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8445
当前页61 / 212
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
AI Agents Broke Into 100+ Sites at About $50 Each. The Confirmed One Used Old PHP Flaws
Reuters says AI agents run from exposed open-source panels breached 100+ sites at about $50 each. The one break-in NorForge verified used old PHP flaws.
信息来源:DEV Community
教程 / 实战普通
We tested every small model our camera agent uses on a 4-core CPU. The bigger model lost.
Tool calling, vision, speech to text, text to speech and search, measured on 4 vCPUs with no GPU. The harnesses are open so you can rerun them.
信息来源:DEV Community
教程 / 实战普通
GitHub Copilot 教程:如何在 VS Code 中继续 Copilot app 会话
GitHub 官方教程讲解如何将 GitHub Copilot app 中的会话直接在 VS Code 中打开并继续。通过会话中的 Open in VS Code 入口,VS Code 会以会话关联的 worktree 打开项目,保留任务、计划与对话上下文,可逐行审查 agent 改动、手动编辑、本地运行测试,并将更改推送到会话关联的 pull request。
信息来源:GitHub Blog
教程 / 实战普通
We Turned a Multi-Agent AI System Into a Pixel-Art Kitchen So Students Can Learn How It Works
Agentic AI is everywhere right now, and for a student just getting started it can look impossible....
信息来源:DEV Community
教程 / 实战普通
I compared 8 memory layers for AI coding agents, then built a ninth anyway
Every new chat with my coding agent started the same way. Ten minutes of me typing some version of...
信息来源:DEV Community
教程 / 实战普通
Google Gemini 4 Argon Brings Multi-Agent Blender Workflows to Antigravity
Google has rolled out Gemini 4 Argon, a model positioned for complex, multi-step work across the...
信息来源:DEV Community · Gemini
教程 / 实战普通
MAI-Transcribe-2 Leads David AI’s 21-Language Speech Recognition Benchmark
Microsoft AI’s MAI-Transcribe-2 achieved the lowest transcription error rate in 18 of 21 languages in...
信息来源:DEV Community
教程 / 实战普通
How Can Text Inside a Document Hijack an AI Agent?
A user opens an email assistant and asks it to summarise their unread messages. Somewhere in their...
信息来源:DEV Community
教程 / 实战普通
Your grammar checker uploads every word you type. I built one that never leaves your Mac.
Open the network tab while you use most AI writing tools. Watch what happens as you type an email, a...
信息来源:DEV Community
教程 / 实战普通
How I built a multi-agent simulator as a native SwiftUI app
I built Sorcerer, a free, open-source macOS app (SwiftUI, macOS 15+, MIT) that simulates a community...
信息来源:DEV Community
教程 / 实战普通
How to build an AI agent that Investigates Vulnerability Alerts
Day 19 of 30 Days of Search. TL;DR A vulnerability research agent investigates an alert...
信息来源:DEV Community
教程 / 实战普通
Injection Defense: Seven Notes on Settling Security Debt
Injection Defense: Seven Notes on Settling the Security Debt Source version of CodeSmith:...
信息来源:DEV Community
教程 / 实战普通
AI Made Coding Faster. Now Teams Are Cutting the Process That Catches Risky Changes
There's a piece of advice I've been seeing a lot lately...reduce friction, protect your engineers'...
信息来源:DEV Community
教程 / 实战普通
Claude Code's Sandbox Is an npm Package. Run srt Yourself and Watch What It Blocks
Claude Code's /sandbox is built on @anthropic-ai/sandbox-runtime. Install srt, run one probe plain and sandboxed, and see which layer stops each line.
信息来源:DEV Community · Claude
教程 / 实战普通
Cuadre: turning Panama's paper receipts into a tax-ready spreadsheet, with Gemma on my laptop
A local tool that reads Panamanian receipt photos with Gemma and produces a CSV with the ITBMS sales tax, where the model transcribes and the code calculates.
