<?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/"
     xmlns:dc="http://purl.org/dc/elements/1.1/"
     xmlns:media="http://search.yahoo.com/mrss/">
  <channel>
    <title>AI on 熊鑫伟（cubxxw）的简体中文博客 🇨🇳</title>
    <link>https://cubxxw.com/zh/tags/ai/</link>
    <description>AI Builder、开源贡献者、数字游民的技术博客：Kubernetes、Go、AI 开源项目与成长思考。</description>
    <image>
      <title>熊鑫伟（cubxxw）的简体中文博客 🇨🇳</title>
      <url>https://cubxxw.com/assets/og-image.png</url>
      <link>https://cubxxw.com/</link>
    </image>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-cn</language>
    <lastBuildDate>Mon, 29 Jun 2026 09:30:00 +0800</lastBuildDate>
    <atom:link href="https://cubxxw.com/zh/tags/ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>2026年3月思考笔记</title>
      <link>https://cubxxw.com/zh/growth/posts/2026-03-thought-notes/</link>
      <pubDate>Tue, 31 Mar 2026 23:59:59 +0800</pubDate>
      <atom:updated>Tue, 07 Jul 2026 13:05:29 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/growth/posts/2026-03-thought-notes/</guid>
      <description>2026 年 3 月思考笔记，本月共 468 条，跨越 31 天。涵盖旅行见闻（柬埔寨暹粒、吴哥窟、金边历史）、AI Agent 架构与多智能体系统设计、高棉文明的工程美学、自我叙事与认知探索。 核心话题：格物/ai (53 条)、格物/柬埔寨 (38 条)、格物/吴哥窟 (23 条)、格物/印度教 (15 条)、观我 (14 条)、格物/越南 (11 条)。
</description>
      <category domain="category">Growth</category>
      <category domain="tag">Blog</category>
      <category domain="tag">Monthly Notes</category>
      <category domain="tag">Personal Growth</category>
      <category domain="tag">Travel</category>
      <category domain="tag">Self-Discovery</category>
      <category domain="tag">AI</category>
    </item>
    <item>
      <title>拆解 open-lovable：一个不靠 Agent 框架、直接驯服裸 API 的应用生成器</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/dissecting-open-lovable/</link>
      <pubDate>Mon, 29 Jun 2026 09:30:00 +0800</pubDate>
      <atom:updated>Mon, 29 Jun 2026 23:33:51 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/dissecting-open-lovable/</guid>
      <description>把 firecrawl/open-lovable（27k★，输入一个网址几秒重建成 React 应用）从产品到代码彻底拆开。它最有意思的地方不是「能生成代码」，而是它不用任何 Agent 框架、不用 Claude Agent SDK、不用原生 tool-calling，而是在裸 LLM API 之上手搓了一整套 harness：文本 DSL 协议、流式正则解析、截断检测与补全、手工上下文编排，再配一套可切换的云端沙箱（E2B / Vercel Sandbox）。这是一份「直接驯服原始 API」的工程范本拆解。
</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">LLM</category>
      <category domain="tag">Architecture</category>
      <category domain="tag">Sandbox</category>
      <category domain="tag">Harness</category>
    </item>
    <item>
      <title>超级个体的栈：2026 年 AI 原生 Solo Builder 的产品方向与运营全图</title>
      <link>https://cubxxw.com/zh/growth/posts/super-individual-ai-product-and-solo-builder-stack/</link>
      <pubDate>Wed, 24 Jun 2026 14:55:00 +0800</pubDate>
      <atom:updated>Wed, 24 Jun 2026 15:27:30 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/growth/posts/super-individual-ai-product-and-solo-builder-stack/</guid>
      <description>当模型层趋于商品化、企业 AI 项目 40% 注定被取消，超级个体反而第一次拥有了切入 4.6 万亿美元服务市场的全套原语。这篇文章把 2025-2026 年最前沿的方法论拼成一张可执行的全景图：从思想内核、6 个产品方向、5 大运营栈，到 Soul Core 与 Harness Engineering 的工程支撑，再到 12 个月的行动路线图。
</description>
      <category domain="category">Growth</category>
      <category domain="tag">Super Individual</category>
      <category domain="tag">Solo Builder</category>
      <category domain="tag">Indie Hacker</category>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Harness Engineering</category>
      <category domain="tag">MCP</category>
      <category domain="tag">Product Strategy</category>
      <category domain="tag">Personal Growth</category>
      <enclosure url="https://cubxxw.com/images/posts/2026/super-individual/cover.jpg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/posts/2026/super-individual/cover.jpg" medium="image"><media:description>超级个体的栈：AI 原生 Solo Builder 的产品方向与运营全图</media:description></media:content>
    </item>
    <item>
      <title>从零设计一个生产级 AI Agent 系统：Relay 求职 Agent 的架构全解</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/relay-agent-architecture-design/</link>
      <pubDate>Wed, 24 Jun 2026 10:00:00 +0800</pubDate>
