<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>人工智能 on 正能量</title><link>https://www.znl.net/categories/%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD/</link><description>Recent content in 人工智能 on 正能量</description><generator>Hugo -- gohugo.io</generator><language>zh-CN</language><copyright>© 2026 正能量</copyright><lastBuildDate>Tue, 20 Oct 2026 12:27:42 +0800</lastBuildDate><atom:link href="https://www.znl.net/categories/%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD/index.xml" rel="self" type="application/rss+xml"/><item><title>给 AI 编程助手一台独立 Linux：沙箱、凭据与验收边界</title><link>https://www.znl.net/posts/ai-agent-linux-sandbox/</link><pubDate>Tue, 13 Oct 2026 00:00:00 +0800</pubDate><guid>https://www.znl.net/posts/ai-agent-linux-sandbox/</guid><description>让 Agent 在独立 Linux 中写代码，能减少它直接影响开发电脑的机会。模型服务、执行环境与业务授权仍要分别设计，磁盘检查点也无法撤销外部动作。</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.znl.net/posts/ai-agent-linux-sandbox/featured.png"/></item><item><title>Ollama 与 GGUF：本地模型能否运行，要看哪些条件</title><link>https://www.znl.net/posts/ollama-gguf-support/</link><pubDate>Fri, 05 Jun 2026 00:00:00 +0800</pubDate><guid>https://www.znl.net/posts/ollama-gguf-support/</guid><description>下载到 GGUF 文件，只完成了本地部署的一步。分别检查文件、模型架构、推理后端和硬件资源，再用固定任务比较性能，才能定位加载失败或运行缓慢的原因。</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.znl.net/posts/ollama-gguf-support/featured.png"/></item><item><title>让 AI 编程任务持续推进：执行环境、状态交接与恢复设计</title><link>https://www.znl.net/posts/long-running-agent-harness/</link><pubDate>Tue, 24 Mar 2026 00:00:00 +0800</pubDate><guid>https://www.znl.net/posts/long-running-agent-harness/</guid><description>长任务不能只依赖一段越来越长的聊天记录。把任务拆成可验收的切片，保存代码版本与验证证据，才能在中断后找到可靠的下一步。</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.znl.net/posts/long-running-agent-harness/featured.png"/></item><item><title>AI Agent 评估怎么做：从一次演示到可靠完成任务</title><link>https://www.znl.net/posts/agent-evaluation-guide/</link><pubDate>Fri, 09 Jan 2026 00:00:00 +0800</pubDate><guid>https://www.znl.net/posts/agent-evaluation-guide/</guid><description>演示成功一次，不能说明 Agent 可以稳定交付。通过固定任务题集、核对最终状态、重复试验和隔离环境，才能发现退步并解释失败原因。</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.znl.net/posts/agent-evaluation-guide/featured.png"/></item><item><title>MCP 工具太多、结果太大怎么办：让代码处理中间数据</title><link>https://www.znl.net/posts/mcp-code-execution/</link><pubDate>Tue, 04 Nov 2025 00:00:00 +0800</pubDate><guid>https://www.znl.net/posts/mcp-code-execution/</guid><description>用只读构建统计流程说明如何把确定性处理交给代码，并让模型得到精简、完整且能追溯的结果。</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.znl.net/posts/mcp-code-execution/featured.png"/></item><item><title>把重复工作教给 AI：设计一份真正有用的 Agent Skill</title><link>https://www.znl.net/posts/agent-skills-guide/</link><pubDate>Thu, 16 Oct 2025 00:00:00 +0800</pubDate><guid>https://www.znl.net/posts/agent-skills-guide/</guid><description>将接口检查经验拆成入口说明、检查表和案例，让 AI 按需获取工作方法，并通过正反案例验证技能是否有效。</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.znl.net/posts/agent-skills-guide/featured.jpg"/></item><item><title>AI 为什么越聊越乱：用一次后端排障理解上下文工程</title><link>https://www.znl.net/posts/ai-context-engineering/</link><pubDate>Mon, 29 Sep 2025 00:00:00 +0800</pubDate><guid>https://www.znl.net/posts/ai-context-engineering/</guid><description>把 AI 的上下文当作一份需要维护的工作资料，设计可追溯的排障记录，并用证据检查回答质量。</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.znl.net/posts/ai-context-engineering/featured.png"/></item><item><title>Ollama 流式工具调用：从逐字输出到完整执行闭环</title><link>https://www.znl.net/posts/ollama-streaming-tools/</link><pubDate>Wed, 28 May 2025 00:00:00 +0800</pubDate><guid>https://www.znl.net/posts/ollama-streaming-tools/</guid><description>聊天文字可以边生成边展示，工具却需要完整参数才能执行。把增量消息收集、参数校验、执行结果和停止条件连接起来，才能形成可靠的工具调用闭环。</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.znl.net/posts/ollama-streaming-tools/featured.png"/></item><item><title>Java 开发者接入 Spring AI：从一次模型调用到可控的业务服务</title><link>https://www.znl.net/posts/spring-ai-java-guide/</link><pubDate>Tue, 20 May 2025 00:00:00 +0800</pubDate><guid>https://www.znl.net/posts/spring-ai-java-guide/</guid><description>沿着熟悉的 Spring 服务分层理解 AI 集成：先接通一次请求，再逐步增加资料、会话与工具能力，同时保留输入校验、权限和失败处理。</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.znl.net/posts/spring-ai-java-guide/featured.png"/></item><item><title>DeepSeek-R1 与 Open-R1：推理模型、蒸馏和开源复现怎么区分</title><link>https://www.znl.net/posts/deepseek-r1-open-r1/</link><pubDate>Tue, 28 Jan 2025 00:00:00 +0800</pubDate><guid>https://www.znl.net/posts/deepseek-r1-open-r1/</guid><description>区分基础模型、推理训练、蒸馏和开源复现，再用固定任务评估模型效果，并估算本地部署需要的内存与计算资源。</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.znl.net/posts/deepseek-r1-open-r1/featured.png"/></item></channel></rss>