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5596

当前页107 / 140

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2026-09-09 01:46

Why I built a zero-telemetry Chrome extension to measure the physical cost of AI prompts

Every developer today relies on LLMs. Whether it's drafting boilerplate, refactoring complex logic,...

信息来源：DEV Community

教程 / 实战普通2026-09-09 01:14

FAILED is not UNKNOWN: the retry bug hiding in every AI agent

An agent refunds a customer $500. Stripe processes it. The response never comes back — a proxy...

信息来源：DEV Community

教程 / 实战普通2026-09-09 01:11

One Model Call, Then Deterministic Code: Build a Controllable Tencent RTC Voice Companion

Build a real-time AI voice companion where the LLM may answer or propose a timer, but only deterministic application code can confirm and execute it. This TypeScript tutorial covers interruption, stale results, idempotency, ambiguous confi…

信息来源：DEV Community

教程 / 实战普通2026-09-09 01:02

Why do developers continue to write code by hand?

Imagine you need to write a long piece of text that requires you to think things through, gather...

信息来源：DEV Community

教程 / 实战普通2026-09-09 00:50

弱通用AI已实现，提前一年达标

弱通用AI已实现（至少根据2020年设定的标准）。比近期预测提前一年 ✅勒布纳奖是弱图灵测试，GPT-4.5已等效达成 ✅Winograd被GPT-3通过 ✅SAT由GPT-4以75%通过 ✅蒙特祖玛的复仇被GPT-6攻克

信息来源：X：Ethan Mollick (@emollick) · GPT

教程 / 实战普通2026-09-09 00:45

Hello Dev Community: Introducing BoomTick

Every creative project has a rhythm. In software, it might be the hum of a CI/CD pipeline or the...

信息来源：DEV Community

教程 / 实战普通2026-09-09 00:35

This Is How I Built a Self-Healing CI Pipeline With Agents!

TL;DR: A failed CI build is often not just a failed CI build. It is a developer opening logs,...

信息来源：DEV Community

教程 / 实战普通2026-09-09 00:33

My Agent Returned Success. The Browser State Said Otherwise

An agent clicks Checkout. The browser tool returns success. The run completes without an...

信息来源：DEV Community

教程 / 实战普通2026-09-09 00:15

GEO and AEO Audits Must Check AI Crawler Access Beyond Google Search Console

A website can appear healthy in conventional SEO reporting while still being difficult for AI systems...

信息来源：DEV Community

教程 / 实战普通2026-09-09 00:13

Laravel's Native Vector Search Now Speaks MariaDB — Plain MySQL Is Still Left Out

Originally published on my blog. On August 20, PR #61250 was merged into Laravel's 13.x branch,...

信息来源：DEV Community

教程 / 实战普通2026-09-09 00:00

Google Search Console Rolls Out AI Reporting and Controls to Websites Worldwide

Google has completed the worldwide rollout of Search Generative AI performance reports and controls...

信息来源：DEV Community

教程 / 实战普通2026-09-08 23:50

I Used Every AI Coding Assistant I Could Find for a Month. Here's What I Actually Pay For Now

One developer tested Copilot, Cursor, Codeium, Tabnine, Replit AI, v0, Bolt and Lovable on the same two jobs for a month. What survived the renewal, what got cancelled, and the one skill that matters in 2026.

信息来源：DEV Community · Cursor

教程 / 实战普通2026-09-08 23:46

Databricks 如何用 Temporal 和 Lakebase 构建持久化智能体

Databricks 介绍如何结合 Temporal 与 Lakebase 构建持久化 AI 智能体，以个人贷款审批场景为例，展示智能体在收集证据、应用策略及等待外部输入等环节中的状态保持与恢复能力。文章聚焦于架构设计与工程实践，而非发布新模型或产品。

信息来源：Databricks：Blog（RSS）

教程 / 实战普通2026-09-08 23:41

AI Made Coding Faster. Now the Bottleneck Has Moved.

The code is being produced faster than I can confidently review, validate, and ship it. ...

信息来源：DEV Community

教程 / 实战普通2026-09-08 23:40

An AI-Fixed Test Passed. What Should QA Check Next?

One thing I’ve been thinking about something that sounds simple but is actually a little tricky: what...

信息来源：DEV Community

教程 / 实战普通2026-09-08 23:15

n8n’s AI Security Monitoring Guide Explains How to Detect Risks in AI Workflows

n8n has published new guidance on AI security monitoring for production environments, arguing that...

信息来源：DEV Community

教程 / 实战普通2026-09-08 23:04

The Circuit Breaker Pattern: Why Deterministic Code Hooks Beat Agent Self-Correction in Production LLM Pipelines

Original Article published on ZeroLabs. The Circuit Breaker Pattern: Why Deterministic...

信息来源：DEV Community

教程 / 实战普通2026-09-08 23:03

🤖 Hermes Agent Advanced Features Explained: Loop, Goal, Cron, Delegation, Bot Mode, Kanban & Mixture of Agents

Using Hermes Agent as a normal AI assistant is pretty straightforward. You give it a task. It...

信息来源：DEV Community

教程 / 实战普通2026-09-08 23:03

Can I remove the AI-generated tag from my AI-generated course?

I recently used DeepSeek v4 Pro to generate an embedded systems course for app, game, or web...

信息来源：DEV Community · DeepSeek

教程 / 实战普通2026-09-08 23:00

171 days, zero to first subscription — what actually worked

On September 7, 2026, someone paid $12 for KweliAI Pro Monthly. 171 days after I started building in...