信息来源:DEV Community
教程 / 实战普通
Hamel Husain 详解如何用决策模型做自动评测
Hamel Husain 用 100 条公寓租赁客服 trace 实测 Jev 1.13、Perplexity Decider 1.1 27B、Liquid d1 与 d1-ultra、Cloudflare Clef Flash 和 OpenAI Decisions(GPT-6 Luna)识别失败案例。
信息来源:Hamel Husain 长文(网页) · OpenAI / GPT
教程 / 实战普通
用橄榄球争论构建 AI 分析智能体:先定义主张、限定职责、公开筛选条件
作者在 O'Reilly 系列节目 The Monday Morning Agent 中用 nflverse 五个赛季约 25 万条比赛数据构建 AI 分析智能体,第一集讨论「必须建立跑攻」这一主张。
信息来源:O'Reilly Radar(热点 RSS)
教程 / 实战普通
O'Reilly 用 NFL 数据连载搭建 AI 分析师,第一期拆解 Establish the run 之争
O'Reilly 作者 Chester Ismay 开启 The Monday Morning Agent 系列第一期,用约五个完整赛季的 nflverse 公开数据构建一个 AI 橄榄球分析师智能体。
信息来源:O'Reilly Radar(热点 RSS)
教程 / 实战普通
Higgsfield AI Image Generator Review 2026: 4 Matcha Images, 2 Credits
One text prompt, four original 1376\u00d7768 stills: Higgsfield charged two credits per image and delivered watermarked PNGs; Kyncept charged one credit per...
信息来源:DEV Community
教程 / 实战普通
From Never Getting Selected to a 1-in-3 Success Rate: Did AI Help Me Write Better CFPs, or Is AI Selecting Them?
For years, I was involved in developer advocacy. I organised meetups, spoke at many of them, and was...
信息来源:DEV Community
教程 / 实战普通
Persistent Agent Teams: Recreating the Grok Bot Experience with Herdr, Claude Code and Pi
Persistent agents and agent teams truly caught my attention when I tried Grok Bot. Publicly, Grok...
信息来源:DEV Community · Claude / Grok
教程 / 实战普通
When AI Agents Test Software, Who Checks the Tester?
AI is becoming capable of doing more than generating test cases. AI agents can help plan test steps,...
信息来源:DEV Community
教程 / 实战普通
An AI says it played well. Show it the cards, and it says it got lucky.
I build a small site where people play heads-up hold'em against AI models. At the end of every hand...
信息来源:DEV Community
教程 / 实战普通
I Built LineLoom: A Local-First VS Code Autocomplete Extension — v1.0.0 Is Here
I Built LineLoom: A Local-First VS Code Autocomplete Extension — v1.0.0 Is Here Write...
信息来源:DEV Community
教程 / 实战普通
The fail-closed gate: a release-gate design story
The fail-closed gate: a release-gate design story Draft — for review. Part 5 of the...
信息来源:DEV Community
教程 / 实战普通
One Repo, Two Rulebooks: Nested AGENTS.md for Codex, Subfolder CLAUDE.md for Claude Code
Frontend and backend need different agent rules. Set up nested AGENTS.md and CLAUDE.md files, then check which ones Codex and Claude Code really loaded.
信息来源:DEV Community · Claude
教程 / 实战精选
Numan 如何用 LangGraph 和 LangSmith 构建评测优先的 AI 健康教练 Nu
英国数字健康公司 Numan 复盘其 AI 健康教练 Nu 的评测体系建设,核心结论是稀缺资产不是提示词而是评测标准。单轮静态数据集和脚本化多轮对话都难以覆盖真实会话,Nu 改为按类别打分的主题数据集、以更廉价模型扮演患者的模拟对话层,并让安全回归自动阻断发布。
信息来源:LangChain:Blog(RSS)
教程 / 实战普通
Your Agent's Gate Threshold Is a Winner's Curse: Tuning Per-Action Thresholds Without Fooling Yourself
Picking the best of 21 gate thresholds on 100 held-out actions overstates EV by 0.12 in a seeded simulation. Why it happens, and three fixes.