      <atom:updated>Wed, 24 Jun 2026 14:18:19 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/relay-agent-architecture-design/</guid>
      <description>这篇文章以 Relay 开源求职 Agent 项目为案例，完整拆解一个生产级多 Agent 系统从架构设计到落地的每一个关键决策：为什么把单 Agent 拆成 5 个、如何用 LangGraph 实现 HITL 检查点、三层 LLM 路由如何精算成本、反虚构防卫如何运行时验证、混合后端（Hono/Bun + FastAPI/Python）如何优雅解耦。无论你是在搭建第一个 Agent PoC 还是推进生产落地，这里都有可以拿走的设计模式。
</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">LangGraph</category>
      <category domain="tag">LLM</category>
      <category domain="tag">Architecture</category>
      <category domain="tag">TypeScript</category>
      <category domain="tag">Python</category>
      <enclosure url="https://cubxxw.com/images/blog/relay-agent-architecture.webp" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/blog/relay-agent-architecture.webp" medium="image"><media:description>展示 Relay 求职 Agent 系统五层架构的技术图解：用户层、API 编排层、Agent 执行层、共享服务层、数据与集成层</media:description></media:content>
    </item>
    <item>
      <title>Context 不是 Prompt：为什么「上下文工程」正在成为 AI 的新地基</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/context-engineering-the-new-foundation/</link>
      <pubDate>Mon, 22 Jun 2026 03:30:00 +0800</pubDate>
      <atom:updated>Tue, 23 Jun 2026 15:16:04 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/context-engineering-the-new-foundation/</guid>
      <description>上下文工程正在从一句口号变成一门独立学科。这篇文章从 Anthropic、Karpathy、LangChain、Sourcegraph 与 Manus 的一线实践出发，拆解上下文工程与提示词工程的本质区别、两套四支柱分类法、以及装配检索压缩淘汰这些具体设计模式，再回到我自己的判断：上下文不是工具的参数，而是 AI 与你之间那条共享的世界线。
</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">Context Engineering</category>
      <category domain="tag">AI</category>
      <category domain="tag">LLM</category>
      <category domain="tag">Agent</category>
      <category domain="tag">MCP</category>
      <enclosure url="https://cubxxw.com/images/blog/context-engineering-desk.webp" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/blog/context-engineering-desk.webp" medium="image"><media:description>书桌上的笔记本电脑显示「Context 不是 Prompt」文章与核心要点面板，旁边摊开的笔记写着 Context Engineering 的四支柱与 Worldline</media:description></media:content>
    </item>
    <item>
      <title>Agent Engineering 全景地图：那 98.4% 的工程量到底在哪里</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/agent-engineering-the-98-percent-harness/</link>
      <pubDate>Wed, 17 Jun 2026 09:30:00 +0800</pubDate>
      <atom:updated>Wed, 24 Jun 2026 14:18:30 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/agent-engineering-the-98-percent-harness/</guid>
      <description>一篇把 Agent Engineering 当成一门学科来拆的全景地图。从 Claude Code 那个广为流传的「1.6% 是 AI 决策、98.4% 是基础设施」说起，沿着八大支柱——编排、上下文、记忆、工具、可靠性、评估、成本、治理——逐根讲清每一块填补的缺口、最小实现与失效边界，并融合 Anthropic、OpenAI、Cognition、Manus、Temporal 在 2025 至 2026 年的一线工程实践，最后落到一句话：模型是买来的，harness 是你造的，工程杠杆全在那 98.4%。
</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">LLM</category>
      <category domain="tag">Context Engineering</category>
      <category domain="tag">Architecture</category>
      <category domain="tag">MCP</category>
      <enclosure url="https://cubxxw.com/images/blog/agent-engineering-harness.webp" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/blog/agent-engineering-harness.webp" medium="image"><media:description>一张技术示意图，中心是一个小小的 agent loop，外面一圈一圈包裹着编排、上下文、记忆、工具、可靠性、评估、成本、治理八根支柱</media:description></media:content>
    </item>
    <item>
      <title>Agent 的自我：从洛克到 OpenClaw</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/agent-identity-from-locke-to-openclaw/</link>
      <pubDate>Sun, 05 Apr 2026 20:00:00 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/agent-identity-from-locke-to-openclaw/</guid>
      <description>AI Agent 的失忆不是功能缺陷，是信任账户的根本缺失。本文从洛克 1689 年的身份理论出发，逐层拆解 2026 年 Agent 身份连续性的完整工程栈：文件即身份（SOUL.md 范式）、Harness 作为环境条件、记忆的四层结构与 Gene Capsule 协议、多智能体拓扑中的自我定位，以及评测作为身份验证的终极难题。 适合正在构建或设计 AI Agent 系统的从业者，以及对 AI 自主性边界有深度思考需求的研究者。
</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">AI</category>
      <category domain="tag">Open Source</category>
      <category domain="tag">Monthly Notes</category>
