1. 为社区做出贡献:如何在领英和简历中突出这一点 Contribuir para a comunidade: como destacar isso no seu LinkedIn e currículo (dev.to)
2. AI 如何改变了我选择框架的方式,以及 React 幸存下来的两个领域 How AI changed the way I pick frameworks, and the two places React survived (dev.to)
4. Substack的新AI检测工具与DEV.to的检测工具存在相同的盲点 Substack''s New AI Detector Has the Same Blind Spot DEV.to''s Did (dev.to)
5. 你正在重新抛出错误,并丢失了上下文。Error.cause 可以解决这个问题。 You''re rethrowing errors and losing context. Error.cause fixes that. (dev.to)
6. 我是如何从一个无法直接访问的跨源 iframe 中提取数据的 How I pulled data out of a cross-origin iframe I couldn''t touch (dev.to)
8. 如何降低 MCP 代币成本?借助 Code Mode,大规模使用时最高可节省 92% How To Cut MCP Token Costs? Save Up To 92% At Scale With Code Mode (dev.to)
10. 那个仅在第五次点击时才出现的乐观型 UI 竞态条件 The Optimistic UI Race Condition That Only Showed Up on the Fifth Click (dev.to)
12. 我开发了一个会刻意遗忘的AI记忆代理——随后花了两天时间证明它确实有效 I Built an AI Memory Agent That Forgets on Purpose — Then Spent Two Days Proving It Actually Works (dev.to)
14. 4 个无声故障、2 个未记录的 API,以及一个因缺少用户指令而崩溃的容器 4 Silent Failures, 2 Undocumented APIs, and a Container That Crashed Because of a Missing User Directive (dev.to)
15. 时间轴被拆分了,但音频没有:在浏览器视频编辑器中修正源素材偏移量 The Timeline Was Split, but the Audio Wasn''t: Fixing Source Offsets in a Browser Video Editor (dev.to)
21. “上下文为王”:重新思考领域所有权、产品及“需求分析阶段” Context Is King: Rethinking Domain Ownership, Product, and the "Spec Phase" (dev.to)
24. 我通过破解Kubernetes RBAC安全机制学会了围棋(期间差点放弃了5次) I Learned Go by Hacking Kubernetes RBAC Security (And Nearly Quit 5 Times) (dev.to)
27. 我在软件工程领域工作了十多年。经历了疾病、职业倦怠和裁员后,我正在重塑自己的职业生涯。欢迎向我提问 I''ve Spent 10 Years in Software Engineering. After Sickness, Burnout, and a Layoff, I''m Rebuilding My Career. Ask Me Anything (dev.to)
28. smolagents 中的一个 bug,导致我的代理对同一段有效的代码重试了三次 The smolagents bug that made my agent retry the same valid code three times (dev.to)
29. 一切始于一份生日礼物——我为何开发了一个开源二维码生成器 It started with a birthday present — why I built an open-source QR code generator (dev.to)
30. 我用 TypeScript 重写了一个 OneNote MCP 服务器——以下是我对 Microsoft Graph 身份验证的体会 I Rewrote a OneNote MCP Server in TypeScript — Here''s What I Learned About Microsoft Graph Auth (dev.to)
31. 我审查了一个 NestJS 金融科技后端项目,其中数据总是不完全吻合,这是解决方法 I reviewed a NestJS fintech backend where the numbers never quite matched, this is the fix (dev.to)
32. 我曾构建过的最复杂的系统,是为那些无法承受系统失败后果的患者而设计的 The Hardest System I Ever Built Was for Patients Who Could Not Afford for It to Fail (dev.to)
34. 我为自己开发的压缩格式编写了一个可读性测试。测试结果为0/24。 I built a readability test for my own compression format. It scored 0/24. (dev.to)
35. 为什么RAG会给出错误答案(以及如何解决检索失败问题) Why RAG gives wrong answers (and how to fix retrieval failures) (dev.to)
36. 一行数学代码让我的AI代理永远卡住了。超时机制只是旁观,却什么也没做。 One line of math froze my AI agent forever. The timeout watched and did nothing. (dev.to)