信息来源：DEV Community

教程 / 实战普通2026-09-08 22:49

The Agent Doesn't Have to Be Malicious for the Action to Be Dangerous

We often talk about malicious AI. Rogue AI. Misaligned AI. AI agents going beyond their...

信息来源：DEV Community

教程 / 实战普通2026-09-08 22:42

Why I am not sad that the machine writes the code

A fourth piece, after "What's left when the machine writes the code", "How to start when the machine...

信息来源：DEV Community

教程 / 实战普通2026-09-08 22:41

Context Hydration: When Memory Becomes Voice

Part 7 of the Building the AI Memory Stack series Back in Part 1, I made a promise: memory...

信息来源：DEV Community

教程 / 实战普通2026-09-08 21:21

Docker Security Dispatch — Issue 6: Wait Five Days, Take a SIP ☕

The repository was real. The publishing workflow was trusted. The provenance checked out. The...

信息来源：DEV Community

教程 / 实战普通2026-09-08 21:20

Top 4 Open-Weight Coding Models for Local Workstations in Late 2026

Discover the top 4 permissive open-weight coding models for local developer workstations: Muse Spark 1.2, Qwen3.8-27B, Muse Glimmer, and Qwen3.8-Flash-Next.

信息来源：DEV Community · Qwen

教程 / 实战普通2026-09-08 21:20

Top 5 Rust-Powered CLI Utilities to Modernize Your Terminal in 2026

Explore the top 5 Rust-powered CLI tools to replace legacy Unix utilities: ripgrep, bat, eza, zoxide, and fd for speed and ergonomics.

信息来源：DEV Community

教程 / 实战普通2026-09-08 21:09

Claude Code vs Cursor vs Codex: I Tested All Three on the Same Task

The AI coding agent space has gone from "novelty" to "daily driver" fast. Three tools — Claude Code...

信息来源：DEV Community · Claude / Cursor

教程 / 实战普通2026-09-08 21:02

Build an RFP Response Manager with ToolJet MCP

Introduction An RFP response team uses this app to track active requests, assign SMEs, and...

信息来源：DEV Community

教程 / 实战普通2026-09-08 21:00

OpenAI：更强大且更实惠的 AI 如何拓展人与企业可完成的工作

OpenAI 探讨更强大且更实惠的 AI 如何拓展个人与企业可完成的工作范围，并让增长更具经济性。文章聚焦于 AI 能力提升与成本下降带来的实际应用空间扩展，而非发布具体新模型或产品。

信息来源：OpenAI：官网动态（RSS · 排除企业/客户案例） · OpenAI

教程 / 实战普通2026-09-08 20:51

5 AI Gateways That Actually Work in Production (2026)

If you've built a serious AI application, you've probably hit the same wall: hardcoding a model into...

信息来源：DEV Community

教程 / 实战普通2026-09-08 20:48

One question, 437,000 tokens: what real agents found in our MCP server

Eighteen scenarios, two hosted connectors, one production MCP server. The traces, the token numbers, and a JSON-RPC bug we only found by reading the spec twice.

信息来源：DEV Community

教程 / 实战普通2026-09-08 20:31

Has AI Made You A Lazier Developer? Be Honest.

Haven't you ever wondered if this AI vibe coding has made us lazy? Who's been solving problems on...

信息来源：DEV Community

教程 / 实战普通2026-09-08 20:16

I built a testing tool for AI agents — it caught a real prompt-injection vulnerability in a local model

I've been building Agenci — open-source CI/CD testing for AI agents (functional tests, security...

信息来源：DEV Community

教程 / 实战普通2026-09-08 20:11

WordPress Performance From The Code Side — No Plugins Needed

WordPress Performance From The Code Side — No Plugins Needed Every WordPress site...

信息来源：DEV Community

教程 / 实战普通2026-09-08 20:11

Your Agent Remembered the Fact. It Answered Like a Stranger.

A memory system can return the exact fact a request depends on whenever that fact is named, and still...

信息来源：DEV Community

教程 / 实战普通2026-09-08 20:02

Debugging the Black Box: Why Session Replay, Error Tracking, and Structured Logs Are the Missing Observability Layer for Production AI Agents

AI agents in production fail silently in non-deterministic ways. Learn the observability architecture—session replay, semantic error tracking, and structured logs—that makes them debuggable.

信息来源：DEV Community

教程 / 实战普通2026-09-08 19:46

Attention is simpler than you think - A hand-crafted superhero transformer

Part of the TechAarvam workshop support files — Build Your Own Model. Attention is...

信息来源：DEV Community

教程 / 实战普通2026-09-08 19:46

We Let Claude Code Refactor Our 200K-Line Java Monolith. Here's the Honest Result.

A real post-mortem on 6 weeks of AI-assisted refactoring — what it got right, what it silently broke, what we'd do differently, and the hybrid model we actually shipped.

信息来源：DEV Community · Claude

教程 / 实战普通2026-09-08 19:45

EU Opens €96 Million in Cybersecurity Calls Covering AI Tools, SMEs and Cable Resilience

The European Union has opened seven new cybersecurity funding calls worth a combined €96 million...

信息来源：DEV Community

教程 / 实战普通2026-09-08 19:33

One Visual Rule from a 3.2M-View TikTok — Rebuilt with an MCP Agent

A “dog as a skateboard” AI clip had about 3.2 million views on TikTok when I checked on September 6,...

信息来源：DEV Community