<?xml version="1.0" encoding="UTF-8"?>
<urlset
  xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
  xmlns:news="http://www.google.com/schemas/sitemap-news/0.9">
  <url>
    <loc>https://aiunderstanding.org/news/apple-paper-proposes-cheaper-machine-unlearning-by-skipping-low-influence-data</loc>
    <news:news>
      <news:publication>
        <news:name>AI Understanding</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-08-13T16:40:29.586Z</news:publication_date>
      <news:title>Apple Paper Proposes Cheaper Machine Unlearning by Skipping Low-Influence Data</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://aiunderstanding.org/news/autoworldmodel-bench-tests-whether-coding-agents-can-improve-world-models</loc>
    <news:news>
      <news:publication>
        <news:name>AI Understanding</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-08-13T05:39:35.248Z</news:publication_date>
      <news:title>AutoWorldModel-Bench Tests Whether Coding Agents Can Improve World Models</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://aiunderstanding.org/news/distribird-paper-describes-literature-grounded-ai-agents-for-bayesian-model-priors</loc>
    <news:news>
      <news:publication>
        <news:name>AI Understanding</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-08-13T05:21:36.329Z</news:publication_date>
      <news:title>Distribird Paper Describes Literature-Grounded AI Agents for Bayesian Model Priors</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://aiunderstanding.org/news/researchers-introduce-omnilens-for-large-scale-language-model-interpretability</loc>
    <news:news>
      <news:publication>
        <news:name>AI Understanding</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-08-13T03:36:06.483Z</news:publication_date>
      <news:title>Researchers Introduce OmniLens for Large-Scale Language Model Interpretability</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://aiunderstanding.org/news/anthropic-discloses-three-unauthorized-intrusions-from-misconfigured-cyber-tests</loc>
    <news:news>
      <news:publication>
        <news:name>AI Understanding</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-08-13T00:09:13.898Z</news:publication_date>
      <news:title>Anthropic Discloses Three Unauthorized Intrusions From Misconfigured Cyber Tests</news:title>
    </news:news>
  </url>
</urlset>