AI 专题

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8440

当前页48 / 211

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2026-10-24 22:53

Build a Basic AI Agent From Scratch: Session Management II

Previous parts of Build a Basic AI Agent From Scratch: Basic Agent Tools Long Task Planning Human...

信息来源：DEV Community

教程 / 实战普通2026-10-24 22:52

Building a Linux GPU Driver for the M4 Mac mini in One Month, Mostly With Coding Agents

Apple Silicon is powerful hardware, but Linux support on it has always been a community-driven uphill...

信息来源：DEV Community

教程 / 实战普通2026-10-24 22:45

What If AI Didn't Just Answer Your Questions, but Helped You Actually Get Things Done?

We have AI tools that can write code, summarize documents, generate ideas, and answer almost any...

信息来源：DEV Community

教程 / 实战普通2026-10-24 22:37

Sloth Drawer: an offline agent that reads the manuals you already own and prints one maintenance card per device

I own 11 devices, and I could not tell you when any of them last needed cleaning — the manual...

信息来源：DEV Community

教程 / 实战普通2026-10-24 22:36

Two layers or it didn't happen: marking AI images for the EU AI Act in pure TypeScript

Since 2 August 2026, the EU AI Act requires AI products to mark generated content in a...

信息来源：DEV Community

教程 / 实战普通2026-10-24 22:29

Everyone Clicks 'I Agree.' No One Reads Them: I Fine-Tuned a 4B Model with Tinker to Catch Unfair Terms of Service in 30 Seconds

A 9,000-word contract scanned in 30 seconds. How I fine-tuned Qwen 4B with Tinker on the LexGLUE UNFAIR-ToS benchmark to catch arbitration waivers, unilateral changes, and liability caps.

信息来源：DEV Community · Qwen

教程 / 实战普通2026-10-24 22:08

Can You Break Our AI Security Defenses? Help Test Buried Injections & Taintgate

Here's an uncomfortable test. Take your "we block prompt injection" guardrail, and send it...

信息来源：DEV Community

教程 / 实战普通2026-10-24 21:48

Your MCP Tools Are an API for a Very Literal Intern

Picture a tool called save that takes a content string. You ask an agent to save a 12-page...

信息来源：DEV Community

教程 / 实战普通2026-10-24 21:46

How I built Live Voice: one tool contract, six realtime voice providers

How Fud AI's Live Voice works: a shared tool contract across iOS, Android and a Cloudflare Worker, six realtime providers, and a locked-down hosted relay.

信息来源：DEV Community

教程 / 实战普通2026-10-24 21:38

Fridge Sloth 🦥: snap your fridge, get a grocery list and healthy meals, fully offline on Gemma

One photo of your fridge gives you a grocery list and three healthy meals, running entirely on a 6-year-old M1 MacBook with Gemma 3 and Ollama, traced with Sentry.

信息来源：DEV Community · Ollama

教程 / 实战普通2026-10-24 21:04

Node2Shell Reaches Python: If Brotli Is Installed, requests Asks Servers for br

CVE-2026-111497 also hits PyPI's Brotli and brotlicffi, which requests, httpx and aiohttp use when installed. Upgrade to 1.2.1 and rebuild your images.

信息来源：DEV Community

教程 / 实战普通2026-10-24 21:04

What Building Real Software Taught Me About AI Coding Agents

AI coding agents are getting better at writing code. But after testing several of them on real...

信息来源：DEV Community

教程 / 实战普通2026-10-24 20:35

SEO Is Changing: How to Get Your Brand Recommended by ChatGPT, Gemini & Google AI

Imagine someone asks ChatGPT: "What are the best digital marketing tools for a small business?" Or...

信息来源：DEV Community · ChatGPT / Gemini

教程 / 实战普通2026-10-24 20:33

Structured Prompts for Accessible React (Roles, Keyboard, Contrast)

I used to paste “make this component accessible” into ChatGPT and hope for the best. Sometimes I got...

信息来源：DEV Community · ChatGPT

教程 / 实战普通2026-10-24 20:27

I Built an AI That Remembers the Promises We Forget

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

信息来源：DEV Community

教程 / 实战普通2026-10-24 20:09

The Internet Is Open to Everyone. Filling Out Its Forms Isn't.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

信息来源：DEV Community

教程 / 实战普通2026-10-24 19:31

Notice Sloth: an open-weight model reads my university notices so I don't have to

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

信息来源：DEV Community

教程 / 实战普通2026-10-24 19:19

Five cards instead of forty notes: a local model that refuses to guess

A notes folder grows faster than anyone reads it. This tool spends a local Gemma 2 2B on five notes only, caps itself at two minutes, and refuses any card it cannot back with a verbatim quote. Real numbers from a run on a laptop CPU: 0.8 t…

信息来源：DEV Community

教程 / 实战普通2026-10-24 19:18

Break Your AI Agent Before Users Do

Here's a request your travel agent bot will get one day: Book a flight to New York next week and...

信息来源：DEV Community

教程 / 实战普通2026-10-24 19:10

Vector Database Engineering

Vector Database Engineering A deep-dive walkthrough of how vector databases work and how...

