<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
        <title>Reasoning - Tag - Simi Studio</title>
        <link>/en/tags/reasoning/</link>
        <description>Reasoning - Tag - Simi Studio</description>
        <generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>simi@simi.studio (Simi)</managingEditor>
            <webMaster>simi@simi.studio (Simi)</webMaster><lastBuildDate>Fri, 20 Feb 2026 10:00:00 &#43;0800</lastBuildDate><atom:link href="/en/tags/reasoning/" rel="self" type="application/rss+xml" /><item>
    <title>LLM Extended Thinking: Engineering Practices for &#34;Think Longer&#34;</title>
    <link>/en/posts/extended-thinking-llm/</link>
    <pubDate>Fri, 20 Feb 2026 10:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/extended-thinking-llm/</guid>
    <description><![CDATA[Extended Thinking (thinking budget) is standard in 2026. But how to use it well, which scenarios are worth extra tokens—these are engineering problems.]]></description>
</item>
<item>
    <title>Gemini 3 Deep Think: 84.6% on ARC-AGI-2, 0.4% Shy of the AGI Signal Threshold</title>
    <link>/en/posts/gemini-3-deep-think-arc-agi/</link>
    <pubDate>Fri, 13 Feb 2026 10:00:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/gemini-3-deep-think-arc-agi/</guid>
    <description><![CDATA[February 13, 2026—Google releases Gemini 3 Deep Think mode, scoring 84.6% on ARC-AGI-2, just 0.4% below the ARC Prize "strong AGI signal" threshold of 85%.]]></description>
</item>
<item>
    <title>LLM Reasoning Models: What o1/o3/C4 Actually Solve</title>
    <link>/en/posts/llm-reasoning-models-deep-dive/</link>
    <pubDate>Thu, 18 Dec 2025 09:15:00 &#43;0800</pubDate>
    <author>simi@simi.studio (Simi)</author>
    <guid>/en/posts/llm-reasoning-models-deep-dive/</guid>
    <description><![CDATA[OpenAI o1, Claude 3.5 Sonnet, o3—reasoning models have been hot for a year. This article explains from an engineering perspective: what reasoning models are, how they differ from regular LLMs, and when to use them.]]></description>
</item>
</channel>
</rss>
