<?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>Development on 熊鑫伟（cubxxw）· 公开的实践与思想档案</title>
    <link>https://cubxxw.com/zh/tags/development/</link>
    <description>熊鑫伟的公开实践与思想档案，记录 AI 工作流、真实项目、工程方法、系统思维，以及关于个人成长、哲学与人生的长期思考。</description>
    <image>
      <title>熊鑫伟（cubxxw）· 公开的实践与思想档案</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>Fri, 07 Aug 2026 19:43:00 +0800</lastBuildDate>
    <atom:link href="https://cubxxw.com/zh/tags/development/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Agent 不是一种产品：十套系统如何重新分配控制权、状态、身份与副作用</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/agent-system-design-synthesis/</link>
      <pubDate>Fri, 07 Aug 2026 19:43:00 +0800</pubDate>
      <atom:updated>Fri, 07 Aug 2026 19:43:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/agent-system-design-synthesis/</guid>
      <description>基于十篇个案，以控制权、状态、执行身体、强制层和产品表面五个所有权问题，推导 bounded function、workflow、harness、event platform、gateway/computer 与 vertical organization 六种形态，并给出副作用宪法、五层停止协议和选型树。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Harness Engineering</category>
      <category domain="tag">System Design</category>
      <category domain="tag">Data Processing</category>
      <category domain="tag">Security</category>
      <category domain="tag">Development</category>
      <enclosure url="https://cubxxw.com/images/agent-system-series/11-synthesis/agent-system-constitutional-route.svg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/agent-system-series/11-synthesis/agent-system-constitutional-route.svg" medium="image"><media:description>Agent 系统设计的五个所有权问题、从意图到副作用与证据的控制权宪法之河，以及六种最小成立形态的决策图</media:description></media:content>
    </item>
    <item>
      <title>Conversation as Database：OpenHands 的无状态 Agent 与事件运行时</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/agent-system-design-openhands/</link>
      <pubDate>Fri, 07 Aug 2026 19:40:00 +0800</pubDate>
      <atom:updated>Fri, 07 Aug 2026 19:40:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/agent-system-design-openhands/</guid>
      <description>以 OpenHands SDK v1.41.0 为样本，沿事件链拆解无状态 step、Conversation 与 local/remote workspace。文章区分 event log、覆盖式 base state、派生 view 和外部世界，并以崩溃路径说明内部可回放为何仍不等于副作用恰好一次。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Harness Engineering</category>
      <category domain="tag">Data Processing</category>
      <category domain="tag">Monitoring</category>
      <category domain="tag">Security</category>
      <category domain="tag">Development</category>
      <enclosure url="https://cubxxw.com/images/agent-system-series/10-openhands/openhands-event-sourced-runtime.svg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/agent-system-series/10-openhands/openhands-event-sourced-runtime.svg" medium="image"><media:description>OpenHands V1 从无状态 Agent step、追加式 typed event log、base state、派生 view 到 local/remote runtime 与副作用恢复协议的架构图</media:description></media:content>
    </item>
    <item>
      <title>多 Agent 辩论真的增加了信息吗：TradingAgents 的组织图与相关性风险</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/agent-system-design-tradingagents/</link>
      <pubDate>Fri, 07 Aug 2026 18:50:00 +0800</pubDate>
      <atom:updated>Fri, 07 Aug 2026 18:50:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/agent-system-design-tradingagents/</guid>
      <description>以 TradingAgents v0.3.1 与论文 v7 为样本，把分析师、牛熊辩手、交易员、风险声部和组合经理还原成真实 LangGraph。文章区分角色多样性与证据独立性，核验串行分析、共享模型、时间截点、checkpoint 和反思记忆，并以相关性、消融及外部执行成本检验多 Agent 辩论是否真正增加信息。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Harness Engineering</category>
      <category domain="tag">Data Processing</category>
      <category domain="tag">Monitoring</category>
      <category domain="tag">Security</category>
      <category domain="tag">Development</category>
      <enclosure url="https://cubxxw.com/images/agent-system-series/09-tradingagents/tradingagents-evidence-debate-graph.svg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/agent-system-series/09-tradingagents/tradingagents-evidence-debate-graph.svg" medium="image"><media:description>TradingAgents 从时间截点证据、串行分析师、牛熊法庭、风险声部到组合经理研究输出的证据法庭架构图</media:description></media:content>