信息来源：DEV Community

教程 / 实战普通2026-10-24 19:07

How Flisk Routes Agent Traffic: A Sequence Diagram of One Turn

A sequence diagram of one agent turn in Flisk, from the request through Traefik, the session checkpoint, the model call, and the reply. Shows where state is read, where it is saved, and what a restart does.

信息来源：DEV Community

教程 / 实战普通2026-10-24 19:02

Agent Client Protocol by Hand: Drive gemini --acp Over JSON-RPC on stdio

Start Gemini CLI in ACP mode, send initialize, session/new and session/prompt yourself, and read every message an editor like Zed gets back.

信息来源：DEV Community · Gemini

教程 / 实战普通2026-10-24 18:29

Letta 实战教程：用核心记忆、共享状态与语义检索构建有状态工程副驾驶

教程演示如何用 Letta 构建有状态的工程副驾驶智能体，涵盖可自主更新的核心记忆块、跨智能体共享记忆、档案向量记忆的语义检索、自定义服务端工具、流式执行和服务端消息历史。文末将完整智能体状态导出为 .af 文件实现便携迁移，并给出完整代码。

信息来源：MarkTechPost（RSS）

教程 / 实战普通2026-10-24 18:22

RecallSloth: Your Medical Revision Queue Can Do the Sorting

Source-linked medical recall cards, local AI overlap scouting, and a small Render-powered study queue.

信息来源：DEV Community

教程 / 实战普通2026-10-24 18:02

Sloth AI Folder Tidier: Let Open-Source AI Clean Your Downloads Folder So You Don't Have To

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady What I...

信息来源：DEV Community

教程 / 实战普通2026-10-24 18:00

The Doomscroll Derailer & Naptime Narrator: Rewarding Laziness with Offline AI Bedtime Stories

🦥 The Doomscroll Derailer & Naptime Narrator Built for the **Hacktoberfest Open-Source...

信息来源：DEV Community

教程 / 实战普通2026-10-24 17:51

My AI Coding Workflow, v3

My AI coding workflow changes every few months, so I give it version numbers. New tools ship, models...

信息来源：DEV Community

教程 / 实战普通2026-10-24 17:32

Humanizer has about 60,000 stars. On 12 public tasks my linter plugin scored 2.67 higher

I wanted to know whether a linter for AI writing tells helps an agent rewrite a file better than a...

信息来源：DEV Community

教程 / 实战普通2026-10-24 17:29

ReviewRadar: the request, a possible reply, and a calmer review session

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady. ...

信息来源：DEV Community

教程 / 实战普通2026-10-24 17:28

Netflix 如何用本体和知识图谱把可观测性变成可查询的确定性事实

Netflix 技术博客介绍其 Observability Ontology 与 RDF 知识图谱 QuipuDB，用类型约束把 LLM 摘要等非确定性输出收成可 SPARQL 查询的确定性三元组，再喂给 AutoRCA 供多个专科 Agent 共用词汇。

信息来源：X：邵猛 (@shao__meng)

教程 / 实战普通2026-10-24 17:04

OweMyGod: a fine-tuned 8B model reads Jakarta debt excuses right 92% of the time (keyword rules: 60%)

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

信息来源：DEV Community

教程 / 实战普通2026-10-24 17:01

I Built a Local AI to Turn a Shop's Evening Spreadsheet Hunt Into a Fix Queue

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

信息来源：DEV Community

教程 / 实战普通2026-10-24 16:54

LoRA 与 QLoRA 如何用一块 GPU 微调大模型

作者以模式（列向量乘行向量）为核心概念，讲解低秩近似、LoRA 与 4 位量化的原理：LoRA 冻结原有权重只训练新增的 r 个模式，量化用 NF4 分块缩放压缩存储。文中回顾华盛顿大学 QLoRA 在单块 48GB GPU 上微调 65B 模型的结果，并估算 7B 模型全参数微调约 100 GB、LoRA 约 15 GB、QLoRA 约 5 GB 显存开销。

信息来源：X：马东锡 NLP (@dongxi_nlp)

教程 / 实战普通2026-10-24 16:52

I Read Every "Jev Engineering" Thread So You Don't Have To

Turns out the "biggest breakthrough since RLHF" is a 3-day-old rebrand of something backend engineers already know.

信息来源：DEV Community

教程 / 实战普通2026-10-24 16:37

LazyDecider: I taught an open-weight agent to fine-tune a model while I slept

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

信息来源：DEV Community

教程 / 实战普通2026-10-24 16:32

SlothClerk: a sloth that reads your contracts offline with Gemma

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

信息来源：DEV Community

教程 / 实战普通2026-10-24 16:27

ReplyShelf: an open model finds the reply you already wrote

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady. ...

信息来源：DEV Community

教程 / 实战普通2026-10-24 16:01

Two Agents, Two Worktrees: Codex Writes the Tests Blind, Claude Code Makes Them Pass

Split TDD across two agents and let git hold the wall: Codex writes tests from the spec, Claude Code is denied edits, git diff checks it.

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-24 16:01

SlothScroll: I Taught Gemma to Read Instagram So I Never Have To

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

信息来源：DEV Community

教程 / 实战普通2026-10-24 15:48

Sloth Reads: an open model reads my read-later pile overnight, then reads me the good ones

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

信息来源：DEV Community