1. 我对移动运营商的APK进行了逆向工程——随后Hermes Agent撰写了执行报告 05-28 I reverse-engineered my mobile operator''s APK — then Hermes Agent wrote the executive report (dev.to)
2. 我将Hermes Agent转变为一个可验证的代理操作系统 05-30 I Turned Hermes Agent into a Verifiable Agent Operating System (dev.to)
3. 我在 Python 代理中添加了一个 71 行代码的黑盒子，然后使用 DuckDB 查询了那次价值 200 美元的崩盘事件 00:54 I Added a 71-Line Black Box to My Python Agent, Then Queried the 200 Crash With DuckDB (dev.to)
6. 重振 Ultra Creative Suite：首款专为视障用户设计的全无障碍视频编辑器 05-30 Reviving Ultra Creative Suite: The First Fully Accessible Video Editor for Blind Users (dev.to)
8. 每一场伟大的杯赛都始于一个正确的问题——我借助 Hermes Agent 构建了支撑这个答案的社区 05-29 Every Great Cup Starts with the Right Question — I Built the Community Behind the Answer with Hermes Agent (dev.to)
9. 我用 Python 开发了一款人工智能驱动的电脑显示器。28 位陌生人共同构成了它的“大脑”。PC Workman 1.7.6 05-29 I Built an AI-Powered PC Monitor in Python. 28 Strangers Shaped Its Brain. PC Workman 1.7.6 (dev.to)
10. 两年前我没能完成的项目——ChatGPT笔记本 05-29 The Project I Couldn’t Finish 2 Years Ago - Notebook for ChatGPT (dev.to)
11. 我在 PM Agent 中添加了人工否决功能——看看首先出了什么问题 05-30 I Added a Human Veto to My PM Agent — Here''s What Broke First (dev.to)
12. 500 MB 的缓冲区如何导致我们的归档任务失败——以及为何流式传输解决了这个问题 05-28 How a 500 MB Buffer Killed Our Archival Job — And Why Streaming Fixed It (dev.to)
14. Hermes Agent 每天都在变得更智能。账单也是如此。 05-31 Hermes Agent Gets Smarter Every Day. So Does the Bill. (dev.to)
16. Kubernetes 过度使用：为何我为小型环境打造了一款“K8s 杀手” 05-29 The Kubernetes Overkill: Why I Built a "K8s Killer" for Small Environments (dev.to)
17. 一款自托管的 Google reCAPTCHA 替代方案（我们提供该服务） 05-17 A self-hosted Google reCAPTCHA alternative (we ship it) (dev.to)
18. 我开发了“Sổ Lãi”——一款专为越南网店设计的实用利润追踪工具 05-28 I Built Sổ Lãi, a Practical Profit Tracker for Vietnamese Online Shops (dev.to)
19. 我的 AI 总是在胡编乱造职业发展路径。我放弃了这个项目。GitHub Copilot 帮我修复了真正存在的问题。 05-24 My AI Kept Hallucinating Career Paths. I Abandoned the Project. GitHub Copilot Helped Me Fix What Was Actually Broken. (dev.to)
20. 开发者机会雷达 #1：10万美元的人工智能资助金、两项研究员奖学金以及人工智能代理资源 05-29 Dev Opportunity Radar #1: A 100K AI Grant, Two Fellowships, and an AI Agent Resource (dev.to)
21. DevRelCon NYC 2026：开发者关系、DevX 与开发者营销的交汇之地 05-30 DevRelCon NYC 2026: Where Developer Relations, DevX, & Developer Marketing Come Together (dev.to)
22. Copilot 帮助我将我的个人项目发布到了 App Store 05-28 Copilot helped me deploy my passion project to the App Store (dev.to)
23. Git 与 GitHub：如何使用简单的 Git 命令管理 GitHub 仓库 05-29 Git for GitHub: How to use simple Git commands to manage a GitHub repository (dev.to)
26. 我为自己的工学学士毕业设计开发了一个 MCP 代理框架。发布首周，该框架在 npm 上的下载量就突破了 750 次。以下便是它的逆袭故事。 05-28 I Built an MCP Agent Framework for My B.Tech Major Project. It Got 750 npm Downloads in Week One. Here''s the Comeback Story. (dev.to)
28. 利用 Hermes Agent 构建以离线模式为主的丛林大火响应平台 05-24 Building an Offline-First Bushfire Response Platform With Hermes Agent (dev.to)
30. AI 代理在处理我们 80% 的代码方面表现出色。剩下的 20% 正是我们仍需资深开发人员的原因。 05-28 AI Agents Are Great at 80% of Our Code. The Other 20% Is Why We Still Need Seniors. (dev.to)
34. 关于可访问性的问题：嵌套交互式元素是否不可取？ 05-27 Accessibility question: is nesting interactive elements bad? (dev.to)
36. 亲手打造AI聊天机器人让我对生成式AI有了哪些新认识 05-25 What Building My Own AI Bot Taught Me About Generative AI (dev.to)
