<?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>模型评测 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%A8%A1%E5%9E%8B%E8%AF%84%E6%B5%8B/</link><description>Recent content in 模型评测 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Tue, 07 Jul 2026 11:30:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%A8%A1%E5%9E%8B%E8%AF%84%E6%B5%8B/index.xml" rel="self" type="application/rss+xml"/><item><title>Claude Fable 5降智争议：AI安全护栏的度在哪里</title><link>https://guijiagi.com/posts/claude-fable5-degradation/</link><pubDate>Tue, 07 Jul 2026 11:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/claude-fable5-degradation/</guid><description>Anthropic重新上架Claude Fable 5后用户普遍反馈降智，安全护栏与模型能力的平衡成为焦点</description></item><item><title>GPT-5.5 深度评测：多模态推理的新标杆</title><link>https://guijiagi.com/posts/gpt-55-%E6%B7%B1%E5%BA%A6%E8%AF%84%E6%B5%8B-%E5%A4%9A%E6%A8%A1%E6%80%81%E6%8E%A8%E7%90%86%E7%9A%84%E6%96%B0%E6%A0%87%E6%9D%86/</link><pubDate>Sat, 27 Jun 2026 00:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/gpt-55-%E6%B7%B1%E5%BA%A6%E8%AF%84%E6%B5%8B-%E5%A4%9A%E6%A8%A1%E6%80%81%E6%8E%A8%E7%90%86%E7%9A%84%E6%96%B0%E6%A0%87%E6%9D%86/</guid><description>全面评测 GPT-5.5 的推理能力、多模态表现与 Agent 构建能力，对比 GPT-5 提升幅度，分析其在实际应用中的表现</description></item></channel></rss>