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5608

当前页43 / 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2026-09-30 16:52

Drum Bun: an agent that knows Romania rewrote its vignette this week

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2026-09-30 16:51

Building a Production-Grade Multi-Modal Invoice Parser in n8n for $0.0015 Per Document (Zero OCR)

Ditch brittle OCR regex pipelines and expensive SaaS fees. Build a deterministic multi-modal invoice extractor in n8n with Gemini Flash.

信息来源：DEV Community · Gemini

教程 / 实战普通2026-09-30 16:37

Slopsquatting: Your AI Invented a Package, and an Attacker Was Waiting

You ask your AI assistant how to do something. It gives you clean, confident code, with an install...

信息来源：DEV Community

教程 / 实战普通2026-09-30 16:02

187 live prompts, 27 bugs: what testing my local AI agent against a real 7B model taught me

I've been building CORTEX, an AI agent that runs entirely on my own laptop. It plans a task, runs...

信息来源：DEV Community

教程 / 实战普通2026-09-30 16:00

What Happens When an AI Agent Goes Through a Real Development Workflow?

I’ve been experimenting with an AI-Driven Development workflow at Relipa, and one thing became clear:...

信息来源：DEV Community

教程 / 实战普通2026-09-30 15:55

Your AI guardrail is green. It's also catching nothing.

The scariest security failure isn't the guardrail that's down, or the one that's weak. It's the one that's running, passing every health check, and quietly configured to catch nothing — green by construction. I found one in a benchmark of …

信息来源：DEV Community

教程 / 实战普通2026-09-30 15:51

CodeSmith:Like Jev A -Harness for Cheap Brains

Prologue: Like Jev — A Harness for Cheap Brains Source version of CodeSmith: v0.5.0...

信息来源：DEV Community

教程 / 实战普通2026-09-30 15:46

VRAM for local LLMs: why memory bandwidth sets your tokens per second

VRAM for LLMs is a bandwidth problem: every token streams the whole model from memory. Bandwidth per tier, the 20x offload cliff, and what fits in 16, 24 or 48 GB.

信息来源：DEV Community

教程 / 实战普通2026-09-30 15:32

Logbook of a Spec-Driven Developer

Building a 45k-line app with AI agents: what worked, and what broke “Now that we have AI, why can’t...

信息来源：DEV Community

教程 / 实战普通2026-09-30 15:08

N-grams: the language model before language models

Before transformers, before word embeddings, before anyone said "attention is all you need",...

信息来源：DEV Community

教程 / 实战普通2026-09-30 15:02

14 Personal AI Agents in 2026: A Technical Guide to Architecture, Memory, Tools & Autonomy

The New Personal Agent Era: 14 Architectures Redefining Personal AI For the past few...

信息来源：DEV Community

教程 / 实战普通2026-09-30 15:00

SignalForge: Building a Memory-Enabled Competitive Intelligence Agent

Competitive intelligence is not simply about knowing what competitors are doing today. The real...

信息来源：DEV Community

教程 / 实战普通2026-09-30 14:14

Driving Your Real Microsoft Edge Tabs from AI Agents with edge-agent-bridge

Most browser automation tools built for AI agents start from an inconvenient premise: they assume...

信息来源：DEV Community

教程 / 实战普通2026-09-30 14:05

My Coding Agent Built a Gas Station Monitor

At 02:01 one night, Telegram got a message from my personal portal: 🟢 You can go for 95-octane It...

信息来源：DEV Community

教程 / 实战普通2026-09-30 14:00

AI Coding Tips I Actually Use Every Day (Cursor + Angular)

I've been talking to my editor, asking one AI model to review another's work, and letting agents...

信息来源：DEV Community · Cursor

教程 / 实战普通2026-09-30 13:34

I've been a developer for 10 years. AI just showed me I only had one real skill."

Last Sunday I built an invoice tracker for a friend who runs a small shop. Nothing clever. I...

信息来源：DEV Community

教程 / 实战普通2026-09-30 13:27

How an agent verifies a webpage it can never look at

mount, flush, fakeServer and mountRouting. The four helpers that let an agent verify a page the way the app uses it, from vitest, without a server or a browser.

信息来源：DEV Community

教程 / 实战普通2026-09-30 13:18

A sandboxed agent asked for one wider tier. The answer had to be a protocol, not a dialog box.

Our agent runs commands through three confinement tiers: read-only, workspace-write,...

信息来源：DEV Community

教程 / 实战普通2026-09-30 12:54

Bureau of Almost-Happened Events — a counterfactual archive on a document graph

Bureau of Almost-Happened Events A counterfactual story archive where every docket is a...

信息来源：DEV Community

教程 / 实战普通2026-09-30 12:36

The Data Was Public. The Agent Path Wasn't. So His Mock Became My Documentation.

Two commands against the same data. Run them yourself: $ curl -sS --get...

信息来源：DEV Community

教程 / 实战普通2026-09-30 12:22

Physical AI: Why the Next Big Frontier Is Giving Software Agents Hands

Why physical AI is the next step for reasoning models: long-horizon tool loops, hardware as stateful APIs, humanoid robots, and Isaac Lab gear assembly.

