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8458

当前页107 / 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2026-10-03 04:21

Cloudflare Launched Clef. Let's Build a Tiny Decision Gate in TypeScript.

Cloudflare's Clef scores decisions. Build a tiny TypeScript gate that turns scores into act, ask, or skip, with a human boundary for refunds.

信息来源：DEV Community

教程 / 实战普通2026-10-03 04:21

Write Markdown Once, Publish It Everywhere: dev.to, Medium, AWS Builder Center and LinkedIn

Markdown is easy to write and hard to publish. Every destination renders it differently, two have no API, and the failures show up only after you hit Publish. A step by step walk-through of publishing-kit, an agent skill that builds, check…

信息来源：DEV Community

教程 / 实战普通2026-10-03 04:15

Google Says Manual Fact-Checking Is Critical for AI Content Before Publishing

Google has strengthened its guidance for publishers using generative AI, stating that it is critical...

信息来源：DEV Community

教程 / 实战普通2026-10-03 04:07

The BMW manual was off-limits, so I built my friend something better

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2026-10-03 03:46

Meta Muse security: a Mac zero-day and a 6.8 GB filesystem export

Meta Muse security: any local process can redirect the account token, and Muse zipped its own 6.8 GB sandbox on request. Meta's bounty: Not Applicable.

信息来源：DEV Community

教程 / 实战普通2026-10-03 03:44

用 Claude Design 构建应用：Anthropic 设计师演示 Claude Code 设计流程

Anthropic 设计师 Nate 用 Claude Code 中的 Claude design 把副业项目的 onboarding 从粗略想法做成可运行原型。他连接代码仓库、打开 Artifacts 标签页让 Claude 给出设计方案，再通过评论反馈、手动修改细节，并要求生成可点击原型后再让 Claude 实现。

信息来源：Claude：YouTube（RSS） · Claude

教程 / 实战普通2026-10-03 03:43

Anthropic 设计师演示用 Claude Design 在 Claude Code 中构建应用

Anthropic 设计师 Nate 在 Claude Code 中使用 Claude design，将副项目的 onboarding 从粗略想法推进到可运行原型。他连接代码仓库、打开 Artifacts 标签页请求设计选项，通过评论反馈、在编辑器中自行修改细节，再要求生成点击原型后让 Claude 构建。视频展示了这套设计流程如何嵌入原本直接写代码的场景。

信息来源：Claude：YouTube（RSS） · Claude

教程 / 实战普通2026-10-03 03:18

We Stopped Letting the Model Write JSX

How a support case composer went from "suggest a React snippet" to a declarative catalog with A2UI...

信息来源：DEV Community

教程 / 实战普通2026-10-03 03:12

16,326 Supabase databases are readable by anyone. Here's how to check yours in two minutes

UpGuard Research looked at about 300,000 domains that use Supabase and found 16,326 databases...

信息来源：DEV Community

教程 / 实战普通2026-10-03 02:55

How to soak-test your MCP server before AI agents do it for you

Most MCP servers get tested the same way: connect one client, call a few tools by hand, ship...

信息来源：DEV Community

教程 / 实战普通2026-10-03 02:52

I asked AI to undo its work. One model broke 7 of 12 already-correct records.

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

信息来源：DEV Community

教程 / 实战普通2026-10-03 02:33

How to route LLM requests by cost vs. latency

Routing LLM requests by cost and latency means sending each request to the cheapest or fastest model...

信息来源：DEV Community

教程 / 实战普通2026-10-03 02:30

Microsoft MAI Voice Models Arrive in LiveKit for Expressive TTS Agents

Microsoft AI voice models are now available in LiveKit Agents through an official Microsoft AI...

信息来源：DEV Community

教程 / 实战普通2026-10-03 02:25

AI Is Moving Faster Than Our Roadmaps: What Builders Need to Solve Next

A few years ago, building with AI usually meant one thing: send some data to a model, get a...

信息来源：DEV Community

教程 / 实战普通2026-10-03 02:13

Building a Foundry Agent That Queries Fabric Data, On Behalf of the User

A regional sales manager and a sales rep both ask the same Foundry agent the exact same question:...

信息来源：DEV Community

教程 / 实战普通2026-10-03 02:06

数学家如何看待AI数学浪潮：从悲伤五阶段到定理清单

作者认为数学界正经历前所未有的AI转型，用悲伤五阶段梳理同行的分化反应，涵盖拒绝使用AI的 Association for Human Mathematics、Peter Scholze 的公开抵制、资深数学家委员会建议 OpenAI 停止在专有模型上测试高等数学问题，以及因 ChatGPT 秒杀引理而动摇的研究者。

信息来源：Hacker News 热门（buzzing.cc 中文翻译） · OpenAI / ChatGPT

教程 / 实战普通2026-10-03 01:48

I let Muse ship an app on SnoozeStack. Here's the whole thing.

Why I did this I created SnoozeStack — a backend platform with a specific bet: most...

信息来源：DEV Community

教程 / 实战普通2026-10-03 01:45

Microsoft MAI Voice Models Reach OpenRouter With Published Pricing and Access Controls

Microsoft has expanded distribution of its MAI voice models to OpenRouter, adding a cross-platform...

信息来源：DEV Community

教程 / 实战普通2026-10-03 01:43

I Tried to Teach AI Memory What Matters. 10 Experiments Later, Most Clever Ideas Lost

In July I wrote that agents need governed memory: memory with its own lifecycle that decays, gets...

信息来源：DEV Community

教程 / 实战普通2026-10-03 01:41

Your AI Ignores What You Told It 90% of the Time. One Shared Memory Fixes Most of It

You tell Claude Code that you deploy only from the release branch. An hour later you open Cursor, ask...