37. Hermes Mentor —— 助你摆脱教程地狱的本地 AI 助手 05-27 Hermes Mentor — A Local AI Agent That Gets You Out of Tutorial Hell (dev.to)
38. Next.js 16 在 4 个地方导致我的应用崩溃，但都没有抛出错误 05-27 Next.js 16 Broke My App in 4 Places and None of Them Threw an Error (dev.to)
40. Hermes Agent 改变了我对执行边界的看法 05-26 Hermes Agent Changed How I Think About Execution Boundaries (dev.to)
41. 重振一个拥有1.2万星的废弃仓库：toastr-next v3 05-27 Reviving a 12K Star Abandoned Library: toastr-next v3 (dev.to)
43. GitHub Copilot 帮助我们在电子商务业务中将时间缩短了 50% 至 75% 05-26 Github Copilot helped us cut down 50-75% time in our e-commerce business (dev.to)
48. 你（目前）不需要微服务：给开发者的现实检验 05-26 You Don’t Need Microservices (Yet): A Reality Check for Devs (dev.to)
49. 如果连微软和优步都负担不起人工智能编程，我们其他人还有什么机会？ 05-25 If Microsoft and Uber can''t afford AI coding, what chance do the rest of us have? (dev.to)
50. 现在我明白为什么翻译们会因人工智能而感到恐慌了——程序员也该恐慌吗？ 25-11-28 Now I See Why Translators Are Panicking Over AI—Should Coders Panic Too? (dev.to)
51. 你的收件箱知道得太多了：专为隐私控打造的 Parsli 05-24 Your Inbox Knows Too Much: Parsli for the Privacy Paranoid (dev.to)
53. 为什么人工智能生成的代码总是“够用”——却永远称不上“出色” 05-25 Why AI-Generated Code Is Always Good Enough — And Never Great (dev.to)
54. 一款基于 Google Gemma 4 的 100% 私有本地 AI 简历优化工具：我是如何打造 ResuMate 的！ 05-18 A 100% Private, Local AI Resume Optimizer with Google Gemma 4: How I Built ResuMate! (dev.to)
55. Google I/O 2026：AI 仅用 12 小时就开发出一个操作系统。而我却把时间都花在整理截图上了。 05-25 Google I/O 2026: AI Built an OS in 12 Hours. I Spent Mine Sorting Screenshots. (dev.to)
56. 别让人工智能破坏你们的集体思维：面向工程团队的实用指南 05-08 Don’t let AI break your collective thinking: a practical guide for engineering teams (dev.to)
57. 我放弃了云端大型语言模型，转而使用 Gemma 4 4B：一位 DevOps 工程师的 48 小时现实检验 05-25 I Ditched Cloud LLMs for Gemma 4 4B: A DevOps Engineer''s 48-Hour Reality Check (dev.to)
58. PromptGuard：我开发了一款本地 AI 隐私防火墙，能在提示词离开您的设备之前对其进行数据脱敏处理 05-25 PromptGuard: I Built a Local AI Privacy Firewall That Sanitizes Your Prompts Before They Leave Your Machine (dev.to)
59. Vestige：一款不会对你吹牛的Gemma 4脑电波追踪仪 05-21 Vestige: A Gemma 4 Brain Tracker That Won''t Blow Smoke Up Your Ass (dev.to)
60. 先做再用：我是如何从零开始编写435节人工智能工程课程的 05-24 Build It, Then Use It: How I wrote 435 AI engineering lessons from scratch (dev.to)
61. 你的公司不会用优秀的AI来取代你。他们只会用糟糕的AI来取代你。 05-23 Your company won''t replace you with good AI. They''ll replace you with bad AI. (dev.to)
62. NeuralHats：我利用Gemma 4将爱德华·德·博诺的“六顶思考帽”模型应用于本地化大型语言模型 05-24 NeuralHats: I Put Edward de Bono’s Six Thinking Hats on Local LLMs Using Gemma 4 (dev.to)
64. 如何聪明地使用 Gemma 4 E2B：家庭旅行指南 05-15 How to Use Gemma 4 E2B the Smart Way: Family Trip Advisor (dev.to)
65. 大家都在热议 Gemini 3.5 Flash。但 2026 年 Google I/O 大会上的真正亮点其实是一个技能文件。 05-24 Everyone''s Talking About Gemini 3.5 Flash. The Real Story at Google I/O 2026 Was a Skill File. (dev.to)
67. Google Antigravity 1.0 至 2.0/IDE 快速迁移指南 05-23 Google Antigravity 1.0 to 2.0/IDE Quick Migration Guide (dev.to)
68. 从“洞穴”里的手机到全球开源：谷歌的Gemma模型为何是预算有限开发者的救命稻草 05-20 From a Phone in a "Cave" to Global Open Source: Why Google’s Gemma Models are a Lifeline for Budget Developers (dev.to)
70. 我在笔记本电脑的显卡上对 Gemma 4 E4B 的 128K 上下文进行了压力测试——召回效果很好，预填充效果则不尽如人意 05-24 I stress-tested Gemma 4 E4B''s 128K context on a laptop GPU — recall is great, prefill is not (dev.to)