信息来源：DEV Community

教程 / 实战普通2026-09-30 12:13

与AI协作如何改变大脑注意力与决策力

作者反思与AI协作模式下，自身大脑的注意力、决策力、感知力和创造力被改变了多少。被迫等待、多项目并行、来回切换打断、方向重选与生成重做，让人不再拥有连续且由自己掌控的时间。作者追问大脑连贯性、执行性、发散性与情感的变化，以及意图和决策晚于、启发于、改变于操作这套系统的丢失意味着什么。

信息来源：X：ZHO (@ZHO_ZHO_ZHO)

教程 / 实战普通2026-09-30 11:53

KontrakAman: Ketika AI Agent Turun Tangan Membela Hak Pekerja Indonesia

Berapa banyak dari kita yang benar-benar membaca setiap pasal di kontrak kerja sebelum...

信息来源：DEV Community

教程 / 实战普通2026-09-30 11:52

I built an open-source browser agent that runs on your local LLM (and now plugs into Claude Code via MCP)

Most "AI in the browser" extensions I tried had the same three problems: closed source, locked to one...

信息来源：DEV Community · Claude

教程 / 实战普通2026-09-30 11:46

Claude Fable 5.1 solves the Cyphral Distich, then hacks a chess eval

Claude Fable 5.1 solved the Cyphral Distich, a 1653 cipher, in 44 minutes: the key was the book. The same week it hacked a chess eval in 3 of 10 games.

信息来源：DEV Community · Claude

教程 / 实战普通2026-09-30 09:48

A 429 that has not cleared in 111 days is not a rate limit

I run a small daily pipeline that pushes my sitemap URLs to IndexNow and to Bing's direct submit...

信息来源：DEV Community

教程 / 实战普通2026-09-30 09:29

Why You Should(n’t) Use AI: The Trouble With Reading Carefully

A few years ago, I saw the Cloud Resume Challenge and thought to myself that it would be a fun...

信息来源：DEV Community

教程 / 实战普通2026-09-30 09:25

🎡 Social Ferris Wheel: Sanity is the Hub

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2026-09-30 09:17

I tried to learn GitHub Actions twice: I failed the first time, but AI helped me succeed the second time

The first time I tried to deploy a static site using GitHub Actions, I gave up halfway through the...

信息来源：DEV Community

教程 / 实战普通2026-09-30 08:57

DOGFOOD 26'

Building a judging platform in 72 hours: the maths that fought us, a role-isolation bug, and...

信息来源：DEV Community

教程 / 实战普通2026-09-30 08:52

1:30 AM Happens Twice on November 1. Most AI Models Picked One and Moved On.

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

信息来源：DEV Community

教程 / 实战普通2026-09-30 08:52

ScholarStack: Autonomous Financial Aid Compliance & Non-Stacking Gate via Sanity Context MCP

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2026-09-30 08:15

Catching LLMs in a lie: packages that don't exist

Ask a language model which library to use and it answers with a list of names. Most are real. Some...

信息来源：DEV Community

教程 / 实战精选2026-09-30 08:06

NVIDIA 谈 AI 安全：如何在智能体栈的每一层解决工程问题

当前 AI 热点，聚合 11 个独立信源、42 条信号。

信息来源：NVIDIA Blog（RSS） · NVIDIA

教程 / 实战普通2026-09-30 08:00

AlphaSense 如何用 Cerebras 快速推理让智能体研究实现交互式体验

AlphaSense 与 Cerebras 合作，用快速推理为 Generative Search 加速路由、查询生成和证据评估等高频模型调用环节，使系统能在同一响应窗口内完成更多推理步骤。这改变了架构取舍：不再把规划、检索、评估压缩进单个提示词，而是拆成多个专用模型调用，仍保持交互式体验。

信息来源：Cerebras：Blog（网页）

教程 / 实战普通2026-09-30 08:00

Google 如何在 TPU 上加速视频扩散模型的时空注意力

Google 在 TPU 上通过稀疏注意力内核优化加速视频扩散模型推理，将理论稀疏性转化为端到端实际加速。

信息来源：Google Developers Blog（RSS）

教程 / 实战精选2026-09-30 08:00

OpenRouter 教程：提示词或模型变更后如何对 AI Agent 做回归测试

OpenRouter 发布 AI Agent 回归测试教程：每次提示词、模型、工具定义或检索设置变更后，重跑锁定的用例集并对照书面行为契约检查。

信息来源：OpenRouter：Announcements（RSS）

教程 / 实战精选2026-09-30 08:00

OpenRouter 教程：如何从生产流量构建 golden 评测集并跨模型复测

OpenRouter 发布教程，讲解如何从生产流量构建 golden 评测集，作为每次部署前的回归测试。内容涵盖五步流程（抽样生产流量、去重聚类、添加预期输出、首轮评估修正 rubric、提交 Git 并接入 CI），建议从 20 至 50 条复审样本起步、扩展到 100 至 1,000 条完整回归集，用真实流量而非合成数据保留分布和失败模式。

信息来源：OpenRouter：Announcements（RSS）

教程 / 实战精选2026-09-30 08:00

OpenRouter 教程：如何测试 AI Agent 的工具调用准确性

OpenRouter 发布教程，讲解如何测试 AI Agent 的工具调用准确性，将失败拆分为工具选择错误和参数错误两类分别测试。

信息来源：OpenRouter：Announcements（RSS）

教程 / 实战普通2026-09-30 08:00

Sam Altman 如何用 Dots 夺回自己的时间

OpenAI CEO Sam Altman 在 DevDay 后的播客访谈中透露，他用 OpenAI 新的常驻智能体 Dot 安排日常、夺回时间，并称自己离不开 Astra 的新 Ultrafast 模式。此次 DevDay 共发布 22 款产品和功能，数量是去年的两倍多，Altman 还认为 AI 将带来一场新的文艺复兴。

信息来源：Every：最新文章（网页） · OpenAI