      <enclosure url="https://cubxxw.com/images/agent-identity/01-locke-spec.svg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/agent-identity/01-locke-spec.svg" medium="image"><media:description>Locke Identity Spec — Agent Identity Engineering Stack</media:description></media:content>
    </item>
    <item>
      <title>在不被需要的时代，如何维持自我的重量</title>
      <link>https://cubxxw.com/zh/growth/posts/weight-of-self-in-ai-age/</link>
      <pubDate>Sat, 04 Apr 2026 22:00:00 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/growth/posts/weight-of-self-in-ai-age/</guid>
      <description>当 AI 能替代我们思考、执行、甚至创作时，&#34;我&#34;的重量从哪里来？这不是一篇关于职业危机的文章，是一个人试图搞清楚自己为什么还在这里的轨迹。
</description>
      <category domain="category">Growth</category>
      <category domain="tag">AI</category>
      <category domain="tag">Personal Growth</category>
      <category domain="tag">Self-Discovery</category>
      <enclosure url="https://cubxxw.com/images/posts/2026/ai-self-identity/mountain-path.jpg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/posts/2026/ai-self-identity/mountain-path.jpg" medium="image"><media:description>在不被需要的时代，如何维持自我的重量</media:description></media:content>
    </item>
    <item>
      <title>Mem0 开源项目：AI记忆层的技术分析与实践</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/mem0/</link>
      <pubDate>Fri, 09 May 2025 21:33:46 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/mem0/</guid>
      <description>本文深入分析Mem0开源项目的技术架构、核心功能和应用场景，探讨如何为AI系统构建智能记忆层，实现个性化交互体验。
</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Open Source</category>
    </item>
    <item>
      <title>微软UFO项目深度解析：设计、实现、原理与架构</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/ufo/</link>
      <pubDate>Fri, 09 May 2025 21:30:15 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/ufo/</guid>
      <description>本文深入解析微软UFO项目的核心设计、技术实现与系统架构，涵盖其多智能体协作、混合GUI/API操作、持续学习等创新特性，帮助开发者全面理解这一前沿的桌面自动化平台。
</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Automation</category>
      <category domain="tag">Windows 开发</category>
      <category domain="tag">微软技术</category>
    </item>
    <item>
      <title>Ai Recommend 技术、实践和深度学习</title>
      <link>https://cubxxw.com/zh/projects/ai-recommend/</link>
      <pubDate>Wed, 23 Apr 2025 10:39:05 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/projects/ai-recommend/</guid>
      <description>本项目是一个持续的过程，以日拱一卒的态度去学习 AI 开源项目，并且记录。
</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Project Learning</category>
    </item>
    <item>
      <title>Google NotebookLM 的 RAG 深度调研思考</title>
      <link>https://cubxxw.com/zh/projects/notebooklm/</link>
      <pubDate>Mon, 21 Apr 2025 22:59:57 +0800</pubDate>
      <atom:updated>Tue, 23 Jun 2026 15:16:04 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/projects/notebooklm/</guid>
      <description>Google NotebookLM 的 RAG 实现机制深度调研：向量检索、引用溯源与知识图谱构建，探讨 AI 笔记工具的技术本质。</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Project Learning</category>
    </item>
    <item>
      <title>AI 时代初创企业的测试驱动开发（TDD）实践方案</title>
      <link>https://cubxxw.com/zh/projects/tdd/</link>
      <pubDate>Mon, 21 Apr 2025 15:52:34 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/projects/tdd/</guid>
      <description>本项目是一个持续的过程，以日拱一卒的态度去学习 AI 开源项目，并且记录。
</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Project Learning</category>
    </item>
    <item>
      <title>MarkItDown 开源项目深度学习</title>
      <link>https://cubxxw.com/zh/projects/markitdown/</link>
      <pubDate>Mon, 21 Apr 2025 15:41:21 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/projects/markitdown/</guid>
      <description>深度分析 Microsoft MarkItDown：将 PDF、Word、PowerPoint、Excel、图像、音频等多种格式转换为 Markdown 的开源 Python 工具。涵盖架构原理、安装使用、实操教程、LLM 集成、安全考量及与同类工具的对比，帮助开发者快速上手并融入 AI 工作流。
</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Open Source</category>
      <category domain="tag">Python</category>
      <category domain="tag">LLM</category>
      <category domain="tag">RAG</category>
    </item>
    <item>
      <title>LangGraph 深度解析：设计、架构、原理与应用</title>