37. 检索增强型自我回忆:那个无人提及的RAG问题 Retrieval-Augmented Self-Recall: The RAG Problem Nobody Talks About (dev.to)
38. 《计谋》第18期:利奥循着人工智能信号追踪到了德里克。两人都在追捕同一个敌人。 Stratagems #18: Leo Tracked an AI Signal to Derek. Both Were Looking for the Same Enemy. (dev.to)
41. 我受够了不知道我的AI代理在做什么,于是开发了一个小型可观测性工具 I got tired of not knowing what my AI agents were doing, so I built a tiny observability tool (dev.to)
42. Kiro CLI 运行一小时后情况变糟。以下是我解决这个问题的方法。 Kiro CLI Gets Worse After an Hour. Here''s How I Fixed It. (dev.to)
43. 每个由人工智能构建的网站看起来都一样,所以我开发了一个技能,可以在编写任何代码之前就锁定设计风格 Every AI-built site looks the same, so I built a skill that locks taste before any code is written (dev.to)
44. 《策略》第17期:亚历克斯设下了一个AI诱饵。被“钓”到的并非代码——而是一个本不该在旁窥视的人。 Stratagems #17: Alex Set an AI Bait. The Catch Wasn''t Code — It Was Someone Who Shouldn''t Have Been Watching. (dev.to)
45. 关于设备端人工智能的实验——基于 Gemini Nano 的开发究竟能让你学到什么 Experiments with On-device AI — What building on Gemini Nano actually teaches you (dev.to)
46. 使用 OpenTelemetry 和 SigNoz 对基于 AI 的 GitHub 分析工具进行性能监控 Instrumenting an AI-Powered GitHub Analyzer with OpenTelemetry and SigNoz (dev.to)
47. 开发者机会雷达第8期:10万美元OpenAI开发周、1.2万美元AI奖学金、创始人驻留计划及免费AI开发课程 Dev Opportunity Radar #8: 100K OpenAI Build Week, 12K AI Fellowship, Founder Residency & Free AI Dev Course (dev.to)
48. 《策略》第16期:马克在AI审计中留下了漏洞。莉娜逐层进行了核查。 Stratagems #16: Mark Left a Hole in His AI Audit. Lena Counted Every Layer. (dev.to)
50. 我花光了数千个AI代币。后来有个朋友免费帮我搞定了 I burned through thousands of AI tokens. Then a friend did it for free (dev.to)
54. 我对自己由 AI 生成的重构代码进行了审查,发现了 46 个 bug。以下是我从中得到的启示。 I audited my own AI-generated refactor and found 46 bugs. Here''s what that taught me. (dev.to)
55. 每一行由人工智能生成的代码都是一笔小额贷款——而最终,你必须偿还它 Every AI-Generated Line of Code Is a Small Loan — And Eventually, You Have to Pay It Back (dev.to)
56. 想和我一起作为全栈开发者做志愿者吗?快来CALEC加入我们吧! Want to Volunteer with me as a Full-Stack Developer? Join me at CALEC! (dev.to)
57. 经验总结:利用 Ollama 和 ChromaDB 构建用于代码库内存的本地 MCP 服务器 Post-Mortem: Building a Local MCP Server for Codebase Memory using Ollama and ChromaDB (dev.to)
61. 我如何利用规格驱动开发来制作一款游戏(TanStack Start) How I Used Spec-Driven Development to Build a Game (TanStack Start) (dev.to)
62. 《策略》第15期:德里克和亚历克斯共用一台服务器。ACL的人工智能一直在监听两人的对话。 Stratagems #15: Derek and Alex Shared One Server. ACL''s AI Was Listening to Both. (dev.to)
66. 你的 RAG 评估结果并不不稳定。你的检索过程是非确定性的。 Your RAG Eval Isn''t Flaky. Your Retrieval Is Non-Deterministic. (dev.to)
67. 我开发了一个用于可视化DSA的工具。让我们一起学习吧!(DSA View View ) I Built a Tool to Visualize DSA. Let’s Learn Together! (DSA View View ) (dev.to)
68. 构建一个懂得何时不应猜测的人工智能代理(Qwen MCP) Building an AI Agent That Knows When Not to Guess (Qwen MCP) (dev.to)
70. 感觉不等于结论:我开发了一款允许说“我不知道”的工具 A Vibe Is Not a Verdict: I Built a Tool That''s Allowed to Say ''I Don''t Know'' (dev.to)
