<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Age of LLMs on Zenithia</title><link>/series/age-of-llms/</link><description>Recent content in Age of LLMs on Zenithia</description><generator>Hugo</generator><language>en-nz</language><lastBuildDate>Wed, 16 Sep 2026 14:22:54 +0300</lastBuildDate><atom:link href="/series/age-of-llms/index.xml" rel="self" type="application/rss+xml"/><item><title>Age of LLMs</title><link>/posts/age-of-llms/</link><pubDate>Wed, 16 Sep 2026 14:22:54 +0300</pubDate><guid>/posts/age-of-llms/</guid><description>&lt;p>Over the last few months I&amp;rsquo;ve dived head first into LLMs starting from running them locally understanding all the ins and outs of what that requires, to running them in data centers on serverless GPUs paid by usage, to finally joining the rest and paying a provider for a plan. I haven&amp;rsquo;t quite gotten into finetuning/post-training but I got pretty close that I can quickly set that up within a day provided good training datasets are already prepared.&lt;/p></description></item></channel></rss>