71. 一款让你的 GitHub README 引人注目的工具 05-23 A tool to make your GitHub README impossible to ignore (dev.to)
72. 2026年谷歌I/O大会上最被低估的公告，竟被埋没在一段90秒的演示中 05-22 The Most Underrated Announcement from Google I/O 2026 Was Buried in a 90-Second Demo (dev.to)
73. 我基于 Gemma 4 E4B 的 128K 上下文构建了一个本地文档问答工具——耗时五天，未使用 RAG，也未连接云端 05-24 I built a local document Q&A tool around Gemma 4 E4B''s 128K context — five days, no RAG, no cloud (dev.to)
74. 我仅用3个月就搭建了一个生产级电商平台——GitHub Copilot 就是我的联合创始人 05-24 I Built a Production-Grade E-Commerce Platform in 3 Months — GitHub Copilot Was My Co-Founder (dev.to)
75. 从一个被搁置的黑客马拉松项目到一个 AI 学习工作区 05-23 From an Abandoned Hackathon Project to an AI Study Workspace (dev.to)
76. 7 个 Next.js 16 版本的缓存漏洞：编译通过却在生产环境中悄然失效 05-21 7 Next.js 16 Caching Bugs That Compile Fine and Break Silently in Production (dev.to)
78. 我提高了Gemma 4的代币上限。Dense模型不再拒绝了。 05-21 I Raised Gemma 4''s Token Cap. The Dense Model Stopped Refusing. (dev.to)
79. 您应该在开发中使用 Gemma 4 吗？通过多维分析，判断 Gemma 4 是否适合您！ 05-16 Should you use Gemma 4 for your Development? A Multiversal Analysis to Determine if Gemma 4 is Right for You! (dev.to)
82. 我们如何利用 Gemini Embeddings 在 DEV 上构建一个更智能、由社区驱动的信息流 05-20 How we''re using Gemini Embeddings to build a smarter, community-driven feed on DEV (dev.to)
83. 无障碍功能——这看起来正是开发者倡导者大显身手的时候！ 05-21 Accessibility - This looks like a job for a developer advocate! (dev.to)
84. 在 AWS 上构建制作公司网站 — 项目概述 05-21 Building a Production Company Website on AWS — Project Overview (dev.to)
85. 2026年的 jnigen 和 swiftgen——一些经验教训 05-21 jnigen and swiftgen in 2026 - some lessons learned (dev.to)
87. 回收变简单：一款由Gemma 4驱动的波兰回收助手 05-15 Recycling made easy: a Polish recycling assistant powered by Gemma 4 (dev.to)
89. 利用人工智能构建数据库性能测试工具：真实详解 05-21 Building a Database Performance Testing Tool With AI: The Honest Breakdown (dev.to)
90. 参加 GitHub “Finish-Up-A-Thon” 挑战赛：总奖金高达 3,000 美元！ 05-19 Join the GitHub Finish-Up-A-Thon Challenge: 3,000 Prize Pool! (dev.to)
93. 中级开发者的悖论：为何初级开发者从容不迫，而中级开发者却会在凌晨三点重构你的代码 05-20 The Mid-Dev Paradox: Why Juniors Are Chill and Mid-Levels Will Reorganize Your Code at 3 AM (dev.to)
95. 每个开发者都在撒谎——而人工智能也无能为力 05-21 Every Developer Is Lying About Something — And AI Won’t Fix It (dev.to)
96. MCP 现已登陆您的手机：Google AI Edge Gallery 的实际功能是什么 05-21 MCP Just Landed on Your Phone: What Google AI Edge Gallery Actually Does (dev.to)
97. 一个糟糕的提示词如何在18分钟内耗尽了我40美元的Claude预算 05-19 How one bad prompt burned 40 of my Claude budget in 18 minutes (dev.to)
98. 我决定构建一个 Kubernetes 替代方案。是的，我知道我疯了 05-20 I decided to build a Kubernetes alternative. Yes, I know I''m crazy (dev.to)
100. 与日本客户合作让我比预想中更快地学会了谦逊 05-18 Working With Japanese Clients Humbled Me Faster Than I Expected (dev.to)
101. Google AI Edge Gallery 现已支持在设备上运行 MCP。隐私架构 05-20 Google AI Edge Gallery Now Runs MCP On-Device. The Privacy Architecture (dev.to)
102. 发现了一个隐藏在我关注者中的、有组织的 GitHub 关注机器人网络？ 05-20 Found a Coordinated GitHub Follow Botnet Hiding in My Followers? (dev.to)
103. 为印度普及前沿人工智能：Gemma 4 在资源匮乏环境中的边缘计算能力 05-18 Democratizing Frontier AI for Bharat: Gemma 4’s Edge Capabilities in Low-Resource Environments (dev.to)
105. 人工智能不会取代初级开发人员。真正造成这种局面的，是你们的组织架构。 05-19 AI isn''t replacing junior devs. Your org chart is. (dev.to)
