<?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>Model-Selection on Girish Shekhar</title><link>https://blog.girishshekhar.com/tags/model-selection/</link><description>Recent content in Model-Selection on Girish Shekhar</description><generator>Hugo -- 0.163.3</generator><language>en-us</language><lastBuildDate>Wed, 29 Mar 2023 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.girishshekhar.com/tags/model-selection/index.xml" rel="self" type="application/rss+xml"/><item><title>The LLM Landscape: Models, Capabilities, and Tradeoffs</title><link>https://blog.girishshekhar.com/posts/llms-and-how-our-work-is-changing/3-the-llm-landscape/</link><pubDate>Wed, 29 Mar 2023 00:00:00 +0000</pubDate><guid>https://blog.girishshekhar.com/posts/llms-and-how-our-work-is-changing/3-the-llm-landscape/</guid><description>Once you understand how LLMs work, the next real question is model choice. This post explains how to reason about LLM tradeoffs — capability, cost, controllability, and domain fit — without relying on benchmarks alone.</description></item></channel></rss>