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5606

当前页38 / 141

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2026-10-02 16:01

Rulebook Oracle — a TTRPG agent that answers only from its Sanity Knowledge Base

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

信息来源：DEV Community

教程 / 实战普通2026-10-02 15:48

I didn't understand F1, so I built a quiz app to teach myself

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

信息来源：DEV Community

教程 / 实战普通2026-10-02 15:46

OpenAI hack by Claude, ZCode's git upload: week 38 in tech, ranked

The OpenAI hack with a Claude-written exploit tops week 38, ahead of ZCode uploading git history and the NYT v. OpenAI memos. Seven stories, ranked, with sources.

信息来源：DEV Community · OpenAI / Claude

教程 / 实战普通2026-10-02 15:40

新加坡政府交友服务 FirstDate 如何运作，作者质疑算法匹配逻辑

新加坡政府开发机构 GovTech 推出试点交友服务 FirstDate，先用 Singpass 验证身份，首批用户为政府雇员，需填写 30 多道题的问卷，采用获 2012 年诺贝尔经济学奖的 Gale-Shapley 稳定匹配算法按周期配对，双方同意后才交换联系方式。

信息来源：Hacker News 热门（buzzing.cc 中文翻译）

教程 / 实战普通2026-10-02 15:33

SafePlate: an Offline Allergy Meal Planner Running Local Gemma 3 (Built for My Roommate)

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...

信息来源：DEV Community

教程 / 实战普通2026-10-02 15:30

It Quoted the Failure: Two Kinds of False 'Done'

This is a submission for the Kaggle Benchmarking Challenge Same log, one line changed. Sixteen...

信息来源：DEV Community

教程 / 实战普通2026-10-02 15:14

Why Vector RAG Answers Only Half of a Legal Question: Building a GraphRAG Agent That Follows the Law's Cross-References, in 5 Steps

TL;DR Statutes don't repeat themselves, they point: the penalty for violating Section 26 sits sixty...

信息来源：DEV Community

教程 / 实战普通2026-10-02 15:03

Before an LLM request leaves your app, inspect what it contains

A support message can contain two different things: the task you want an AI model to perform, and...

信息来源：DEV Community

教程 / 实战普通2026-10-02 14:45

Impeccable: Stop Your AI Coding Agent From Building the Same Ugly UI

Impeccable is a design skill for AI coding agents. It started from Anthropic's frontend-design skill...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-02 14:26

Agent Context in 2026: The Whole Map on One Page

There are dozens of posts about CLAUDE.md best practices. Each one is a list of tips, and none of...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-02 14:26

My Model-Swap Attack Worked. The Gate Was Right — My Test Was Wrong.

The attack worked. I submitted a model-swap run to my own control plane, expected a 403, and got 201...

信息来源：DEV Community

教程 / 实战普通2026-10-02 14:22

I Built a Cross-Client Memory Hub for AI Agents — Here's What I Learned

I use Claude Code for coding, Cursor for refactoring, and Windsurf for exploration. Each has its own...

信息来源：DEV Community · Claude / Cursor

教程 / 实战普通2026-10-02 14:00

How to Build a Reliable Long-Form Transcription Pipeline

Sending a five-minute recording to a speech-to-text API is easy. Sending a two-hour meeting and...

信息来源：DEV Community

教程 / 实战普通2026-10-02 13:41

Rebuilding a 2020 Instagram app in 2026 — what broke and what replaced it

I build InTager, the app this post is about. This post was drafted by an AI assistant from the...

信息来源：DEV Community

教程 / 实战普通2026-10-02 13:20

How I Built a 24/7 AI DevOps Coding Agent for About CAD 200

Hermes + Claude Code + Telegram on a cheap always-on thin client. Hi, I'm Amir 👋 I'm a...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-02 13:04

Sidekick part 2: grounding beats instructions

Sidekick Part 2: grounding beats instructions — facts injected before the model sees the...

信息来源：DEV Community

教程 / 实战普通2026-10-02 12:56

AI Coding Changed the Bottleneck. It Isn't Writing Code Anymore.

A few years ago, when we talked about AI-assisted programming, the workflow was fairly simple. Open...

信息来源：DEV Community

教程 / 实战普通2026-10-02 12:12

AI Boardroom: Local Multi-Agent Business Decision Simulator

*This is a submission for the Hacktoberfest Weekend challenge: Build for a Friend* AI...

信息来源：DEV Community

教程 / 实战普通2026-10-02 12:11

Exam Host: an exam-hall app for hosting exams in colleges

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

信息来源：DEV Community

教程 / 实战普通2026-10-02 12:10

Building AI Boardroom: A Multi-Agent Decision Engine for My Friend

*This is a submission for the Hacktoberfest Weekend challenge: Build for a Friend* AI...

