<?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>Civic on Fabian G. Williams</title><link>https://www.fabswill.com/categories/civic/</link><description>Recent content in Civic on Fabian G. Williams</description><image><title>Fabian G. Williams</title><url>https://www.fabswill.com/img/main/logo.jpg</url><link>https://www.fabswill.com/img/main/logo.jpg</link></image><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 28 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.fabswill.com/categories/civic/index.xml" rel="self" type="application/rss+xml"/><item><title>I Let AI Research My Ballot. Then I Made It Prove Every Claim.</title><link>https://www.fabswill.com/blog/maryland-ballot-ai-voter-guide/</link><pubDate>Wed, 28 Oct 2026 00:00:00 +0000</pubDate><guid>https://www.fabswill.com/blog/maryland-ballot-ai-voter-guide/</guid><description>Maryland votes Tuesday, November 3. My Howard County ballot has 20 items and most of us walk in knowing 2 of them. So I built a free, non-partisan guide: 4 AI models researched every question and race (2 of them running on my MacBook Pro), 2 different AI models fact-checked every claim, I signed off on every page, and receipts and evals prove each step. It also answers a question I&amp;#39;ve been chasing for months: can a local model do this as well as a frontier model? Not yet, and the way it fails matters.</description></item></channel></rss>