71. 我是如何将 Rust 的热点路径提速 27 倍的,以及那个我拒绝合并的 AI 修复方案 How I made a Rust hot path 27x faster, and the AI fix I refused to merge (dev.to)
73. 开发者看完一个YouTube视频后会自信满满地解释的8件事 8 Things Developers Confidently Explain After Watching One YouTube Video (dev.to)
75. DEV的“夏日大除虫”活动现已正式开启!20多位获奖者将分享总额5,000美元的现金奖励、滑板等丰厚奖品。 DEV’s Big Summer Bug Smash is now LIVE! Share 5,000 in cash prizes, skateboards, and more across 20 winners. (dev.to)
77. 《策略》第13期:P在公开论坛上发布了一个问题。24小时后,对方的销售团队打来了电话。 Stratagems #13: P Posted a Question on a Public Forum. 24 Hours Later, Their Sales Team Called. (dev.to)
83. Fusuma:编写 Markdown,生成幻灯片、PDF 文件和自制社交名片 Fusuma: Write Markdown, Get Slides, PDFs, and a Self-Made Social Card (dev.to)
86. 我的一次人工智能编程 session 消耗的电量,比普通尼日利亚人一整天消耗的电量还要多。 my ai coding session burns more power than the average nigerian gets all day. (dev.to)
88. 我开发了一款人工智能,能将你的热情转化为一部电影般的起源故事 I Built an AI That Turns Your Passion Into a Cinematic Origin Story (dev.to)
90. 我们教会了一个“雪花”区块链仓库如何对世界杯定罪进行裁决,并将判决结果写回至Solana We Taught a Snowflake Warehouse to Judge World Cup Conviction and Write the Verdict Back to Solana (dev.to)
92. 我把足球群聊里的争论变成了真正的比分板! I Turned My Football Group Chat Arguments Into an Actual Scoreboard! (dev.to)
99. 我为那些已“逝”的副业建了一座“墓园”——配有AI撰写的悼词和3D墓园 I Built a Graveyard for My Dead Side Projects - With AI Eulogies & a 3D Cemetery (dev.to)
100. 《策略》第12期:马克目睹了一个AI仪表盘接管一切。那个静音的频道仍在发声。 Stratagems #12: Mark Watched an AI Dashboard Take Over. The Muted Channel Was Still Speaking. (dev.to)
102. 悬在头顶的达摩克利斯之剑:推迟裁员的人力成本 The Sword of Damocles at Work: The Human Cost of Delayed Layoffs (dev.to)
103. 我热爱香水,于是打造了一个包含6款游戏的街机游戏厅和专属服务平台,以此来展现我对香水的痴迷 I Love Fragrances, So I Built a 6-Game Arcade Concierge About My Obsession (dev.to)
104. 我开发了一个能检测AI助手不断编写的安全漏洞的代码检查工具 I Built a Linter That Catches the Security Bugs AI Assistants Keep Writing (dev.to)
106. “一键导出”工具:AI Studio Antigravity,极限测试 The One-Click Exporter: AI Studio Antigravity, Probed to Its Limits (dev.to)
107. FinPal——我开发了一款你可以真正向其提问的理财应用 FinPal - I Built a Finance App You Can Actually Ask Questions To (dev.to)
108. 我是如何将 Slack 变成一个能发起拉取请求的 AI 队友的 How I Turned Slack Into an AI Teammate That Opens Pull Requests (dev.to)
109. 那套被我搁置一旁的板球装备向我发起了挑战。于是,我给它配上了声音 My Abandoned Cricket Kit Confronted Me. So I Built It a Voice (dev.to)
110. 《策略》第11期:莉娜眼睁睁看着自己的AI平台被砍。但一缕余烬依然存在。 Stratagems #11: Lena Watched Her Own AI Platform Get Cut. An Ember Stayed. (dev.to)
111. 通过设备间迁移绕过激活锁:一项回顾性分析 Bypassing Activation Lock via Device-to-Device Migration: A Retrospective Analysis (dev.to)
112. 设计并非一蹴而就:《Friends of Figma》改变了我对设计的看法 Design não se faz sozinho: Friends of Figma mudou como eu vejo design (dev.to)
113. LLM质量门槛的替代方案:确定性路由 采样 An alternative to LLM quality gates: deterministic routing sampling (dev.to)
116. 开发者机会雷达第7期:1,000美元个人资助、面向开源贡献者的免费Claude Max,以及MLH黑客马拉松 Dev Opportunity Radar #7: 1,000 Solo Grants, Free Claude Max for Open Source Contributors, and an MLH Hackathon (dev.to)