      <link>https://cubxxw.com/zh/projects/langgraph/</link>
      <pubDate>Sat, 19 Apr 2025 15:19:20 +0800</pubDate>
      <atom:updated>Tue, 23 Jun 2026 15:16:04 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/projects/langgraph/</guid>
      <description>LangGraph 图状态机框架深度解析：设计架构、节点路由、多 Agent 工作流构建，解读有状态 AI Agent 的核心实现机制。</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Project Learning</category>
    </item>
    <item>
      <title>LangChain 开源项目深度学习</title>
      <link>https://cubxxw.com/zh/projects/langchain/</link>
      <pubDate>Wed, 16 Apr 2025 17:36:46 +0800</pubDate>
      <atom:updated>Tue, 07 Jul 2026 14:23:03 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/projects/langchain/</guid>
      <description>LangChain 开源框架深度学习：从 LCEL、链式调用、RAG 管道到 LangChain 1.0 的 create_agent 与中间件（middleware）体系，配套上手案例、前沿进展与面试高频题，持续记录学习过程与关键实践。</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Project Learning</category>
      <category domain="tag">LangChain</category>
      <category domain="tag">Agent</category>
      <category domain="tag">RAG</category>
    </item>
    <item>
      <title>Ai Gateway 开源项目深度学习</title>
      <link>https://cubxxw.com/zh/projects/ai-gateway/</link>
      <pubDate>Wed, 16 Apr 2025 17:36:12 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/projects/ai-gateway/</guid>
      <description>本项目是一个持续的过程，以日拱一卒的态度去学习 AI 开源项目，并且记录。
</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Project Learning</category>
    </item>
    <item>
      <title>独立开发者必备技能及现代工具 &amp; 分别的上手指导</title>
      <link>https://cubxxw.com/zh/projects/independent-developer/</link>
      <pubDate>Tue, 15 Apr 2025 20:53:12 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/projects/independent-developer/</guid>
      <description>介绍一些好用的工具，以及基本的上手的步骤，学习，note
</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Project Learning</category>
    </item>
    <item>
      <title>Gpt Researcher 开源项目深度学习</title>
      <link>https://cubxxw.com/zh/projects/gpt-researcher/</link>
      <pubDate>Mon, 14 Apr 2025 16:17:27 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/projects/gpt-researcher/</guid>
      <description>本项目是一个持续的过程，以日拱一卒的态度去学习 AI 开源项目，并且记录。
</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Project Learning</category>
    </item>
    <item>
      <title>Jina 开源项目深度学习</title>
      <link>https://cubxxw.com/zh/projects/jina/</link>
      <pubDate>Sat, 12 Apr 2025 13:01:59 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/projects/jina/</guid>
      <description>AI开源项目学习笔记</description>
      <category domain="category">Projects</category>
      <category domain="tag">AI</category>
      <category domain="tag">Project Learning</category>
    </item>
    <item>
      <title>利用 LangChain 框架的语言模型应用：开发者指南</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/harnessing-language-model-applications-with-langchain-a-developer-is-guide/</link>
      <pubDate>Wed, 22 May 2024 21:37:34 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/harnessing-language-model-applications-with-langchain-a-developer-is-guide/</guid>
      <description>本指南深入探讨了使用 LangChain 框架集成和应用语言模型的过程，专为希望简化复杂实现的开发者量身定制。</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">AI 开发 (AI Development)</category>
      <category domain="tag">语言模型 (Language Models)</category>
      <category domain="tag">LangChain</category>
      <category domain="tag">AI 框架 (AI Frameworks)</category>
      <category domain="tag">AI</category>
      <category domain="tag">API 集成 (API Integration)</category>
      <category domain="tag">自然语言处理 (NLP)</category>
      <category domain="tag">软件开发 (Software Development)</category>
      <category domain="tag">编程 (Programming)</category>
      <category domain="tag">Automation</category>
      <category domain="tag">AI 工具 (AI Tools)</category>
      <category domain="tag">OpenAI</category>
      <category domain="tag">深度学习 (Deep Learning)</category>
    </item>
    <item>
      <title>探索大型语言模型（llm）：人工智能在理解与生成人类语言方面的先锋</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/exploring-large-language-models-llms-pioneering-ai-understanding-generation-human-language/</link>
