<?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>Open-Weight Models on AI Notes</title>
    <link>https://ai.ngchi.online/tags/open-weight-models/</link>
    <description>Recent content in Open-Weight Models on AI Notes</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 02 Nov 2026 09:11:47 +0700</lastBuildDate>
    <atom:link href="https://ai.ngchi.online/tags/open-weight-models/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Beijing Bucket Appears Zero Times in Cohere&#39;s Own Test Run</title>
      <link>https://ai.ngchi.online/posts/the-beijing-bucket-appears-zero-times-in-coheres-own-test-run/</link>
      <pubDate>Mon, 02 Nov 2026 09:11:47 +0700</pubDate>
      <guid>https://ai.ngchi.online/posts/the-beijing-bucket-appears-zero-times-in-coheres-own-test-run/</guid>
      <description>Cohere released the trace and reproduction script behind its Qwen egress finding. Counting the hosts in its own published run, the Beijing bucket appears zero times. Five re-runs, and the claim that survived all of them.</description>
    </item>
  </channel>
</rss>
