<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Jev on Subin S V</title><link>https://blog.devsv.in/tags/jev/</link><description>Recent content in Jev on Subin S V</description><generator>Hugo -- gohugo.io</generator><language>en-US</language><copyright>Subin</copyright><lastBuildDate>Fri, 25 Sep 2026 10:00:00 +0530</lastBuildDate><atom:link href="https://blog.devsv.in/tags/jev/index.xml" rel="self" type="application/rss+xml"/><item><title>Jev vs LLMs, Thinking Fast and Slow</title><link>https://blog.devsv.in/posts/jev_vs_llms/</link><pubDate>Fri, 25 Sep 2026 10:00:00 +0530</pubDate><guid>https://blog.devsv.in/posts/jev_vs_llms/</guid><description>
Quick, what's 2 + 2? Now, what's 17 × 24?
Most of the small checks an AI agent makes are 2 + 2 questions, yet we send every one of them to a big LLM. This post looks at Jev, a "System One" model inspired by Kahneman's *Thinking, Fast and Slow*, and where it fits next to LLMs.</description></item></channel></rss>