    </item>
    <item>
      <title>Instructions as Code：OpenMontage 如何用工件契约编排视频生产</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/agent-system-design-openmontage/</link>
      <pubDate>Fri, 07 Aug 2026 18:20:00 +0800</pubDate>
      <atom:updated>Fri, 07 Aug 2026 18:20:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/agent-system-design-openmontage/</guid>
      <description>以 OpenMontage 固定提交为样本，沿脚本、分镜、素材、剪辑、渲染与导出追踪规范工件，解释 coding assistant 如何用 YAML 和 Skill 驱动生产。文章拆开 tool、checkpoint、validator 与人工门，并以无音轨成片和付费素材崩溃检验恢复、成本、版权及发布边界。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Harness Engineering</category>
      <category domain="tag">Automation</category>
      <category domain="tag">Content Strategy</category>
      <category domain="tag">Development</category>
      <category domain="tag">Open Source</category>
      <enclosure url="https://cubxxw.com/images/agent-system-series/08-openmontage/openmontage-artifact-production-line.svg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/agent-system-series/08-openmontage/openmontage-artifact-production-line.svg" medium="image"><media:description>OpenMontage 由 instruction 控制带、canonical artifact 胶片河和工具检查点验证带组成的视频生产架构图</media:description></media:content>
    </item>
    <item>
      <title>拒绝成为 Agent：TaxHacker 为什么把 LLM 压缩成一个函数</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/agent-system-design-taxhacker/</link>
      <pubDate>Fri, 07 Aug 2026 17:55:00 +0800</pubDate>
      <atom:updated>Fri, 07 Aug 2026 17:55:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/agent-system-design-taxhacker/</guid>
      <description>以 TaxHacker v0.8.5 为样本，追踪票据如何经过多模态抽取、provider fallback、动态 schema、表单校验、重复检查与人工保存，解释何时应把 LLM 限制成结构化函数。文章区分结构有效、事实正确与会计记录，并揭示 compatible 路径、前四页预览、缓存候选和金融数据的边界。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Document AI</category>
      <category domain="tag">Data Processing</category>
      <category domain="tag">Security</category>
      <category domain="tag">Development</category>
      <enclosure url="https://cubxxw.com/images/agent-system-series/07-taxhacker/taxhacker-bounded-ai.svg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/agent-system-series/07-taxhacker/taxhacker-bounded-ai.svg" medium="image"><media:description>TaxHacker 将不可信票据经顺序 provider 抽取、schema 窄腰、原件核对、表单校验与显式保存变成 canonical transaction 的架构图</media:description></media:content>
    </item>
    <item>
      <title>OpenClaw 的常驻网关：连续性不是把所有消息塞进同一会话</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/agent-system-design-openclaw/</link>
      <pubDate>Fri, 07 Aug 2026 17:40:00 +0800</pubDate>
      <atom:updated>Fri, 07 Aug 2026 17:40:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/agent-system-design-openclaw/</guid>
      <description>以 OpenClaw v2026.7.1-2 为样本，追踪消息如何经过渠道准入、binding、agent 与 session key，解释跨渠道连续性的身份维度。文章拆开 Gateway、模型、workspace、sandbox 与设备节点，并用跨账户串线反例说明常驻 Agent 的权限、凭据、注入与撤销边界。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Harness Engineering</category>
      <category domain="tag">Security</category>
      <category domain="tag">Monitoring</category>
      <category domain="tag">Automation</category>
      <category domain="tag">Development</category>
      <enclosure url="https://cubxxw.com/images/agent-system-series/06-openclaw/openclaw-persistent-gateway.svg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/agent-system-series/06-openclaw/openclaw-persistent-gateway.svg" medium="image"><media:description>OpenClaw 从互联网渠道经过常驻 Gateway、确定性 bindings、session key、per-agent enclave 到设备节点与外部副作用的路由图</media:description></media:content>
    </item>
    <item>
      <title>n8n 的确定性外骨骼：Queue、Worker 与副作用从不承诺 Exactly-Once</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/agent-system-design-n8n/</link>
      <pubDate>Fri, 07 Aug 2026 17:25:00 +0800</pubDate>
      <atom:updated>Fri, 07 Aug 2026 17:25:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/agent-system-design-n8n/</guid>
      <description>以 n8n 2.33.6 源码追踪一次执行如何跨主进程、Redis 队列、工作进程与 Postgres 流动，并拆开工作流图与 Agent 节点的控制边界。文章解释等待、重试、崩溃恢复、幂等键和对账各自解决什么，以及 queue mode 为什么只能扩大吞吐，不能承诺 exactly-once 副作用。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Automation</category>