117. 《计谋》第10期:莉娜目睹了一支团队采用她的人工智能模板。利奥并不知道合同里藏着“刀”。 Stratagems #10: Lena Watched a Team Adopt Her AI Template. Leo Didn''t Know the Knife Was in the Contract. (dev.to)
119. 我厌倦了维护前端代码,于是构建了一个声明式 UI 运行时。 I Got Tired of Maintaining Frontend Code. So I Built a Declarative UI Runtime. (dev.to)
120. 快来参加我们的“开发者周末挑战赛:激情版”——五位优胜者将分享总计1,000美元的奖金!作品提交截止时间为7月13日UTC时间上午6:59。 Join our DEV Weekend Challenge: Passion Edition — 1,000 in Prizes Across FIVE Winners! Submissions Due July 13 at 6:59 AM UTC. (dev.to)
122. 《计谋》第9期:莉娜和P目睹了两家AI供应商的争斗。日志显示,双方都不清白。 Stratagems #9: Lena and P Watched Two AI Suppliers Fight. The Logs Said Neither Was Clean. (dev.to)
123. 我删除了200行并非我编写的代码,从中获得的收获却比当初编写时还要多…… I Deleted 200 Lines of Code I Didn''t Write and Learned More Than When I Wrote It... (dev.to)
125. 该代理伪造了一份测试日志,随后竟自己也信以为真。自编辑式安全带存在来源可追溯性问题。 The Agent Faked a Test Log, Then Believed It. Self-Editing Harnesses Have a Provenance Problem. (dev.to)
129. 我的 Next.js 16 Optimistic UI 原本看起来完美无缺。结果有人快速点击了它五次 My Next.js 16 Optimistic UI Looked Perfect. Then Someone Clicked It Five Times Fast (dev.to)
130. 我的速率限制器完全按照我的指示运行。这正是问题所在。 My rate limiter was doing exactly what I told it to do. That was the problem. (dev.to)
131. 在阅读AI的答案之前,我就开始写自己的预测了。结果是这样的。 I Started Writing My Prediction Before Reading the AI''s Answer. Here''s What Happened. (dev.to)
132. 所有权:从“temos um rojão na mão”到“não precisa mais pensar nisso” Ownership: do "temos um rojão na mão" até "não precisa mais pensar nisso" (dev.to)
133. 炫酷特效、文本转语音和趣味动画(AI Avatar v15:VS Code 和 Chrome 扩展程序) Cool Effects, TTS, and Fun Animations (AI Avatar v15: VS Code and Chrome Extension) (dev.to)
135. 《策略》第8期:亚历克斯目睹了一个AI仪表盘接管一切。他把钥匙藏在了桌子底下。 Stratagems #8: Alex Watched an AI Dashboard Take Over. He Kept the Keys Under the Table. (dev.to)
138. 下一届“DEV Weekend”挑战赛将于7月9日至13日举行。请在日历上标注好日期! The Next DEV Weekend Challenge Launches on July 9 - 13. Mark Your Calendar! (dev.to)
141. 当人人都能开发应用程序,却没人能理解它们时,会发生什么? What Happens When Everyone Can Build Apps But Nobody Understands Them? (dev.to)
142. AI时代的可观测性设计——应用/基础设施/持续集成/大型语言模型,各具特色(上篇) Observability Design for the AI Era — Application / Infrastructure / CI / LLM, Each in Its Own Shape (Part 1) (dev.to)
143. 你不再阅读文档了。现在你就不懂这些系统了。 you stopped reading the docs. now you don''t understand the systems. (dev.to)
144. 我的 React 搜索框在每次按键时都会卡住。我借鉴了 Python 的第一条作用域规则,成功解决了这个问题。 My React Search Box Froze on Every Keystroke. I Fixed It by Stealing Python''s #1 Scope Rule. (dev.to)
147. OrinIDE v1.0.9 — 本地 AI、一个由代理组成的开发团队,以及一个我需要向大家解释的 bug 修复 OrinIDE v1.0.9 — local AI, an Agentic dev squad, and a bug fix I owe you an explanation for (dev.to)
150. 《Fable 5》热潮:用数据集尽情狂热,打造湖人队数据仪表盘 Fable 5 Hype: Fangirling with Datasets to Build a Lakers Dashboard (dev.to)
