<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel><title>hotic's blog</title><link>https://hotic.cc/en/</link><description>hotic’s personal blog: tech, design, and stray thoughts.</description><language>en</language><lastBuildDate>Thu, 18 Jun 2026 00:00:00 GMT</lastBuildDate><item><title>Why Inference Speed Is the Next Battleground for Coding Agents</title><link>https://hotic.cc/en/posts/smart-is-cheap/</link><guid isPermaLink="true">https://hotic.cc/en/posts/smart-is-cheap/</guid><pubDate>Thu, 18 Jun 2026 00:00:00 GMT</pubDate><category>Tech</category><description>When we talk to a model, the wait before the first token is prefill; streaming tokens out one by one after that is decode.</description></item></channel></rss>
