<?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>开源大模型 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%BC%80%E6%BA%90%E5%A4%A7%E6%A8%A1%E5%9E%8B/</link><description>Recent content in 开源大模型 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, 30 Jun 2026 10:45:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%BC%80%E6%BA%90%E5%A4%A7%E6%A8%A1%E5%9E%8B/index.xml" rel="self" type="application/rss+xml"/><item><title>Mistral Large 3评测：欧洲AI的代表</title><link>https://guijiagi.com/posts/mistral-large-3-evaluation/</link><pubDate>Tue, 30 Jun 2026 10:45:00 +0800</pubDate><guid>https://guijiagi.com/posts/mistral-large-3-evaluation/</guid><description>全面评测Mistral Large 3，分析这家欧洲AI公司的旗舰模型表现</description></item><item><title>Llama 4系列评测：Meta开源旗舰的表现</title><link>https://guijiagi.com/posts/llama-4-series-evaluation/</link><pubDate>Tue, 30 Jun 2026 10:40:00 +0800</pubDate><guid>https://guijiagi.com/posts/llama-4-series-evaluation/</guid><description>全面评测Llama 4系列模型，从405B到8B的开源旗舰表现分析</description></item></channel></rss>