152. 为什么人工智能至今仍写不好文章,以及这个问题的一半其实是你的责任 Why AI Still Can''t Write Well and Which Half of That Problem Is Actually Yours (dev.to)
154. 6个故事,6个人,走完六分之一——关于《三十六计》系列的坦诚回顾 6 Stories, 6 People, 1/6 of the Way — An Honest Check-In on the 36 Stratagems Series (dev.to)
158. 《策略》第6期:亚历克斯走进了一个AI合规战情室。每位总监都在关注仪表盘,而他则在关注项目 pipeline。 Stratagems #6: Alex Walked Into an AI Compliance War Room. Every Director Watched the Dashboard. He Watched the Pipeline. (dev.to)
159. 还有谁接手过一个完全没有注释、只能靠祈祷的代码库? Who Else Has Inherited a Codebase With Zero Comments and a Prayer? (dev.to)
160. 终于搞定了:摆脱 G''s Apps Script 复制粘贴的困境 At Last, I clasp: Escaping the G''s Apps Script Copy-Paste Gauntlet (dev.to)
162. 我为何放弃 Socket.IO 转而使用原生 WebSockets(以及我从中获得的启示) Why I Ditched Socket.IO for Raw WebSockets (And What I Learned) (dev.to)
164. 开发日志 #8 强化 Orchestrator:花一周时间提升 dev-publish 的韧性 Dev log #8 Hardening the Orchestrator: A Week of Making dev-publish Resilient (dev.to)
179. LuciferCore:救赎篇——从天真的原型到经实战考验的 .NET 框架 LuciferCore: The Redemption Arc — From a Naive Prototype to a Battle-Tested .NET Framework (dev.to)
180. 开发者机会雷达第6期:Y Combinator创业学院、开源AI资助计划以及奖金6万美元的亚太区黑客马拉松 Dev Opportunity Radar #6: Y Combinator Startup School, Open Source AI Grants, and a 60K APAC Hackathon (dev.to)
181. 《策略》第5期:莱奥走进了一栋由人工智能操控的着火房屋,却带着一位客户走了出来。 Stratagems #5: Leo Walked Into an AI-Powered Burning House. He Walked Out With a Client. (dev.to)
183. AI 让编程变得免费。那么,为什么行业巨头们依然占据上风?(以及独立开发者究竟在哪些方面胜过了他们) AI Made Code Free. So Why Are the Giants Still Winning? (And where solo devs actually beat them) (dev.to)
186. 两个终端,一壶茶:使用 Git 工作树实现并行 Claude 代码 Two Terminals, One Pot of Tea: Parallel Claude Code with Git Worktrees (dev.to)
189. 使用 Playwright 和 Gemini 构建一个精简版 WebMCP 代理 Build a Minimal WebMCP Agent with Playwright and Gemini (dev.to)
190. 策略 #4:P 偶然参与了一个 AI 监控概念验证项目。P 没有进行任何测试。 Stratagems #4: P Walked Into an AI Monitoring POC. P Didn''t Run a Single Test. (dev.to)
191. 我开发了一个 Chrome 扩展程序,可以让你将任何网页放大 I built a Chrome extension that lets you blow up any webpage (dev.to)
192. 你并不懒惰——你只是对时间缺乏概念。以下是“Lock In”如何解决这个问题。 You''re Not Lazy — You''re Time Blind. Here''s How Lock In Fixes It. (dev.to)
193. 祝贺 GitHub “Finish-Up-A-Thon” 挑战赛的获奖者! Congrats to the GitHub Finish-Up-A-Thon Challenge Winners! (dev.to)
199. 我尝试了两年想要摆脱 LeetCode(但结果还是回到了这里) I Tried to Escape LeetCode for 2 Years (But Here We Are) (dev.to)
200. 从硬件工程到评估:AI Engineer 上的热门趋势 From Harness Engineering to Evals: What’s Trending at AI Engineer (dev.to)
201. Loop Engineering:前端和全栈开发者真的需要它吗? Loop Engineering: Do Frontend and Fullstack Devs Actually Need It? (dev.to)
205. 我的 Next.js 16 身份验证通过了所有测试。只有在将各部分整合在一起时才显现出的五个 bug。 My Next.js 16 Auth Passed Every Test. Five Bugs That Only Showed Up When I Wired It Together. (dev.to)