      <category domain="tag">Harness Engineering</category>
      <category domain="tag">Monitoring</category>
      <category domain="tag">Security</category>
      <category domain="tag">Development</category>
      <enclosure url="https://cubxxw.com/images/agent-system-series/05-n8n/n8n-deterministic-spine.svg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/agent-system-series/05-n8n/n8n-deterministic-spine.svg" medium="image"><media:description>n8n 确定性 workflow 主干、受限 Agent 支线、人工与幂等闸门、外部回执对账以及 Redis worker Postgres queue-mode 车场</media:description></media:content>
    </item>
    <item>
      <title>Codex 的协议化内核：第二个 Surface 不该复制第一个 Agent</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/agent-system-design-codex/</link>
      <pubDate>Fri, 07 Aug 2026 17:05:00 +0800</pubDate>
      <atom:updated>Fri, 07 Aug 2026 17:05:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/agent-system-design-codex/</guid>
      <description>以 Codex 0.147.0、App Server 契约和 Rust core 为证据，拆开 Thread、Turn、Item 与 Submission、Event 两层协议。文章解释多种客户端如何共享 Agent loop、状态与治理，并厘清 approval、sandbox、持久化与产品 Surface 的边界。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Harness Engineering</category>
      <category domain="tag">Open Source</category>
      <category domain="tag">Development</category>
      <category domain="tag">Security</category>
      <category domain="tag">MCP</category>
      <enclosure url="https://cubxxw.com/images/agent-system-series/03-codex/codex-event-control-plane.svg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/agent-system-series/03-codex/codex-event-control-plane.svg" medium="image"><media:description>Codex 多 Surface、App Server 公共契约、Submission 与 Event 双总线以及 approval 和 sandbox 副作用闸门</media:description></media:content>
    </item>
    <item>
      <title>Pi 的减法：最小 Agent Kernel 保留什么，责任又去了哪里</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/agent-system-design-pi/</link>
      <pubDate>Fri, 07 Aug 2026 16:40:00 +0800</pubDate>
      <atom:updated>Fri, 07 Aug 2026 16:40:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/agent-system-design-pi/</guid>
      <description>以 Pi v0.84.1 源码为证据，沿 agent loop、默认四工具、JSONL session tree 与 extension seam 反推最小 Agent kernel。文章审计 Pi 省略 Plan、MCP、subagent、permission 和 sandbox 后，安全、一致性和恢复责任的去向。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Harness Engineering</category>
      <category domain="tag">Open Source</category>
      <category domain="tag">Development</category>
      <category domain="tag">Security</category>
      <category domain="tag">Context Engineering</category>
      <enclosure url="https://cubxxw.com/images/agent-system-series/02-pi/pi-minimal-kernel.svg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/agent-system-series/02-pi/pi-minimal-kernel.svg" medium="image"><media:description>Pi 最小 Agent kernel、可拆卸 extension 轨道、provider 与 host OS 信任边界以及下方 JSONL session tree</media:description></media:content>
    </item>
    <item>
      <title>open-lovable 源码拆解：Agentic Search、文本协议与双沙箱</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/dissecting-open-lovable/</link>
      <pubDate>Mon, 29 Jun 2026 09:30:00 +0800</pubDate>
      <atom:updated>Mon, 29 Jun 2026 09:30:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/dissecting-open-lovable/</guid>
      <description>基于固定提交审计 Firecrawl 的 open-lovable，拆解网址抓取、流式代码生成、Agentic Search、Morph 增量编辑与 E2B、Vercel 双沙箱实现。文章区分仓库当时使用的能力与平台当前提供的功能，纠正命中率、耗时和隔离层误读，适合设计 AI 应用生成器、代码检索与执行边界的开发者。
</description>
      <category domain="category">Development</category>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">LLM</category>
      <category domain="tag">Architecture</category>
      <category domain="tag">Harness Engineering</category>
      <category domain="tag">Development</category>
      <category domain="tag">Open Source</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2026/dissecting-open-lovable.png" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2026/dissecting-open-lovable.png" medium="image"><media:description>open-lovable 从网页抓取到代码生成与双沙箱预览的源码架构</media:description></media:content>
