<?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>Sensitive on Tenu Tech Brief</title>
    <link>https://cluster-site.onrender.com/tags/sensitive/</link>
    <description>Recent content in Sensitive on Tenu Tech Brief</description>
    <generator>Hugo -- 0.146.0</generator>
    <language>en-us</language>
    <lastBuildDate>Thu, 26 Feb 2026 06:03:06 +0000</lastBuildDate>
    <atom:link href="https://cluster-site.onrender.com/tags/sensitive/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Beyond Refusal: Probing the Limits of Agentic Self-Correction for Semantic Sensitive Information</title>
      <link>https://cluster-site.onrender.com/posts/beyond-refusal-probing-the-limits-of-agentic-self-correction-for-semantic-sensitive-information/</link>
      <pubDate>Thu, 26 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/beyond-refusal-probing-the-limits-of-agentic-self-correction-for-semantic-sensitive-information/</guid>
      <description>• Computer Science &amp;gt; Artificial Intelligence [Submitted on 25 Feb 2026] Title:Beyond Refusal: Probing the Limits of Agentic Self-Correction for Semantic Sensitive Information View</description>
    </item>
    <item>
      <title>State censorship shapes how Chinese chatbots respond to sensitive political topics, study suggests</title>
      <link>https://cluster-site.onrender.com/posts/state-censorship-shapes-how-chinese-chatbots-respond-to-sensitive-political-topics-study-suggests/</link>
      <pubDate>Tue, 17 Feb 2026 18:12:17 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/state-censorship-shapes-how-chinese-chatbots-respond-to-sensitive-political-topics-study-suggests/</guid>
      <description>• Chinese chatbots may be censored by the state, according to a study published in PNAS Nexus. • China has a robust program of censorship and all China-originating LLMs must be app</description>
    </item>
  </channel>
</rss>