      <pubDate>Wed, 15 May 2024 20:12:29 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/exploring-large-language-models-llms-pioneering-ai-understanding-generation-human-language/</guid>
      <description>本文系统介绍大型语言模型（LLM）的核心概念、发展历程与涌现能力。从 GPT、PaLM 等数百亿参数模型出发， 解释它们如何在海量文本上训练以理解和生成人类语言，以及为何参数规模的提升会带来小模型不具备的复杂任务处理能力。
</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">LLM</category>
      <category domain="tag">AI</category>
      <category domain="tag">Deep Learning</category>
      <category domain="tag">Machine Learning</category>
    </item>
    <item>
      <title>Sora Ease 指南：开发者掌握 Sora AI 的全面指南</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/sora-ease-guide-mastering-sora-ai-for-developers/</link>
      <pubDate>Thu, 14 Mar 2024 08:44:13 +0800</pubDate>
      <atom:updated>Tue, 07 Jul 2026 15:43:20 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/sora-ease-guide-mastering-sora-ai-for-developers/</guid>
      <description>本综合指南介绍了 Sora AI，为开发者提供了一个易于访问、自动化且迅速的途径来挖掘其潜力。深入不同的场景，掌握指挥 Sora 的技巧，并探索这个 AI 模型的多面应用，该模型被训练用以理解和模拟运动中的物理世界。无论你是寻求最新的 Sora 新闻、开发项目还是开源贡献，本文都是你进入 Sora AI 开发广阔世界的入口。</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">Blog</category>
      <category domain="tag">Sora</category>
      <category domain="tag">AI</category>
      <category domain="tag">Developer Guide</category>
    </item>
    <item>
      <title>Sora 技术讨论以及普通人和开发者如何利用 Sora 改变世界</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/exploring-sora-technology-for-enthusiasts-and-developers/</link>
      <pubDate>Sat, 24 Feb 2024 13:30:15 +0800</pubDate>
      <atom:updated>Tue, 07 Jul 2026 15:43:20 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/exploring-sora-technology-for-enthusiasts-and-developers/</guid>
      <description>深入Sora技术的世界，这是一个开创性的AI驱动视频生成平台。本文旨在为技术爱好者和开发者提供一个了解和利用Sora潜能的入口。探索如何轻松利用Sora创造令人惊叹的AI生成视频，并加入一个正在改变数字景观的创新者社区。</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">Blog</category>
      <category domain="tag">AI</category>
      <category domain="tag">Technology</category>
      <category domain="tag">Development</category>
      <category domain="tag">Git</category>
    </item>
    <item>
      <title>向量数据库的学习</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/vector-database-learning/</link>
      <pubDate>Sat, 20 Jan 2024 12:57:15 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/vector-database-learning/</guid>
      <description>本文介绍了向量数据库的基础知识，使用场景，以及它在现代大数据和人工智能领域中的应用。</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">Blog</category>
      <category domain="tag">AI</category>
      <category domain="tag">Database</category>
      <enclosure url="https://cubxxw.com/images/blog/vector-database.png" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/blog/vector-database.png" medium="image"></media:content>
    </item>
    <item>
      <title>AI元年: 2024年的新兴挑战与趋势</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/emerging-challenges-and-trends-in-2024/</link>
      <pubDate>Sun, 14 Jan 2024 22:52:24 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/emerging-challenges-and-trends-in-2024/</guid>
      <description>探索2024年技术和开发领域的最新趋势和挑战。
</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">Blog</category>
      <category domain="tag">AI</category>
      <category domain="tag">Technology</category>
    </item>
    <item>
      <title>如何安装和使用自主人工智能工具Auto-GPT</title>
      <link>https://cubxxw.com/zh/ai-technology/posts/use-auto-gpt/</link>
      <pubDate>Sun, 16 Jul 2023 16:28:31 +0800</pubDate>
      <atom:updated>Mon, 22 Jun 2026 18:48:25 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-technology/posts/use-auto-gpt/</guid>
      <description>本文详细解释了如何安装和配置 Auto-GPT，一个先进的自主人工智能工具，以及如何有效地利用它来改善业务流程和用户体验。</description>
      <category domain="category">AI &amp; Technology</category>
      <category domain="tag">Blog</category>
      <category domain="tag">AI</category>
      <category domain="tag">Auto-GPT</category>
    </item>
  </channel>
</rss>