    </item>
    <item>
      <title>Relay Agent 架构审计：从设计承诺到本地实现</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/relay-agent-architecture-design/</link>
      <pubDate>Wed, 24 Jun 2026 10:00:00 +0800</pubDate>
      <atom:updated>Fri, 31 Jul 2026 18:00:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/relay-agent-architecture-design/</guid>
      <description>基于 Relay 私有本地实现的源码审计，核对协调器、五个领域 Agent、Harness、路由、事件系统与浏览器投递链路，区分已实现、已测试、设计中和示意内容，并重点解释 LangGraph 恢复语义、幂等边界、审计持久化、反虚构守卫的能力边界，以及浏览器自动化面对服务条款、提示注入和敏感字段时保留的人类审批机制。
</description>
      <category domain="category">Development</category>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">LLM</category>
      <category domain="tag">Python</category>
      <category domain="tag">Security</category>
      <category domain="tag">Development</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>Relay 协调器、五个领域 Agent、浏览器投递、防护机制和审计边界组成的架构图</media:description></media:content>
    </item>
    <item>
      <title>UFO² 桌面 AgentOS：从 Windows 自动化到 UFO³ Galaxy</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/UFO/</link>
      <pubDate>Fri, 09 May 2025 21:30:15 +0800</pubDate>
      <atom:updated>Fri, 31 Jul 2026 01:41:06 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/UFO/</guid>
      <description>从 UFO v1 的界面操作，到 UFO² 的 Windows 桌面 AgentOS，再到 UFO³ Galaxy 的跨设备编排，本文以 UFO² 为主线拆解 HostAgent、AppAgent、GUI 与 API 混合执行、知识检索、PiP 隔离桌面和 MCP，并给出 2026 年仍可使用的安装配置方法与工程判断。
</description>
      <category domain="category">Development</category>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Automation</category>
      <category domain="tag">Development</category>
      <category domain="tag">MCP</category>
      <category domain="tag">Open Source</category>
      <category domain="tag">Project Learning</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2025/UFO.png" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2025/UFO.png" medium="image"><media:description>UFO² 桌面 AgentOS 的多智能体架构</media:description></media:content>
    </item>
    <item>
      <title>独立开发者技术栈指南：从问题验证到可维护 MVP</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/independent-developer/</link>
      <pubDate>Tue, 15 Apr 2025 20:53:12 +0800</pubDate>
      <atom:updated>Fri, 31 Jul 2026 12:00:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/independent-developer/</guid>
      <description>这是一份写给独立开发者的常青技术栈与MVP路线图：从访谈和手工交付验证真实问题，收敛前后端、数据库与API选择，再补齐Git、Docker、持续集成、测试、部署、支付、分析和维护机制。文章不列容易过期的工具榜单，而用阶段决策表、退出成本和真实取舍，帮助一人团队少造基础设施、尽早收费，让产品保持可迁移、可观测、可演进。
</description>
      <category domain="category">Development</category>
      <category domain="tag">Solo Builder</category>
      <category domain="tag">Product Strategy</category>
      <category domain="tag">Development</category>
      <category domain="tag">Git</category>
      <category domain="tag">Docker</category>
      <category domain="tag">Testing</category>
      <category domain="tag">Deployment</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2025/independent-developer.png" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2025/independent-developer.png" medium="image"><media:description>独立开发者从问题验证走向可维护MVP的技术路线图</media:description></media:content>
    </item>
    <item>
      <title>LangChain 1.x 实战指南：从模型调用到可观测 Agent</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/harnessing-language-model-applications-with-langchain-a-developer-is-guide/</link>
      <pubDate>Wed, 22 May 2024 21:37:34 +0800</pubDate>
      <atom:updated>Fri, 31 Jul 2026 10:00:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/harnessing-language-model-applications-with-langchain-a-developer-is-guide/</guid>
      <description>面向 Python 开发者的 LangChain 1.x 实战指南，覆盖模型初始化、工具调用、结构化输出、中间件，以及 LangGraph 记忆、RAG、SQL Agent、Ollama 本地模型和 LangSmith 追踪。文章提供 API 迁移表、可运行代码与排错清单，帮助你避开过时示例，构建可维护的智能体应用。
</description>
      <category domain="category">Development</category>
      <category domain="tag">AI</category>
      <category domain="tag">LLM</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Python</category>
      <category domain="tag">RAG</category>