106. Cloudflare 已弃用我的生产环境模型。推荐的升级方案需花费 4 美元/百万令牌。而 Gemma 4 MoE 则无需此费用。 05-18 Cloudflare Deprecated My Production Model. The Recommended Upgrade Costs 4/M Tokens. Gemma 4 MoE Doesn''t. (dev.to)
107. 投资组合的数学逻辑：当30个小应用胜过1个大应用时。 05-14 The portfolio math. When 30 small apps beat 1 big one. (dev.to)
110. 我开发了一个免费的调试器，因为在开发过程中，Next.js 16 的 ''use cache'' 功能完全无法察觉 05-19 I built a free debugger because Next.js 16 ''use cache'' was completely invisible during development (dev.to)
111. 如果在人工智能时代，房间里的每部手机都能变成游戏手柄，会怎样？ 05-04 What If Every Phone in the Room Was a Game Controller — in the Age of AI? (dev.to)
113. 诚实是最好的策略。关于在DEV环境中使用AI的秘密之战 05-19 Honesty is the best Policy. The Secret Wars on the use of AI on DEV (dev.to)
116. 我还是不想给克劳德 SSH 访问权限，所以我为我的家庭实验室搭建了一个代理服务器 05-18 I still don''t want to give Claude SSH access, so I built a doctor for my homelab (dev.to)
117. 使用 Antigravity 和 Strava API 构建骑行分析 Web 应用 05-16 Building a Ride Analysis Web App with Antigravity and the Strava API (dev.to)
119. 自托管版 Gemma 4 用于生产自动化，揭示了两个 Ollama 漏洞 05-16 Self-Hosting Gemma 4 for Production Automation Revealed Two Ollama Bugs (dev.to)
120. 通过逐台MCP服务器，重新探索领域驱动设计 05-18 Rediscovering Domain-Driven Design, one MCP server at a time (dev.to)
122. 您的代码库存在技术债务。但您的团队是否也存在理解债务？ 04-22 Your Codebase Has Technical Debt. But Does Your Team Have Comprehension Debt? (dev.to)
123. 如今人人都在谈论更强大的AI模型。而我开发了一款基于Gemma 4的“农场医生”系统，即使在断网时也能正常运行。 05-18 Everyone''s Talking About Bigger AI Models. I Built a Gemma 4 Farm Doctor That Works When the Internet Doesn''t. (dev.to)
124. 我直接在浏览器中运行了 AI 模型，并测量了其对核心网络指标的影响 05-17 I Ran AI Models Directly in the Browser and Measured What It Did to Core Web Vitals (dev.to)
125. 真实调试案例 家庭网络分析：Peekyport 05-16 Real-Life Debugging Story Home Network Analysis: Peekyport (dev.to)
126. 我把过去六个月的回顾资料给了克劳德。它发现了我之前遗漏的三点。 05-18 I gave Claude six months of our retros. It found three things I''d missed. (dev.to)
127. DeepSeek 正运行在你最常用的 AI 工具中——而没人告诉你 05-18 DeepSeek Is Running Inside Your Favorite AI Tool – And Nobody Told You (dev.to)
128. 我为 Gemma4 挑战赛开发了一个实时美国手语（ASL）翻译器，无需云端支持 05-17 I built a real-time ASL interpreter for the Gemma4 challenge, no cloud needed (dev.to)
129. 我开发了一款桌面应用，彻底告别了“打开7个终端窗口然后祈祷”的日常 05-17 I Built a Desktop App That Ends My “Open 7 Terminals and Pray” Routine (dev.to)
131. #100DaysOfCode 第100天——我的成果、收获与下一步计划 05-15 Day 100 of #100DaysOfCode — What I Built, What I Learned, and What''s Next (dev.to)
132. 我受够了 Docker 占用我的树莓派内存——于是我开发了自己的容器编排工具 05-17 I Got Tired of Docker Eating My Raspberry Pi''s RAM — So I Built My Own Container Orchestrator (dev.to)
133. Gemma 4 対 克劳德 対 Llama：哪款模型最受开发者青睐 05-18 Gemma 4 vs Claude vs Llama: Which Model Wins for Devs (dev.to)
134. “最后的开发者博物馆”：从 Stack Overflow 到人工智能 05-16 The Last Developer Museum: From Stack Overflow to AI (dev.to)
136. 我在 Gemma 4 中添加了三条规则。MoE 进行了搜索。Dense 模型拒绝了。 05-16 I Added Three Rules to Gemma 4. The MoE Searched. The Dense Model Refused. (dev.to)
137. 永无止境的AI代码审查：为何一次审查远远不够 05-16 The Never‑Ending AI Code Review: Why One Pass Isn’t Enough (dev.to)
139. 别再凭感觉来评估你的代理技能了。消除上下文安全风险。 05-15 Stop trusting your agent skills with vibes. Eliminate the context security risk. (dev.to)
