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116 / 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2026-09-29 21:38

Out-of-Order Events Break Your AI Agent on AWS

Ciao 👋 Make some chai, this is a long one, and it has a plot twist I did not see...

信息来源：DEV Community

教程 / 实战普通2026-09-29 21:27

AI Agent Governance on AWS: Block Agents, Prove EU AI Act Compliance

I built a synthetic multi-agent loan crew on Amazon Bedrock and made Traccia hard-block a runaway agent, redact applicant PII across every sub-agent, and export EU AI Act audit evidence. Two of my three governance policies blocked nothing …

信息来源：DEV Community

教程 / 实战普通2026-09-29 20:43

I Built an Agent Skill to Make Management Happy

It didn't make me write better code. It didn't make me deliver features faster. It didn't make the...

信息来源：DEV Community

教程 / 实战普通2026-09-29 20:18

Owambe Desk: running a Nigerian wedding on Sanity Workflows

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2026-09-29 19:46

AI agents took over my YouTube channel (satire): the real guardrails

AI agents write this YouTube channel. A satire episode let them take over; here are the real guardrails, plus Amodei's and Bengio's essays on AI agents.

信息来源：DEV Community

教程 / 实战普通2026-09-29 19:31

Benchmarking Real Work - Case 01: How I Built a Voice Agent Benchmark from Real Customer Failures

Customer complaints are not the problem definition; they are the signal. This post captures a...

信息来源：DEV Community

教程 / 实战普通2026-09-29 19:03

ProofSec: Benchmarking Epistemic Robustness and Evidence-Grounded Vulnerability Reasoning in Frontier LLM

This is a submission for the Kaggle Benchmarking Challenge What happens when an LLM...

信息来源：DEV Community

教程 / 实战普通2026-09-29 19:00

AI Coding Tip 038 - Make the AI Ask Before It Builds

A one-line request hides a dozen decisions you never made. TL;DR: Force the AI to ask about the...

信息来源：DEV Community

教程 / 实战普通2026-09-29 18:44

20 GitHub Repositories to Build with AI

AI is everywhere these days. But instead of just learning about AI, why not build something with...

信息来源：DEV Community

教程 / 实战普通2026-09-29 18:07

even legit coders are being forced to vibe code

Something shifted in the last year and I don't think we've named it properly yet. I know a lot of...

信息来源：DEV Community

教程 / 实战普通2026-09-29 18:07

Build Secure AI Agents with Microsoft Agent Framework and Auth0

A few months ago, I started messing around with Microsoft Agent Framework, and I found it to be very...

信息来源：DEV Community

教程 / 实战普通2026-09-29 17:52

IdeaConnectionAccuracy: Can AI Connect Ideas Like a Human? Three Ways an LLM's List Can Fail

This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked Ask an LLM...

信息来源：DEV Community

教程 / 实战普通2026-09-29 17:47

From Figma to merge request in an afternoon

A mid-size frontend feature used to take me about a week. Now it takes 3–4 hours of my own time....

信息来源：DEV Community

教程 / 实战普通2026-09-29 17:18

ZéroJour: an advisories agent that only works because the content is structured — and we prove it

Most entries will claim their agent works thanks to structured content. This one measures...

信息来源：DEV Community

教程 / 实战精选2026-09-29 17:00

Sarvam AI 发布从第一性原理构建 AI 智能体的入门指南

Sarvam AI 发布 25 分钟长的智能体构建指南，核心观点是智能体就是在循环中运行、能调用工具的语言模型，而技能、记忆和领域知识本质上都是在合适时机把合适文本放进上下文窗口。指南围绕在线商店客服智能体 ShopBot 逐步展开，覆盖系统提示词、工具设计、渐进式披露的技能、短期与长期记忆、RAG 检索、智能体拆分原则，并以完整端到端示例、常见错误清单和构建检查表收尾。

信息来源：Sarvam AI（网页）

教程 / 实战普通2026-09-29 16:52

Who's Accountable When the AI Was Just Following Instructions?

Earlier this year, a company's AI agent quietly leaked internal data for three weeks before anyone...

信息来源：DEV Community

教程 / 实战普通2026-09-29 16:44

How I Built a Code Reviewer That Remembers Every PR It's Ever Seen

I've reviewed enough pull requests to know the pattern: someone forgets to wrap an API call in a...

信息来源：DEV Community

教程 / 实战普通2026-09-29 16:42

Pausing an agent mid-task and resuming it four minutes later, with its memory intact

DigitalOcean's Managed Agents claims a paused session keeps its processes and memory. I put a counter in a shell variable, paused for 4m28s, and it came back at 48. Forking was stranger.

信息来源：DEV Community

教程 / 实战普通2026-09-29 16:39

[AI in Action] Gemini 3.8 Live Upgrade: Paying Off Technical Debt and How My Test Script Fooled Me Three Times

前情提要我有一個自己每天在用的 LINE Bot，linebot-helper-python。丟網址回摘要跟社群文案，丟 YouTube...

