<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Anthropic on PIGSTY</title><link>https://pigsty.io/tags/anthropic/</link><description>Recent content in Anthropic on PIGSTY</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 04 May 2026 18:14:31 +0800</lastBuildDate><atom:link href="https://pigsty.io/tags/anthropic/index.xml" rel="self" type="application/rss+xml"/><item><title>LLMs Have Emotions: Claude's Internals Reveal Steerable Emotion Vectors</title><link>https://pigsty.io/blog/ai/ai-emotion/</link><pubDate>Sat, 04 Apr 2026 00:00:00 +0000</pubDate><guid>https://pigsty.io/blog/ai/ai-emotion/</guid><description>&lt;p&gt;&lt;a href="https://vonng.com/en/ai/ai-emotion/"&gt;&lt;img src="https://pigsty.io/img/hero/ai/ai-emotion.webp" alt="featured"&gt;&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;Anthropic&amp;rsquo;s new research gives us the first direct look at causally steerable emotion vectors inside a large language model. That should change how we think about AI. &lt;a href="https://vonng.com/en/ai/ai-emotion/"&gt;&lt;strong&gt;Read more&lt;/strong&gt;&lt;/a&gt;&lt;/p&gt;</description></item></channel></rss>