142. OpenSEO 在 GitHub 上获得了 1.7k 个星标。我只花了 0 美元就实现了同样的功能。 05-12 OpenSEO Has 1.7k GitHub Stars. I Built the Same Thing for 0. (dev.to)
143. 通过聊天功能，创建并安排您专属的Hacker News邮件摘要吧！ 04-19 Chat to build and schedule your own personal Hacker News email digest! (dev.to)
145. 低质量的AI内容比比皆是。以下是我反复思考的观点。 05-15 AI slop is everywhere. Here''s what I keep coming back to. (dev.to)
146. 构建“Sweets Vault”——一款集成物理硬件的多模态Gemini代理 05-15 Building "Sweets Vault" - a multimodal Gemini Agent with physical hardware integration (dev.to)
147. 更大的AI模型并不一定更好。以下是实际选择的方法。 05-16 Bigger AI models aren''t always better. Here''s how to actually choose. (dev.to)
150. #100DaysOfCode 第99天 — DevCollab：部署 Next.js 并上线 05-14 Day 99 of #100DaysOfCode — DevCollab: Deploying Next.js and Going Live (dev.to)
151. 您的软件包比《雷神之锤》大4000倍。通过9个步骤的审核即可解决此问题。 05-14 Your bundle is 4000x bigger than Quake. The 9-step audit that fixes it. (dev.to)
154. 我让 Cursor 重命名了一个函数。它发送了 8,400 个代币。我确认了一下。 05-07 I asked Cursor to rename a function. It sent 8,400 tokens. I checked. (dev.to)
155. 人工智能可以编写代码，但它仍然会忽略那些关键的决策。 05-15 AI Can Write the Code. It Still Forgets the Decisions That Matter. (dev.to)
156. 人工智能并没有让软件工程变得更简单，反而让其中的难点变得更加棘手。 05-12 AI Didn''t Make Software Engineering Easier. It Made the Hard Parts Harder. (dev.to)
157. 全新的 AWS 代理工具包包含 20 多种代理技能，但如果没有这个文件，您的代理可能永远无法加载它们 05-14 The new Agent Toolkit for AWS includes 20 agent skills, but your agent might never load them without this one file (dev.to)
158. 我如何借助人工智能助手在4天内完成整个产品的文档编写 05-14 How I Documented an Entire Product in 4 Days with an AI Agent (dev.to)
159. 使用 Veo 3.1 和 NanoBanana 2 制作完美正方形 AI 视频 05-13 Hacking perfectly square AI videos with Veo 3.1 and NanoBanana 2 (dev.to)
160. PHP 与 Node.js 对比，Next.js 与 Angular 对比：该学什么 05-15 PHP vs Node.js & Next.js vs Angular: What to Learn (dev.to)
161. 老旧电脑 vs 新型AI：2015年的台式机真的能运行Gemma 4吗？（2B vs 4B 性能测试） 05-10 Old PC vs New AI: Can a 2015 Desktop Actually Run Gemma 4? (2B vs 4B Benchmark) (dev.to)
163. Lambda 刚刚有了文件系统。我在上面部署了 AI 代理。 05-13 Lambda Just Got a File System. I Put AI Agents on It. (dev.to)
164. 我的 GitHub 坟场里有 27 个已废弃的项目。以下是关于原因的残酷真相。 05-14 My GitHub Graveyard has 27 dead projects. Here is the brutal truth about why. (dev.to)
165. 本地优先的人工智能实践范例：Gemma 4 E2B 与“思考模式”如何赋能 DiagramFlowAI 05-13 Local-First AI Done Right: How Gemma 4 E2B and ''Thinking Mode'' Powered DiagramFlowAI (dev.to)
167. 职业倦怠的真实感受（而非Instagram上所描述的那样） 05-13 What Burnout Actually Feels Like (Not What Instagram Tells You) (dev.to)
168. 从第600万名到第2.6万名：1.5年、1040道LeetCode题目，以及一个改变一切的惊喜包裹 05-06 From Rank 6,000,000 to 26,000: 1.5 Years, 1040 LeetCode Problems, and a Surprise Package That Changed Everything (dev.to)
169. React 过于复杂：为何 Python HTMX 将在 2026 年占据主导地位 05-13 React is Overkill: Why Python HTMX is Dominating in 2026 (dev.to)
170. 两位开发者。两个国家。一个古怪的小头像项目。 05-13 Two DEV Users. Two Countries. One Weird Little Avatar Project. (dev.to)
173. Open Vibe——借助人工智能发布您的SaaS产品，畅通无阻。 05-12 Open Vibe -- Ship your SaaS with AI. Without getting stuck. (dev.to)
174. 语言之战已落幕。当你未曾察觉时，局势已然发生转变。 05-08 The Language Wars Are Over. The Ground Shifted Without You. (dev.to)
175. 我不再抗拒 React 服务器组件了——这才是最终让我接受它的原因 05-12 I Stopped Fighting React Server Components — Here''s What Finally Made It (dev.to)