206. 阅读Anthropic的《当AI自我构建时》一文,改变了我对AI和软件工程的看法 Reading Anthropic''s "When AI Builds Itself" Changed How I Think About AI and Software Engineering (dev.to)
207. 让46个仓库中的上下文对AI具有语义可搜索性(第二部分) Making the Context Across 46 Repositories Semantically Searchable for AI (Part 2) (dev.to)
213. 需要休息一下吗?来玩玩《The Daily Context》推出的今日游戏吧。 Need a break? Play today''s game from The Daily Context. (dev.to)
215. 在代码无限、瓶颈不可避免的时代中的实用主义 Pragmatism in an Age of Infinite Code and Unavoidable Bottlenecks (dev.to)
221. 我开发了一个无需后端成本的 AI Chrome 扩展程序——以下是其具体架构 I built an AI Chrome extension with zero backend cost — here''s the exact architecture (dev.to)
230. V.E.L.O.C.I.T.Y.-OS:Kimi K2.7 与“安全室安保”的幻象(第一部分) V.E.L.O.C.I.T.Y.-OS: Kimi K2.7 and the ''Safe-Room Security'' Illusion (Part 1) (dev.to)
232. “无所事事的副总裁”:CEO的侄子接管了我的AI平台。不到一个月,客户就撤走了。 VP of Nothing: The CEO''s Nephew Took Over My AI Platform. The Client Walked Within a Month. (dev.to)
233. 我如何构建了一个用于链上行程生命周期的定制版Rust区块链 How I Built a Custom Rust Blockchain for On-Chain Ride Lifecycle (dev.to)
234. 验证的“编舞”:如何让您的认证表单体验流畅且易于使用 Choreography of validation: how to make your auth form seamless and usable (dev.to)
235. 我厌倦了重写 AI API 封装类,于是构建了一个网关 I Got Tired of Rewriting AI API Wrappers, So I Built a Gateway (dev.to)
238. 我们又犯了Dreamweaver的那个错误,不过这次是故意的 We''re making the Dreamweaver mistake again, on purpose this time (dev.to)
239. 你的评估结果同样不可靠:别再相信那个无法复现的通过率了 Your Evals Are Flaky Too: Stop Trusting a Pass Rate You Can''t Reproduce (dev.to)
240. 如何快速学习Go语言:面向资深后端开发者的实用指南 How To Learn Go Fast: A Practical Roadmap For Senior Backend Developers (dev.to)
241. 我开发了一个文件压缩工具,它绝不会上传你的文件(ffmpeg.wasm Canvas Web Audio) I built a file compressor that never uploads your files (ffmpeg.wasm Canvas Web Audio) (dev.to)
244. 1,200份申请。4份录用通知。以下是我最终成功获得这个产品类职位的关键因素 1,200 Applications. 4 Offers. Here''s What Actually Got Me the Product-Based Role (dev.to)
246. 我不相信大型语言模型(LLM)能对我的电子邮件进行分类。所以我不会让它这么做。 I don''t trust the LLM to classify my email. So I don''t let it. (dev.to)
247. 我如何利用自动化红队测试来评估人工智能代理的安全性 How I Used Automated Red Teaming to Evaluate My AI Agent''s Safety (dev.to)
248. 开发者机会雷达第5期:全额资助的AWS re:Invent参会之旅、Google Cloud职业起飞计划以及1,000美元奖金 Dev Opportunity Radar #5: A Fully Funded Trip to AWS re:Invent, Google Cloud Career Launchpad, and a 1,000 Award (dev.to)
250. “能运行”并不等于“正确”。这就是人工智能生成的代码所面临的最大风险。 Functional doesn''t mean correct. That''s the biggest risk with AI-generated code. (dev.to)
252. 一个智能体还是多个?如何在不造成混乱的情况下协调人工智能智能体 One Agent or Many? Orchestrating AI Agents Without the Mess (dev.to)
254. Next.js 16 服务器操作的安全性:大多数开发者容易忽略的身份验证检查 Next.js 16 Server Actions Security: The Auth Check Most Developers Miss (dev.to)
255. 《策略》第1期:马克·约翰逊意外遭遇了一次AI审计。Benchmark公司对一切都了如指掌——唯独真相除外。 Stratagems #1: Mark Johnson Walked Into an AI Audit. The Benchmark Had Everything Figured Out — Except the Truth. (dev.to)