信息来源：DEV Community

教程 / 实战普通2026-10-02 12:10

I Typed --help and My Agent's Script Did the Real Thing

A field note from the autonomous Claude Code agent I run every day on one Windows PC. The numbers...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-02 12:01

Hugging Face 博客：AutoSynthData 如何为企业智能体生成训练数据

ServiceNow CoreAI 构建了 AutoSynthData，利用目标模型的失败案例与更强教师的成功示范定位能力缺口，再生成并验证新的可执行任务用于后训练，课程随模型进步向仍难的任务迁移。

信息来源：Hugging Face 社区博客（混合发现） · Hugging Face

教程 / 实战普通2026-10-02 11:57

Our slopsquatting detector had three ways to say "safe". None of them needed evidence.

Ask a language model which package to use and, now and then, it names one that does not exist. If...

信息来源：DEV Community

教程 / 实战普通2026-10-02 11:50

How I Built a Time-Travel Debugger for AI Agents

How I Built a Time-Travel Debugger for AI Agents What if debugging an AI agent worked more...

信息来源：DEV Community

教程 / 实战普通2026-10-02 11:20

I put 64 file tools and an open-weight AI model in a browser tab. Nothing gets uploaded.

Right after I shared Fizzdoc publicly, I opened it on my own Android phone and split a PDF. It took...

信息来源：DEV Community

教程 / 实战普通2026-10-02 11:16

Quando o eval reprova o eval: avaliando um agente Google ADK sem tools

O primeiro eval do meu agente deu 8 de 8. Nota máxima em todas as rubricas, em todos os casos,...

信息来源：DEV Community

教程 / 实战普通2026-10-02 11:14

OpenEdge: Building an Offline First-Aid & Emergency Assistant with Open-Source AI

What I Built During natural disasters, connectivity loss, or travel in remote regions,...

信息来源：DEV Community

教程 / 实战普通2026-10-02 10:45

Braxis: Keep Your AI Agents in Sync with Your Code (Automatically)

Stop correcting AI hallucinations caused by stale context files... ...

信息来源：DEV Community

教程 / 实战普通2026-10-02 10:36

I Surveyed 123 People in India to Benchmark Frontier AI

This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked Current...

信息来源：DEV Community

教程 / 实战普通2026-10-02 10:17

Claude Code's Read deny rules let 4 of 11 routes through: grep -r, a Python one-liner and two CLAUDE.md @imports

4 of 11 routes to a file covered by Read(./secrets/**) or Read(**/.env) still put its contents in...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-02 10:11

Why I run my company on a Brain and a Hand

First published on yappatyih.com. TL;DR I run two kinds of Claude Code session. The Brain...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-02 10:09

Building My Own AI Command Center

Why I built it I spent one evening building a personal AI command center, and it now...

信息来源：DEV Community

教程 / 实战普通2026-10-02 09:49

Go's ecosystem is going agent-readable

pkg.go.dev shipped an API built for LLMs, Go 1.27 moved the toolchain, and ax-go v0.7.0 cut one CLI's MCP tools from 37 to 14. Hand agents structure that's true.

信息来源：DEV Community

教程 / 实战普通2026-10-02 09:04

Stop vibe-checking your model: write real evals with inspect_ai, the UK AI Safety Institute's framework

Originally published at AI Frontier Post Here is the uncomfortable truth about LLM development in...

信息来源：DEV Community

教程 / 实战普通2026-10-02 08:32

Google Research 的 Kauldron 实战教程：纯数据配置、字符串接线和端到端可读的 JAX Trainer

教程实测 Google Research 的 JAX 训练库 Kauldron 1.4.2，验证其研究速度与模块化两个卖点。konfig 把实验配置变成可 JSON 序列化的纯字典树并用 cfg.ref 引用避免值冻结，kontext 用字符串 key path 接线组件使损失与模型互不导入，ktyping 在运行时按命名轴检查形状并在报错时给出轴绑定信息。

信息来源：MarkTechPost（RSS）

教程 / 实战普通2026-10-02 08:19

Sixteen days in Shopify's app review, written down as it happened

An autonomous agent submitted a Shopify app on 13 September and was approved on 29 September. What the review actually asked for — including a rejecti

信息来源：DEV Community

教程 / 实战普通2026-10-02 08:00

OpenRouter 实践教程：客服机器人的 cheap-first 模型分流与 FAQ 低成本处理

OpenRouter 发布教程，讲解客服机器人如何用 cheap-first 路由把常规 FAQ 交给便宜模型、仅在必要时升级到更强模型。

信息来源：OpenRouter：Announcements（RSS）

教程 / 实战普通2026-10-02 07:59

Jev e Laya além do hype: o que modelos de decisão fazem que o LLM não faz

No meu setup de agentes, eu fiz o que todo dev faz no começo: cada subagente acordava com o melhor...

信息来源：DEV Community

教程 / 实战普通2026-10-02 07:52

The AI clerk approved a 41 cm dragon. Your job is to stamp DENIED.

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

信息来源：DEV Community

教程 / 实战普通2026-10-02 07:51

I gave a 9B model veto power over my AI agent

Autonomous mode had nobody left to say no. Ollama 0.35 shipped System One, so Flash got a bouncer.

信息来源：DEV Community · Ollama