177. “见效快”背后的隐性代价：为何速效方案会损害长期速度 04-29 The Hidden Cost of "It Works": Why Quick Fixes Kill Long-Term Speed (dev.to)
178. 《提示工程师生存指南：AI无法取代的技能》 05-12 The Prompt Engineer''s Survival Guide: Skills That AI Can''t Replace (dev.to)
179. 我正准备重写我的聊天路由器。结果发现，问题出在提示信息里的两行代码上。 05-12 I Was About to Rewrite My Chat Router. The Bug Was Two Lines in a Prompt. (dev.to)
180. 您的 AWS 账单在误导您——它显示的是服务，而非功能 05-11 Your AWS bill is lying to you — it shows services, not features (dev.to)
182. 使用 Docker Model Runner 免费在本地运行 Claude Code 05-12 Run Claude Code Locally for Free with Docker Model Runner (dev.to)
183. 我测试了PaioClaw——当我将其推向极限时发生了什么 05-11 I Tested PaioClaw — Here''s What Happened When I Pushed It to Its Limits (dev.to)
186. 我如何不再为后院的乱象感到绝望，并开启了一个AI副业项目 05-11 How I Stopped Despairing Over the Backyard Mess and Started an AI Side Project (dev.to)
187. 我在11.8万颗真实恒星中定位了Gemma 4——它能做什么 05-10 I Grounded Gemma 4 in 118,000 Real Stars — Here''s What It Can Do (dev.to)
189. 如何保障生产环境中AI代理的安全：MCP的正确之处（及其不足） 05-05 How to Secure AI Agents in Production: What MCP Gets Right (and What It Doesn’t) (dev.to)
192. 我用GTX 1650测试了所有Gemma 4型号。以下是实际测试结果。 05-11 I Tested Every Gemma 4 Model on a GTX 1650. Here''s What Actually Happened. (dev.to)
195. 使用 Gemma 26B MoE、.NET 8、Python 和 React 构建人工智能驱动的 ERP 系统 05-09 Building an AI-Powered ERP System with Gemma 26B MoE, .NET 8, Python & React (dev.to)
197. 当你第一次看到人工智能代理进行购物时，你会产生一种难以言喻的感觉。 05-07 The first time you watch an AI agent buy something, you will feel something you cannot name. (dev.to)
198. 在生产环境中使用 InversifyJS 三年后，我已经受够了，于是我开发了一个更好的依赖注入容器 05-11 I was sick of InversifyJS after 3 years in production, so I built a better DI container (dev.to)
200. 诊断结果并未改变我的领导风格，真正改变我的，是主动担当。 05-10 Diagnosis Didn''t Change My Leadership. Ownership Did. (dev.to)
201. 作为一名MCA三年级学生，我是如何入选2026年谷歌夏季编程大赛（GSoC）的 05-10 How I Got Into Google Summer of Code (GSoC) 2026 as a Tier-3 MCA Student (dev.to)
203. 《与克劳德编程：扩展版》：太棒了！等等，什么？ 05-10 Code with Claude Extended SF: Heck yeah and then wait, what? (dev.to)
204. 别再手动绘制骨架了。让您的 UI 像魔法一样自动生成骨架。 05-09 Stop hand-drawing skeletons. Let your UI trace itself magically. (dev.to)
205. @supports 谎言：当 CSS 说“是”，浏览器却说“哈哈，才怪” 05-09 @supports Lies: When CSS Says ''Yes'' but Browsers Say ''LOL No'' (dev.to)
206. Gemma 4 有四款机型。以下是您真正需要的那个 05-08 Gemma 4 Has Four Models. Here''s Which One You Actually Need (dev.to)
207. 如何找到规划器从未选中的 Postgres 索引（我在 51 个中发现了 20 个） 05-09 How to Find the Postgres Indexes Your Planner Never Picks (I Found 20 of 51) (dev.to)
208. Python 的 GIL 究竟是如何工作的（以及何时会给你带来麻烦） 05-10 How Python''s GIL actually works (and when it bites you) (dev.to)
209. 我开发了一个 Ruby gem，这样我就不用再眯着眼睛看哈希转储了 05-08 I built a Ruby gem so I don''t have to squint at hash dumps anymore (dev.to)
210. 每个开发者的 Git 日志都是一处犯罪现场——七步调查法 05-04 Every Developer''s Git Log is a Crime Scene - A 7-Stage Investigation (dev.to)
211. 永不停歇的本地模型：Gemma 4 与 MTP 作为马拉松引擎 05-07 The Local Model That Doesn''t Sleep: Gemma 4 MTP as a Marathon Engine (dev.to)
213. 使用 Terraform 和 Cloud Run 部署多代理系统 05-02 Deploying a Multi-Agent System with Terraform and Cloud Run (dev.to)
215. [GCP 实践][BwAI] 人工智能驱动的开发：使用 Gemini CLI 快速部署 LINE 机器人云备份工具 05-05 [GCP Practice][BwAI] AI-Powered Development: Quickly Deploy a LINE Bot Cloud Backup Tool with Gemini CLI (dev.to)
