AI 教程与实战
收录 AI 工具教程、提示词、安装部署、配置指南、开发实战与可复现步骤。
分类文章5595
当前页13 / 140
持续更新永久归档
分类文章
按发布时间从新到旧 · 每页 40 条
教程 / 实战普通
Firecrawl vs Tavily for an AI agent: 97% vs 82% fact recall, and why retrieval breadth decides grounding
I run a competitor-research agent: give it a company URL and it finds and verifies that company's...
信息来源:DEV Community
教程 / 实战普通
Securing MCP servers: a practical checklist for 2026
MCP servers look harmless because they expose tools, not endpoints. A client calls a tool and gets a...
信息来源:DEV Community
教程 / 实战普通
2,200 applications = two interviews!
In 2022, I spent about a year applying for more than 2,200 jobs. I got two interviews. Two. After...
信息来源:DEV Community
教程 / 实战普通
Zero-Screen Dungeon Master: The Voice-Only RPG Where Your Real Walk Drives the Story
This is a submission for the DEV Hacktoberfest Open-Source AI Challenge: Week 1 - Touch Grass. 🌿...
信息来源:DEV Community
教程 / 实战普通
I Built an AI That Turns “I’m Bored” Into Real-World Side Quests 🌿
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass. Your...
信息来源:DEV Community
教程 / 实战普通
Magentic orchestration explained: why Microsoft's pattern outperforms naive supervisor architectures - Magentic One pattern
I spent a month defending a supervisor architecture I knew was failing. The symptoms were subtle at...
信息来源:DEV Community
教程 / 实战普通
An Unauthenticated KV Cache Server Puts Code Execution on Your Cluster Network
TL;DR LMCache is a caching layer for large language model servers that keeps the...
信息来源:DEV Community
教程 / 实战普通
Instinct 实测:面对 Muse 和 Dots 夹击,短信式 AI 智能体表现如何
The Verge 作者实测初创公司 Instinct 的 AI 智能体,它通过 iMessage、WhatsApp 或短信接口以纯文本方式处理订预约、退换货等生活事务,目前邀请制且免费,公司 9 月底估值 100 亿美元。
信息来源:The Verge:AI(RSS)
教程 / 实战普通
Use your filesystem as your database
If you’re like me, you generate a lot of markdown files with your agents. Maybe they’re things like...
信息来源:DEV Community
教程 / 实战普通
What a test HL7 v2 sender has to get right
Sending an HL7 v2 message is easy. Open a TCP socket, wrap the message in MLLP framing, write it, and...
信息来源:DEV Community
教程 / 实战普通
The retrieval pipeline worked. The product question remained.
I assumed that if search found the right document, that was good enough for a conversational...
信息来源:DEV Community
教程 / 实战普通
Can you deploy Hermes Agent in a Microsoft enterprise? Intune, Teams, Entra ID and Graph, checked against the code
What already works with Microsoft 365, what is still missing for a company-wide rollout, and the pilot checklist I use.
信息来源:DEV Community
教程 / 实战普通
The hard part of agent memory is knowing when to ask
This is a submission for the Kaggle Benchmarking Challenge I gave 39 language models the same...
信息来源:DEV Community
教程 / 实战普通
因为好奇不会飞的超级英雄被丢到沙漠里要怎么最快回到城市,比方说我们纽约好邻居蜘蛛侠,所以用腾讯内侧的游戏Agent做了一个策略游戏,我们只有9格资源,加油!
因为好奇不会飞的超级英雄被丢到沙漠里要怎么最快回到城市,比方说我们纽约好邻居蜘蛛侠,所以用腾讯内侧的游戏Agent做了一个策略游戏,我们只有9格资源,加油!
信息来源:X:卡尔的 AI 沃茨 (@aiwarts)
教程 / 实战普通
Simon Willison 用语音模式让 Codex 为博客开发 Newsletters 功能
Simon Willison 用 ChatGPT 桌面应用 Codex 标签页的语音模式,在做饭的约半小时内基本靠口头指令为博客开发出 Newsletters 索引功能,使用模型为 GPT-6 Astra High。
信息来源:Simon Willison 博客 · ChatGPT / GPT
教程 / 实战普通
Can a Better Model Be a Worse Thinking Partner?
I first noticed something missing while reviewing saved discussions of Microsonya, my Telegram...
信息来源:DEV Community
教程 / 实战普通
PALABRE: An AI-Powered Cultural Treasure Hunt That Gets You Off Your Phone
This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 1 — Touch Grass. ...
信息来源:DEV Community
教程 / 实战普通
I built an offline AI that knows your last frost date, no internet, no API
An open-weight tabular model forecasts your last spring frost and a local Gemma writes the planting advice. Fully offline, no account, $0 to run.
信息来源:DEV Community
教程 / 实战普通
No method has been shown to predict what software to build. So I'm backtesting mine on three years of store data
Update, Oct 9: I wrote this on Sept 29. The first backtest finished on Oct 1. One signal first looked...
