 million tokens. While big numbers in AI are common, this move has tangible, practical implications for those of us building complex systems.&lt;/p&gt;
&lt;p&gt;From my perspective, this isn&amp;rsquo;t just a quantitative leap; it&amp;rsquo;s a qualitative one that unlocks a new class of problems we can solve.&lt;/p&gt;
&lt;h3 id=&#34;moving-from-file-analysis-to-system-level-understanding&#34;&gt;Moving from File Analysis to System-Level Understanding&lt;/h3&gt;
&lt;p&gt;The ability to load an entire codebase—over 75,000 lines with source files, tests, and docs—into a single prompt is a significant shift. Previously, AI code analysis was often limited to individual files or small modules. We could check for errors or refactor a specific function, but the AI lacked a holistic view.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