217. 为什么我不让 AI 处理我的滚动动画：Astro、React 和 TypeScript 架构 05-06 Why I Didn’t Let AI Handle My Scroll Animation: Astro, React, and TypeScript Architecture (dev.to)
218. 黑客马拉松如何教会新手开发者那些一年教程也无法传授的知识 05-08 How a Hackathon Will Teach a New Developer What a Year of Tutorials Can''t (dev.to)
224. 我用 TypeScript 编写了一个仅 200 行代码的 AI 路由器。我的月账单减少了 41%。 05-07 I built a 200 line AI router in TypeScript. My monthly bill dropped 41%. (dev.to)
226. 我用75美元的树莓派取代了500美元的显卡：Gemma 4如何让计算机视觉成本降低10倍 05-06 I Replaced My 500 GPU with a 75 Raspberry Pi: How Gemma 4 Makes Computer Vision 10x Cheaper (dev.to)
230. 祝贺 Google Cloud NEXT ''26 写作挑战赛的获奖者！ 05-07 Congrats to the Google Cloud NEXT ''26 Writing Challenge Winners! (dev.to)
232. Amazon Bedrock AgentCore Harness 负责运行您的代理。ShapeV2 则控制其被允许执行的操作 05-06 Amazon Bedrock AgentCore Harness runs your agent. ShapeV2 controls what it''s allowed to do (dev.to)
236. 打造专属AI管家——一个能自动运行的定时代理！ 05-06 Build Your Own AI Butler - A Scheduled Agent That Runs Itself! (dev.to)
238. 加入“Gemma 4 挑战赛”：总奖金 3,000 美元，将有十位获奖者！ 04-30 Join the Gemma 4 Challenge: 3,000 prize pool for TEN winners! (dev.to)
241. 请停止这样使用 useEffect：5 种正在悄无声息地破坏你的 React 应用的模式 04-29 Stop Using useEffect Like This: 5 Patterns That Are Silently Breaking Your React App (dev.to)
242. 我们将全力支持您（AI Avatar v7：姿势捕捉及其他功能（VS Code 和 Chrome 扩展程序）） 05-03 We''ll Support You with All Our Might (AI Avatar v7: Pose Capture and More (VS Code and Chrome Extension)) (dev.to)
246. 人工智能到底是什么？（我休息了一段时间，结果不得不重新学习一切） 05-06 What Even Is AI? (I Took a Break & Had to Relearn Everything) (dev.to)
248. 基于 Gemini API 文件搜索工具的多模态 RAG：开发者指南 05-05 Multimodal RAG with the Gemini API File Search Tool: A Developer Guide (dev.to)
249. 面向人工智能编程时代的VR编程——同时监控5个AI代理 05-05 VR Coding for the AI Coding Era - Monitoring 5 AI Agents at Once (dev.to)
250. 使用 Angular 和 Signals 构建流式 Gemini 聊天应用——然后将其部署到 Cloud Run 05-02 Build a Streaming Gemini Chat in Angular with Signals — Then Ship It on Cloud Run (dev.to)
251. 开发阿兹拉：别让她发现你：我的游戏开发历程中的启示 05-05 Working on Azirah: Don’t Let Her See You: Lessons from My Game Development Journey (dev.to)
253. 我分别在文档、PDF 和代码上测试了分块处理。结果每次都不一样。 05-05 I Tested Chunking on Docs, PDFs, and Code. The Winner Changed Every Time. (dev.to)
254. 2026年真实存在的6款代理网关平台（及其优势） 05-04 6 Agent Gateway Platforms That Actually Exist in 2026 (And What They''re Good For) (dev.to)
255. 大规模管理 150 多种 AI 代理技能——哪些出了问题，我又构建了什么 05-04 Managing 150 AI Agent Skills at Scale — What Broke, What I Built (dev.to)
256. 我们发布的代码比以往任何时候都多，但我们对其中内容的理解却越来越少。 05-03 We''re Shipping More Code Than Ever. We Understand Less of It. (dev.to)
257. 如何在 Cloud Run 上构建自定义 AI 质量检查（从零开始到投入生产） 04-28 How to Build a Custom AI Quality Gate on Cloud Run (From Zero to Production) (dev.to)
258. [Google Cloud Next ''26 回顾 #3] Anthropic 对“后软件时代”的展望 05-04 [Google Cloud Next ''26 Recap #3] Anthropic''s Vision for "After Software" (dev.to)
259. 一位领英招聘人员向我发送了伪装成“面试前代码审查”的恶意软件 05-04 A LinkedIn Recruiter Sent Me Malware Disguised as a "Pre-Interview Code Review" (dev.to)
260. 将 pytest 风格的测试环境引入 Ruby，实现更智能的浏览器测试 05-04 Introducing pytest-style fixtures into Ruby for smarter browser testing (dev.to)
261. 从 Astro 5 迁移到 Astro 6：实战指南 05-03 Migrating from Astro 5 to Astro 6: A Real-World Breakdown (dev.to)
