<?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>模型选择 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%A8%A1%E5%9E%8B%E9%80%89%E6%8B%A9/</link><description>Recent content in 模型选择 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>Thu, 02 Jul 2026 11:19:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%A8%A1%E5%9E%8B%E9%80%89%E6%8B%A9/index.xml" rel="self" type="application/rss+xml"/><item><title>AI系统A/B测试实践：数据驱动的模型选择</title><link>https://guijiagi.com/posts/a-b-testing-ai-system/</link><pubDate>Thu, 02 Jul 2026 11:19:00 +0800</pubDate><guid>https://guijiagi.com/posts/a-b-testing-ai-system/</guid><description>2026年AI系统A/B测试方法论，科学比较不同模型和提示的效果</description></item><item><title>Agent成本优化实战：从Token到基础设施的全面降本</title><link>https://guijiagi.com/posts/agent-cost-optimization-token-to-infra/</link><pubDate>Tue, 30 Jun 2026 11:10:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-cost-optimization-token-to-infra/</guid><description>从Token消耗、模型选择、缓存策略到基础设施优化的Agent系统全链路成本优化实战指南</description></item><item><title>Qwen3 系列模型选择指南：从 0.6B 到 235B</title><link>https://guijiagi.com/posts/qwen3-model-selection/</link><pubDate>Wed, 24 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/qwen3-model-selection/</guid><description>全面解析 Qwen3 系列模型的架构、规格、性能与部署策略，帮助开发者选择最适合的通义千问模型。</description></item></channel></rss>