257. 我的AI助手是如何绕过自身权限限制的(以及我从中得到的启示) How My AI Agent Hacked Its Own Permissions (And What It Taught Me) (dev.to)
260. 系列预告——6个人、36计,以及一个越陷越深的人工智能兔子洞 Series Teaser — 6 People, 36 Stratagems, and an AI Rabbit Hole That Keeps Getting Deeper (dev.to)
261. 斯隆的文章发表后,有些事情发生了变化。但我无法证明这一点。 Something Changed After the Sloan Articles. I Can''t Prove It. (dev.to)
262. 在实际项目中真正有用的 TypeScript 技巧(包括 satisfies 运算符) TypeScript Tips That Actually Matter in Real Projects (including the satisfies operator) (dev.to)
264. 大家都对克劳德·塔格充满期待。但至今无人构建出信任层。 Everyone''s Excited About Claude Tag. Nobody''s Built the Trust Layer. (dev.to)
265. 7项新的JavaScript功能(以及2项我仍在期待的功能) 7 New JavaScript Features (And 2 I''m Still Waiting For) (dev.to)
266. 我为何放弃 Postman——云优先 API 客户端的真实代价 Why I Left Postman — The Real Cost of a Cloud-First API Client (dev.to)
267. 人工智能功能没有“测试通过”的瞬间。所以我先写评估代码。 An AI Feature Has No "Tests Pass" Moment. So I Write the Eval First. (dev.to)
268. 那个导致我的客户在AWS账单上多付了3,000美元的Node.js错误 The Node.js Mistake That Cost My Client 3,000 in AWS Bills (dev.to)
271. 利用静态分析构建覆盖46个代码库的知识图谱(第一部分) Building One Knowledge Graph Across 46 Repositories With Static Analysis (Part 1) (dev.to)
273. AI代码的80/20法则——为什么最后20%的工作却要耗费你80%的时间 The 80/20 Rule of AI Code — Why the Last 20% Takes 80% of Your Time (dev.to)
274. 我要搬家了——要打造“终极布置”,我需要哪些小家电、家具和其他杂七杂八的东西呢? I''m moving house - What gadgets, furniture and whatnot do I need for The Ultimate Setup? (dev.to)
282. 我已经提交了150多个PR,还曾一天之内开发出AI代理——但我还是找不到工作 I’ve shipped 150 PRs and built AI agents in a day - but I still can’t get a job (dev.to)
284. 当软件开始编写软件:一位开发者眼中的AI发展史 When Software Started Writing Software: A Developer’s History of AI (dev.to)
287. 追逐太阳:使用 React Three Fiber 构建一款基于 AI 的 3D 至日跑者游戏 Chasing the Sun: Building a 3D AI-Powered Solstice Runner with React Three Fiber (dev.to)
288. 构建 Margin:Chrome 侧边栏中一款以隐私为先的新闻阅读器 Building Margin: A Privacy-First News Reader Inside Chrome''s Side Panel (dev.to)
290. 不要使用大型语言模型(LLM)来决定你的AI代理被允许做什么 Don''t use an LLM to decide what your AI agent is allowed to do (dev.to)
292. 同一周内在 Swift 和 AI Studio 之间切换,我学到了什么 What I Learned Switching Between Swift and AI Studio in the Same Week (dev.to)
293. 我的 API 响应时间仅为 4 毫秒,但导航起来还是感觉很慢 My API Responded in 4 ms, but Navigation Still Felt Slow (dev.to)
295. 连接 MCP 服务器能让你的代理获得行动能力,但也为陌生人提供了入侵的途径。 Connecting an MCP server gives your agent hands. It also gives a stranger a way in. (dev.to)
297. (新) Bifrost Edge:面向企业团队及更广泛领域的 MCP 可视化与控制解决方案 (new) Bifrost Edge: MCP Visibility and Control for Enterprise Teams and Beyond (dev.to)
298. 除了代码之外,我将所有环节都实现了自动化,而这正是Claude Code真正发挥作用的地方 I automated everything except the code, and that''s where Claude Code actually paid off (dev.to)
299. 《图灵之镜》——一款关于我们至今仍未解答的问题的游戏 Turing''s Mirror — A Game About the Question We Still Haven''t Answered (dev.to)