262. 我花了3天时间开发了一个移动应用。最难的部分是保持其网络连接。 05-04 I Built a Mobile App in 3 Days. The Hard Part Was Keeping It Connected. (dev.to)
263. AI 代理与代码漏洞：Anthropic Mythos 究竟是大事一桩，还是危言耸听？ 05-02 AI Agents vs Code Vulnerabilities: Was Anthropic Mythos a Big Deal or Fear-mongering? (dev.to)
267. 我开发了一款无需注册即可使用的免费发票生成器、简历生成器和求职信生成器 05-03 I Built a Free Invoice Generator, Resume Builder, and Cover Letter Generator That Don''t Require Signup (dev.to)
270. 我如何用 Python 构建了一个离线 AI 助手——不依赖 OpenAI、LangChain 及任何其他依赖项 05-03 How I Built an Offline AI Assistant in Python - No OpenAI, No LangChain, No Dependencies (dev.to)
271. AI 删除了我的测试，还说“所有测试均通过”——将“typia”从 TypeScript 移植到 Go 时的一段恐怖经历 05-03 AI Deleted My Tests and Said ''All Tests Pass'' — A Horror Story from Porting ''typia'' from TypeScript to Go (dev.to)
272. 我无意中写了一个文件系统驱动程序。给浏览器用的。 05-03 I Accidentally Wrote a Filesystem Driver. For a Browser. (dev.to)
273. 我开发了一款能够检测多个搜索引擎中SEO中毒现象的工具 05-03 I Built a Tool That Detects SEO Poisoning Across Multiple Search Engines (dev.to)
276. 我那位法学硕士助手的最新流行语是，在回复开头总爱说“坦率地说”。听着真让人不舒服。 05-01 My LLM assistant''s new buzzword is starting responses with "be completely candid". Very grating. (dev.to)
277. 我用JAX重构了Karpathy的NanoChat。以下是XLA做对的地方，以及它彻底搞错的地方。 05-01 I Rebuilt Karpathy''s NanoChat in JAX. Here''s What XLA Gets Right and What It Gets Dead Wrong. (dev.to)
278. GitHub 搞砸了 Git：那个悄无声息删除了你代码的合并队列漏洞 05-03 GitHub Broke Git: The Merge Queue Bug That Silently Deleted Your Code (dev.to)
279. 我是如何构建 TypeScript 中最快的颜色处理库的，以及我学到的优化技巧 05-01 How I built the fastest color manipulation library in TypeScript and the optimization techniques I learned (dev.to)
282. 函数调用框架 2：CoT 合规率从 9.91% 提升至 100% 04-30 Function Calling Harness 2: CoT Compliance from 9.91% to 100% (dev.to)
283. 编写易于删除的代码：无常软件的艺术 05-02 Write Code That''s Easy to Delete: The Art of Impermanent Software (dev.to)
284. 《AI Harness：为何你的AI编程助手只能像你放置它的代码仓库那样聪明》 05-02 The AI Harness: why your AI coding agent is only as smart as the repo you put it in (dev.to)
288. 我做了一切人工智能时代要求我做的事，但生活费还是付不起。 04-28 I Did Everything the AI Era Asked. It Still Didn''t Pay My Bills. (dev.to)
290. 人们曾说人工智能会淘汰SaaS的模板化内容。但事实恰恰相反。 04-30 They said AI Would Kill SaaS Boilerplates. It''s Doing the Opposite. (dev.to)
292. AI代码审查的5个层次——从“兄弟，相信我”到“生产就绪” 04-30 5 Levels of AI Code Review — From ''Trust Me Bro'' to Production Ready (dev.to)
294. 如今，代理程序正在构建自己的用户界面。以下是值得这样做的场景。 04-30 Agents are building their own UIs now. Here''s when that''s worth doing. (dev.to)
295. “DEV Weekend挑战赛：地球日特辑”获奖名单揭晓 05-01 Announcing the Winners of the DEV Weekend Challenge: Earth Day Edition (dev.to)
296. Google Cloud TPU 上的 vLLM：模型规模与芯片性能速查表（附交互式工具） 04-30 vLLM on Google Cloud TPU: A Model Size vs Chip Cheat Sheet (With Interactive Tool) (dev.to)
297. 大家都在谈论Gemini。但Google Cloud NEXT ''26大会上的真正焦点其实是GKE Agent Sandbox。 04-29 Everyone''s Talking About Gemini. The Real Story at Google Cloud NEXT ''26 Was GKE Agent Sandbox. (dev.to)
298. 我妻子说服我，终于把我们用了好几年的这款应用发布出来了 04-29 My wife convinced me to finally ship the app we’ve been using for years (dev.to)
299. OpenAI 会告诉你花了多少钱，但不会告诉你花在了哪里。所以我开发了一个仪表盘。 04-30 OpenAI Tells You What You Spent. Not Where. So I Built a Dashboard. (dev.to)