信息来源:DEV Community
教程 / 实战普通
Super-Intelligent Yes-Men: Are We Training AI to Ignore the Truth?
This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked A published...
信息来源:DEV Community
教程 / 实战普通
Building AI-Ready Life Sciences Data Platforms: From Audit to Analytics
In September 2026, IQVIA called trusted data, responsible AI, and enterprise governance the new...
信息来源:DEV Community
教程 / 实战普通
MUSE: An AI Scavenger Hunt That Forces You to Put Your Phone in Your Pocket
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...
信息来源:DEV Community
教程 / 实战普通
DeepSeek 4.1 Flash Costs $0.003 per Million Tokens. Here Is the Two-Tier Router It Makes Possible.
If you run AI agents on cron jobs the way I do, you already know where the bill comes from. It is not...
信息来源:DEV Community · DeepSeek
教程 / 实战普通
Study: How AI Agent "Skills" Leak Your Credentials
A 2026 empirical study found that the reusable "skills" we plug into AI agents leak credentials at scale, usually during ordinary use, with no exploit…
信息来源:DEV Community
教程 / 实战普通
I built a desktop image editor in five weeks with Claude Code
On September 4 I started a ComfyUI custom node: a canvas with layers and selection tools, so I could...
信息来源:DEV Community · Claude
教程 / 实战普通
"Review This Code" Is the Worst ChatGPT Prompt. Here Are 5 Better Ones for the Same Buggy Function.
There is a bug in these six lines. Find it before you scroll. `def get_discount(price, user): ...
信息来源:DEV Community · ChatGPT
教程 / 实战普通
How Can AI Answer Questions About Your PDFs? Meet RAG
Have you ever wanted to upload your college notes and simply ask an AI, “Explain Unit 3” or “What is...
信息来源:DEV Community
教程 / 实战普通
Your dbt descriptions are your AI agent’s real prompt
I built an MCP server so AI agents can find and query our company data. Most of my time did not go...
信息来源:DEV Community
教程 / 实战普通
Building an In-Memory Semantic Cache for LLM Endpoints with Node.js and pgvector
If you run an LLM-backed endpoint (a support bot, a docs assistant, a "chat with your data" feature),...
信息来源:DEV Community
教程 / 实战普通
Giving your coding agent eyes on a React Native app: Argent vs agent-device, measured
At a glance Problem: Let a coding agent run, tap through and profile a React Native app by...
信息来源:DEV Community
教程 / 实战普通
From Jira ticket to feature environment: how we built a multi-agent AI developer
I'm Alina, Head of Web Applications at EXANTE. I'm responsible for the technical strategy of our web...
信息来源:DEV Community
教程 / 实战普通
The header says 10%. The table says 8%. Most frontier models quietly went with the table.
This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked Every...
信息来源:DEV Community
教程 / 实战普通
Why did my Claude Haiku calls start 400ing? Three AI API changes that break code quietly
Three AI API changes from the last two weeks that quietly break shipped code: Claude Haiku 5.5 migration 400s, Managed Agents web_fetch gating, and the GPT-6 plan split.
信息来源:DEV Community · GPT / Claude
教程 / 实战普通
How I built memory for my desktop AI companion: every memory must quote the transcript
How I built memory for my desktop AI companion: every memory must quote the...
信息来源:DEV Community
教程 / 实战普通
One caller, two approvers: the bypass a reader found in my approval code
The last piece ended with a correction. On the HTTP path of aine-control-plane, the field I had...
信息来源:DEV Community
教程 / 实战普通
Sub-400ms Voice AI: Scaling WebRTC and FastAPI on Serverless Cloud Run
Building an AI technical interviewer presents a unique physics problem. When a human engineer pauses...
信息来源:DEV Community
教程 / 实战普通
How to Convert Long Blog Lists Into Instagram Carousels With Nano Banana, AI HTML, and OpenRouter
Build an admin table of your blogs, then turn each post into Instagram carousels using Google Nano Banana images via OpenRouter, AI HTML slides, or an AI React code generator.
信息来源:DEV Community
教程 / 实战普通
Stop Paying $0.05 Per Trace: Building an OTel-Native LLM Cost Attribution Gateway
Build an open-source, OTel-compliant LLM reverse proxy to capture micro-cent token costs and trace inference to Tempo, ClickHouse, or Jaeger
信息来源:DEV Community
教程 / 实战普通
Would today's AI have caught Ariane 5? I rebuilt 26 of history's costliest bugs to find out
This is a submission for the Kaggle Benchmarking Challenge. What I Benchmarked Hindsight...
信息来源:DEV Community
教程 / 实战普通
Stratagems #31: Lena Took the Seat. The AI Had Reserved It for Her.
Send the enemy beautiful women to cause discord within his camp. — The 36 Stratagems, The Beauty...
信息来源:DEV Community