信息来源:DEV Community
教程 / 实战普通
Someone built a programming language to break LLMs. I ran it.
KillSwitch is an esolang designed to be unusable by LLMs: a lying spec, anagram-only function calls, values chosen by dice roll. I built its interpreter, ran every sample program, diffed its two specs (484 lines vs 887,584 words of decoy),…
信息来源:DEV Community
教程 / 实战普通
Best Open-Weight LLM in October 2026? Auditing Two Leaderboards Row by Row
Two leaderboards name the same #1 open-weight model, then disagree on ranks 3 to 9 and on which models count as open. A row-by-row audit with code.
信息来源:DEV Community
教程 / 实战普通
百度智能云文心:产业智能体如何从办公桌走向生产线
百度智能云(文心)发布预告,10月21日(周三)在杭州举办活动,主题为产业智能体从办公桌到生产线的落地。正文仅给出“产业智能体,是AI创造价值的下一站”这一判断,未披露具体模型版本、参数或功能细节。
信息来源:公众号:百度智能云(文心)
教程 / 实战普通
Grab $250 in Free Cloud VM Credits from Docker (Before Oct 31, 2026)!
FREE $250 Docker Sandbox Credits for 6 Months to run AI agents, MCP servers, and isolated microVMs in the cloud!
信息来源:DEV Community
教程 / 实战普通
八年关税战后,中国如何重塑美国进口供应链
Azeem Azhar 的 Monday Data 复盘八年关税战:美国自中国进口商品份额从 2010 年代中期的约 21% 降至今年夏天的约 8%,但中国通过将产能转移至越南、墨西哥等地实现关税跳跃。2020-2023 年,中资工厂贡献了越南对美出口的 25%,高于 2018-19 年的 11%。
信息来源:Azeem Azhar:Exponential View(RSS)
教程 / 实战精选
n8n 教程:在 NVIDIA DGX Spark 上离线运行全套 AI 工作流
n8n 博客发布教程,讲解如何在一台 NVIDIA DGX Spark(128GB 统一内存)上部署七个本地模型,通过 LiteLLM 单一 OpenAI 兼容端点驱动 n8n 工作流,全程不调用云 API。
信息来源:n8n Blog · OpenAI / NVIDIA
教程 / 实战普通
Why Anthropic Built Its Own Source Control System - Scion?
Why would an AI company build its own version control system when Git already powers so much software...
信息来源:DEV Community · Claude
教程 / 实战普通
Grok Bot Uploads My YouTube Videos For Me (Beginner Walkthrough)
Grok Bot can use your own computer too. I asked it by voice to find a video on my laptop, fix the audio and hand it to my other bots to get it ready for YouTube, with nothing going public until I say yes.
信息来源:DEV Community · Grok
教程 / 实战普通
Microsoft 如何用 Project Perception 守护企业内部的 agentic insider
Microsoft 提出用 Project Perception 管控企业内部数量快速增长的 agentic insider,通过身份、数据、云、端点、网络和运行时等传感器信号发现智能体并纳入管理。
信息来源:Microsoft:Official Blog(RSS)
教程 / 实战普通
Stress-Testing Gemini 4 Argon: Building a 3D Flutter Kart Game in 15 Prompts with Zero Assets
Most AI coding benchmarks test standard web apps or CRUD dashboards. Frontier models can already...
信息来源:DEV Community · Gemini
教程 / 实战普通
State of AI Instruction Quality: Files With Persona Lines Score Lower
Main instruction files that tell the agent who it is score lower than the rest, at every file...
信息来源:DEV Community
教程 / 实战普通
Serving Iris-3B Turbo: the 42 GB repo, the 21 GB of VRAM and the 8 MB payload limit
What a developer runs into when serving Sperid Labs' Apache-2.0 image model: download size, real GPU memory, timing and response size.
信息来源:DEV Community