<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Preparedness Framework on GPT资讯  --  知识铺</title>
    <link>https://index.zshipu.com/gpt/tags/Preparedness-Framework/</link>
    <description>Recent content in Preparedness Framework on GPT资讯  --  知识铺</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <lastBuildDate>Tue, 01 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://index.zshipu.com/gpt/tags/Preparedness-Framework/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Astra 首次达到 OpenAI Critical 网络安全能力阈值</title>
      <link>https://index.zshipu.com/gpt/post/20260901/Astra-%E9%A6%96%E6%AC%A1%E8%BE%BE%E5%88%B0-OpenAI-Critical-%E7%BD%91%E7%BB%9C%E5%AE%89%E5%85%A8%E8%83%BD%E5%8A%9B%E9%98%88%E5%80%BC/</link>
      <pubDate>Tue, 01 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://index.zshipu.com/gpt/post/20260901/Astra-%E9%A6%96%E6%AC%A1%E8%BE%BE%E5%88%B0-OpenAI-Critical-%E7%BD%91%E7%BB%9C%E5%AE%89%E5%85%A8%E8%83%BD%E5%8A%9B%E9%98%88%E5%80%BC/</guid>
      <description>Astra 首次满足 Critical 网络安全能力阈值 Astra 是 OpenAI 首个达到 Preparedness Framework Critical 网络安全能力阈值的模型。这一事实直接表明 OpenAI 在网络安全相关的前沿能力上已经跨越了预设的关键节点。 Preparedness Framework 将模型能力分为不同等级，Critical 代表其中最高的风险级别，一旦模型在网络安全任务上表现出达到该级别的表现，就意味着它具备了可能被</description>
    </item>
  </channel>
</rss>