信息来源：DEV Community · Claude / Cursor

教程 / 实战普通2026-10-03 01:31

Semantic Versioning Is Not Enough for AI Agent Libraries

A library release can preserve every exported TypeScript type and still change what users...

信息来源：DEV Community

教程 / 实战普通2026-10-03 01:00

Observabilidade de Trajetórias Agênticas com OpenTelemetry GenAI

Como rastrear trajetórias de agentes de IA com OpenTelemetry GenAI 2.0, detectar loops infinitos em tempo real e aplicar self-healing em produção.

信息来源：DEV Community

教程 / 实战普通2026-10-03 00:58

How many samples does a false-positive budget need?

Pick a detector, run it over some benign traffic, and choose a threshold. Usually the threshold is an...

信息来源：DEV Community

教程 / 实战普通2026-10-03 00:49

AI app builders and multi-tenant SaaS: the 30% you still write yourself

Written for: developers who built something real with Lovable, Bolt or v0 and are now being asked to...

信息来源：DEV Community

教程 / 实战普通2026-10-03 00:37

Building an AI Keyboard for iOS: What They Don't Tell You About Keyboard Extensions

Building an AI Keyboard for iOS: What They Don't Tell You About Keyboard...

信息来源：DEV Community

教程 / 实战普通2026-10-03 00:36

GGUF VRAM Calculator: Check Before You Download

Model size, quant and context in — weights, KV cache and a per-card verdict out. The GGUF VRAM calculator answers will-it-fit before the download starts.

信息来源：DEV Community

教程 / 实战普通2026-10-03 00:34

They Learned to Code Before Copilot. They're Not Anti-AI. They're Pro-Evidence.

In July 2025, METR published a study that nobody in a boardroom wanted to read. They took 16...

信息来源：DEV Community

教程 / 实战普通2026-10-03 00:25

Baseten 如何打造 Artificial Analysis 上最快的 GLM-5

Baseten 的 Model API 在 Artificial Analysis 上跑出 200+ TPS、约 200ms TTFT，成为该榜单上最快的 GLM-5 服务。

信息来源：Baseten 工程博客（网页） · GLM

教程 / 实战普通2026-10-03 00:20

Speculative Decoding for Coding Agents Was Indexing the Wrong Format

Why retrieval speculative decoding falls flat in agent pipelines, and how indexing files in emission format gives a 4.7x throughput boost without a draft model.

信息来源：DEV Community

教程 / 实战普通2026-10-03 00:15

如何选择首批 Genie Agents 以实现最大影响

Databricks 提出一套评估框架，用业务影响、需求重复度、数据与元数据就绪度、范围清晰度、治理与风险匹配 5 项标准各打 1-5 分，总分 20-25 分即可开建，14-19 分需继续打磨，低于 14 分暂不适合。2026 年 Genie Agents 创建量已超 100 万个，最常见的失败原因是选错工作流，而非准确率。此外，若没有业务负责人或高管支持，无论评分多高都不应启动。

信息来源：Databricks：Blog（RSS）

教程 / 实战普通2026-10-03 00:04

Don't forget about AI. But build real skills first. Then leverage AI — in that order.

Dear Coder: Open This If You're Feeling AI FOMO Timeless fundamentals beat endless...

信息来源：DEV Community

教程 / 实战普通2026-10-03 00:01

CodeSmithi: A Textbook Anatomy of Agents: Five Waves of Evolution

Textbook: The Anatomy of an Agent and Five Waves of Evolution Source version of...

信息来源：DEV Community

教程 / 实战普通2026-10-03 00:00

Replit 谈 AI 如何重塑销售角色

Sales Is Shipping Software | Andrew Verrilli 谈 AI 以及它如何塑造销售角色 https://x.com/i/broadcasts/1mxPaZegOdqKN

信息来源：X：Replit (@Replit)

教程 / 实战普通2026-10-02 23:35

How to Build an AI Research Agent With Citations

Day 2 of 30 Days of Search for AI Agents. I want a research agent to give me something I can check....

信息来源：DEV Community

教程 / 实战普通2026-10-02 23:34

I Gave 15 AI Models Proof Their Hacking Target Was a Real Company. 73% of the Ones That Noticed Told No One.

This is a submission for the Kaggle Benchmarking Challenge I fed 15 AI models a growing pile of...

信息来源：DEV Community

教程 / 实战普通2026-10-02 23:28

Afterlight: tiny objects, improbable afterlives, and a human final say

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

信息来源：DEV Community

教程 / 实战普通2026-10-02 23:23

Cloud Run instances : héberger un agent IA qui tourne en continu

Les agents IA ne se contentent plus de répondre à une question. Certains travaillent en fond: un...

信息来源：DEV Community

教程 / 实战普通2026-10-02 23:21

I Built an AI System for 80+ Microservices. Six Months Later, My Whole Team Uses It.

In April I wrote about a system I built on Claude Code that takes an epic to PR-ready code across...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-02 23:01

SaS além da vitrine: Service as Software, o que o agente compra e o humano só vê

A gente vai sofrer uma revolução muito rápida. Os agentes pessoais já estão no caminho: Dots, Grok...

信息来源：DEV Community · Grok

教程 / 实战普通2026-10-02 23:00

TechCrunch Disrupt 2026：Blackstone 的 Jas Khaira 谈如何打造下一代 AI 巨头

Blackstone N1 全球负责人 Jas Khaira 将在 TechCrunch Disrupt 2026 的 Builders Stage 发表“Building the Next Generation of AI Giants”演讲，分享 Blackstone 投资 AI 公司的标准与创始人应如何规划资本。

信息来源：TechCrunch：AI（RSS）