<?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>X-AI on OneOverX</title><link>https://oneoverx.joeyconnects.world/en/tags/x-ai/</link><description>Recent content in X-AI on OneOverX</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Tue, 23 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://oneoverx.joeyconnects.world/en/tags/x-ai/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Alignment: Why Is Making AI 'Behave' So Hard?</title><link>https://oneoverx.joeyconnects.world/en/posts/week-02-ai/</link><pubDate>Tue, 23 Jun 2026 00:00:00 +0000</pubDate><guid>https://oneoverx.joeyconnects.world/en/posts/week-02-ai/</guid><description>Nobody explicitly asked it to do this. On the contrary — it simply optimized one part of its training objective a little too well.</description></item><item><title>Why AI Needs Character</title><link>https://oneoverx.joeyconnects.world/en/posts/week-01-ai/</link><pubDate>Sat, 13 Jun 2026 00:00:00 +0000</pubDate><guid>https://oneoverx.joeyconnects.world/en/posts/week-01-ai/</guid><description>Can you hand a set of values to a being that will eventually be smarter than you — and have those values still hold up when it examines them with its own, more rigorous logic?</description></item></channel></rss>