      <category domain="tag">Development</category>
      <category domain="tag">Automation</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2024/harnessing-language-model-applications-with-langchain-a-developer-is-guide.png" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2024/harnessing-language-model-applications-with-langchain-a-developer-is-guide.png" medium="image"><media:description>LangChain 1.x 模型、Agent、记忆与可观测性工程架构</media:description></media:content>
    </item>
    <item>
      <title>从语言模型到 RAG：理解大模型的能力、边界与工程方法</title>
      <link>https://cubxxw.com/zh/ai-agent/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>Wed, 15 May 2024 20:12:29 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/exploring-large-language-models-llms-pioneering-ai-understanding-generation-human-language/</guid>
      <description>从预测下一个词出发，理解 Transformer、规模化与所谓涌现能力，再走进检索增强生成的完整工程链路。本文不追逐模型榜单，而是解释大模型为何有效、何时会失败，如何设计检索、引用、评估与安全边界，帮助开发者把概率性的语言能力变成可验证、可维护、能持续演进的知识系统。 也给出一条从原型走向生产环境的务实路径。
</description>
      <category domain="category">Development</category>
      <category domain="tag">AI</category>
      <category domain="tag">LLM</category>
      <category domain="tag">RAG</category>
      <category domain="tag">Context Engineering</category>
      <category domain="tag">Development</category>
      <category domain="tag">Testing</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2024/exploring-large-language-models-llms-pioneering-ai-understanding-generation-human-language.jpeg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2024/exploring-large-language-models-llms-pioneering-ai-understanding-generation-human-language.jpeg" medium="image"><media:description>从语言模型到 RAG：理解大模型的能力、边界与工程方法</media:description></media:content>
    </item>
    <item>
      <title>探索开源以及开源商业模式研究</title>
      <link>https://cubxxw.com/zh/engineering/posts/navigating-the-open-source-landscape/</link>
      <pubDate>Sat, 13 Apr 2024 20:29:22 +0800</pubDate>
      <atom:updated>Sat, 13 Apr 2024 20:29:22 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/engineering/posts/navigating-the-open-source-landscape/</guid>
      <description>本文深入探讨了开源和商业模式的结合，分析了开源项目的经济潜力与挑战，为开发者提供了如何在开源项目中找到商业机会的实用指南。</description>
      <category domain="tag">Open Source</category>
      <category domain="tag">Product Strategy</category>
      <category domain="tag">Development</category>
    </item>
    <item>
      <title>Sora 停服之后：SoraEase 提示词档案与开发者迁移指南</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/sora-ease-guide-mastering-sora-ai-for-developers/</link>
      <pubDate>Thu, 14 Mar 2024 08:44:13 +0800</pubDate>
      <atom:updated>Fri, 31 Jul 2026 16:00:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/sora-ease-guide-mastering-sora-ai-for-developers/</guid>
      <description>这是一份写于 2024 年、在 Sora 停服后重新校订的 SoraEase 提示词档案。文章核对 Sora 从研究预览、正式发布到 API 退场的时间线，保留五个有方法价值的提示词，并给出场景契约、三层评测、适配器设计与退出清单，帮助仍在使用视频生成接口的开发者迁移，同时避免把历史经验误写成仍然有效的产品承诺。
</description>
      <category domain="category">Development</category>
      <category domain="tag">AI</category>
      <category domain="tag">Development</category>
      <category domain="tag">Open Source</category>
      <category domain="tag">Automation</category>
      <category domain="tag">Testing</category>
      <category domain="tag">Content Strategy</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2024/sora-ease-guide-mastering-sora-ai-for-developers.png" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2024/sora-ease-guide-mastering-sora-ai-for-developers.png" medium="image"><media:description>废弃的胶片越过桥梁，连接到模块化视频工作流</media:description></media:content>
    </item>
    <item>
      <title>Sora 完整复盘：从视频生成技术预览、Sora 2 到产品与 API 停止</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/exploring-sora-technology-for-enthusiasts-and-developers/</link>
      <pubDate>Sat, 24 Feb 2024 13:30:15 +0800</pubDate>
      <atom:updated>Fri, 31 Jul 2026 00:00:00 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/exploring-sora-technology-for-enthusiasts-and-developers/</guid>