信息来源：DEV Community · Gemini

教程 / 实战普通2026-09-29 16:38

[AI in Practice] Shadowing Assessment with Gemini 3.5 Transcribe: Let Song Lingo Listen to You Read Lyrics

前情提要第一篇我用 Gemini 3.8 Flash TTS 做了 Song Lingo：貼 YouTube MV 網址，Gemini 轉錄歌詞、加上拼音翻譯文法，再由一位用...

信息来源：DEV Community · Gemini

教程 / 实战普通2026-09-29 16:30

OpenAI Tightens Frontier RL Security With Isolated Environments and Monitoring

OpenAI has publicly detailed a more restrictive security approach for frontier reinforcement...

信息来源：DEV Community · OpenAI

教程 / 实战普通2026-09-29 15:46

OpenAI agents and RubyGems: what the May attack report found

OpenAI agents ran May's RubyGems spam campaign, researchers say: the disclosure timeline, the API key leak, what RubyGems fixed, what gem owners should check.

信息来源：DEV Community · OpenAI

教程 / 实战普通2026-09-29 15:28

Ask ten LLMs for a Blender 5.0 script. Then run it in Blender 5.0.

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

信息来源：DEV Community

教程 / 实战普通2026-09-29 15:20

Ask the Archive: a Q&A agent grounded in 150 stories of Black California history

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2026-09-29 15:19

Your AI agent installs skills like npm packages — but nobody's scanning them

Last month I counted the "skills," plugins, and MCP servers I'd dropped into my AI coding agent....

信息来源：DEV Community

教程 / 实战普通2026-09-29 15:08

Agents won't kill apps... on a phone, they can't act without them

At WWDC this year, in the keynote, Apple confirmed something I had been holding as a logical...

信息来源：DEV Community

教程 / 实战普通2026-09-29 14:56

I let AI write my code for a month. The junior devs caught what it broke — I didn't.

Everyone's posting about how AI made them 10x faster. Here's the part nobody screenshots — a month of AI-assisted code where the regressions were silent, plausible, and mine to own. The juniors on the team caught three of them. I caught no…

信息来源：DEV Community

教程 / 实战普通2026-09-29 14:31

OpenAI 前沿 RL 训练安全指南

关于保障前沿 RL 训练的实用指南，反映了我们当前的实践经验：

信息来源：X：Greg Brockman (@gdb) · OpenAI

教程 / 实战普通2026-09-29 14:05

I Audited My Own AI-Agent Library Against a Real Bug Report — Here's What I Found

I maintain StateGuard, a small Python library that gives AI agents transactional state — snapshot,...

信息来源：DEV Community

教程 / 实战普通2026-09-29 13:55

How to Work With Agentic Teammates: A Practical Guide to Assigning, Governing, and Reviewing AI Work

AI agents are becoming much more useful when they can do more than answer a prompt. Instead of...

信息来源：DEV Community

教程 / 实战普通2026-09-29 13:50

The Database Playground: Everything You Can Plug In and Tune in PostgreSQL and MySQL (Including AI Workloads)

TL;DR: PostgreSQL and MySQL are not black boxes. Both let you swap storage engines, index types,...

信息来源：DEV Community

教程 / 实战普通2026-09-29 13:46

Retrieval is a routing problem. Your RAG stack just hides it.

Most RAG failures aren't model failures. They're routing failures wearing a retrieval costume. We...

信息来源：DEV Community

教程 / 实战普通2026-09-29 13:38

VARdict - uphold or overturn a VAR room's decision

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2026-09-29 13:25

Chain of Custody: an AI agent that only says what it can prove

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2026-09-29 13:24

I Gave ChatGPT My Full Codebase. The Results Scared Me — But Not for the Reason You Think.

So I did the thing everyone tells you not to do. I took the whole codebase. Every route, the...

信息来源：DEV Community · ChatGPT

教程 / 实战普通2026-09-29 12:45

AI Incident Response Agent powered by Hindsight

Overview The most dangerous thing an incident tool can do at 3 a.m. is hand an engineer a past fix...

信息来源：DEV Community

教程 / 实战普通2026-09-29 12:16

Why Nature Grows Brains from Embryos: Lessons from a Non-Backprop Neuromorphic Engine in Rust

Author: Andrii Shumko (with the assistance of autonomous AI agents) Corporate Inquiries:...

信息来源：DEV Community

教程 / 实战普通2026-09-29 12:08

Four vendors, one bad assumption: SSRF in MCP servers

There is a particular kind of bug that you only recognize the third time you see it. The first time,...

信息来源：DEV Community

教程 / 实战普通2026-09-29 12:07

An OCR'd wrong date becomes a confidently wrong Hindsight memory

A vision model reads a smudged diary page and gets the 8 in "18 June" wrong. It reads it as a 3. On...

信息来源：DEV Community

教程 / 实战普通2026-09-29 12:00

MIT 教授 Sherry Turkle 新书《Artificial Intimacy》探讨与机器对话如何改变人

MIT 教授 Sherry Turkle 的新书《Artificial Intimacy: Who We Become When We Talk to Machines》由 Little, Brown and Company 出版，基于访谈论述聊天机器人的伪共情正在削弱儿童发展与成人社交能力。

信息来源：MIT News（RSS）