<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>llm on philliant</title><link>https://philliant.com/tags/llm/</link><description>Recent content in llm on philliant</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 philip mathew hern</copyright><lastBuildDate>Fri, 20 Mar 2026 10:45:00 -0700</lastBuildDate><atom:link href="https://philliant.com/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>deep dive: the ai models i use</title><link>https://philliant.com/posts/20260320-deep-dive-ai-models-i-use/</link><pubDate>Fri, 20 Mar 2026 10:45:00 -0700</pubDate><guid>https://philliant.com/posts/20260320-deep-dive-ai-models-i-use/</guid><description>i walk through composer-2, gpt-5.3-codex-xhigh, claude 4.6 opus, gemini 3.1 pro, grok-4-20, and kimi-k2.5 with a comparison table plus longer notes on how i actually use each one.</description></item><item><title>from prototype to production: my early adopter view of ai</title><link>https://philliant.com/posts/20260318-from-prototype-to-production-ai/</link><pubDate>Wed, 18 Mar 2026 07:09:57 -0700</pubDate><guid>https://philliant.com/posts/20260318-from-prototype-to-production-ai/</guid><description>i have watched ai move from a prototype side assistant to an operational core system. this post shares that journey with time-stamped benchmark evidence and a practical view on where model usage is headed next.</description></item></channel></rss>