      <description>本文复盘Sora从2024年研究预览、Sora Turbo产品化，到2025年Sora 2加入同步音频，再到2026年产品停止、API进入关闭倒计时的路径；拆解扩散Transformer与时空patch，澄清一分钟研究样例与1080p、20秒产品规格的区别，并从内容溯源、肖像同意、版权风险与系统迁移中提炼开发者教训。
</description>
      <category domain="category">Development</category>
      <category domain="tag">AI</category>
      <category domain="tag">Development</category>
      <category domain="tag">Product Strategy</category>
      <category domain="tag">Security</category>
      <category domain="tag">Content Strategy</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2024/exploring-sora-technology-for-enthusiasts-and-developers.png" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2024/exploring-sora-technology-for-enthusiasts-and-developers.png" medium="image"><media:description>Sora 从技术预览、产品化到停止服务的时间线</media:description></media:content>
    </item>
    <item>
      <title>Hugo 的高级教程</title>
      <link>https://cubxxw.com/zh/engineering/posts/hugo-advanced-tutorial/</link>
      <pubDate>Mon, 06 Nov 2023 13:44:09 +0800</pubDate>
      <atom:updated>Mon, 06 Nov 2023 13:44:09 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/engineering/posts/hugo-advanced-tutorial/</guid>
      <description>本教程为Hugo高级教程，适合已经有Hugo基础知识的开发者。我们将深入探讨Hugo的高级功能和最佳实践，包括自定义主题开发、数据模板、性能优化和部署策略。此外，教程将介绍如何将Hugo与GitHub结合使用，实现持续部署和版本控制，以优化的工作流程。</description>
      <category domain="tag">Hugo</category>
      <category domain="tag">Blog</category>
      <category domain="tag">Development</category>
    </item>
    <item>
      <title>Kubernetes 控制平面 - Kubectl 详细讲解</title>
      <link>https://cubxxw.com/zh/engineering/posts/deep-dive-into-the-components-of-kubernetes-kubectl/</link>
      <pubDate>Thu, 28 Sep 2023 20:29:30 +0800</pubDate>
      <atom:updated>Thu, 28 Sep 2023 20:29:30 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/engineering/posts/deep-dive-into-the-components-of-kubernetes-kubectl/</guid>
      <description>kubelet 架构kubelet 管理 Pod 的核心流程kubelet 节点管理Pod 管理Pod</description>
      <category domain="tag">Development</category>
      <category domain="tag">Go</category>
      <category domain="tag">Kubernetes</category>
    </item>
    <item>
      <title>一份完整的开源贡献指南（提供给第一次踏入开源伙伴秘籍）</title>
      <link>https://cubxxw.com/zh/engineering/posts/open-source-contribution-guidelines/</link>
      <pubDate>Sat, 16 Sep 2023 16:40:54 +0800</pubDate>
      <atom:updated>Sat, 16 Sep 2023 16:40:54 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/engineering/posts/open-source-contribution-guidelines/</guid>
      <description>探索OpenIM这一活跃的开源项目如何实现其商业发展目标。了解OpenIM如何取得成功，应对挑战，并在社区贡献与商业化之间找到平衡。</description>
      <category domain="tag">Blog</category>
      <category domain="tag">OpenIM</category>
      <category domain="tag">Development</category>
    </item>
    <item>
      <title>关于我的 Hugo 博客 (教程)</title>
      <link>https://cubxxw.com/zh/engineering/posts/my-hugo/</link>
      <pubDate>Tue, 12 Sep 2023 14:26:20 +0800</pubDate>
      <atom:updated>Tue, 12 Sep 2023 14:26:20 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/engineering/posts/my-hugo/</guid>
      <description>本教程将指导你如何使用 Hugo —— 一款流行的静态网站生成器 —— 来搭建和管理个人博客。详细介绍从安装到配置的各个步骤。</description>
      <category domain="tag">Blog</category>
      <category domain="tag">Hugo</category>
      <category domain="tag">Development</category>
      <enclosure url="https://cubxxw.com/images/covers/engineering/2023/my-hugo.jpeg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/engineering/2023/my-hugo.jpeg" medium="image"><media:description>关于我的 Hugo 博客 (教程)</media:description></media:content>
    </item>
    <item>
      <title>Go 调试测试以及调试工具 dlv 学习</title>
      <link>https://cubxxw.com/zh/engineering/posts/use-go-tools-dlv/</link>
      <pubDate>Mon, 19 Jun 2023 16:38:39 +0800</pubDate>
      <atom:updated>Mon, 19 Jun 2023 16:38:39 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/engineering/posts/use-go-tools-dlv/</guid>
      <description>本文深入介绍 Go 语言的调试过程，测试方法以及如何使用调试工具 dlv 来优化代码。</description>
      <category domain="tag">Blog</category>
      <category domain="tag">Development</category>
      <category domain="tag">Debugging</category>
    </item>
  </channel>
</rss>
