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8439

当前页20 / 211

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2026-11-04 08:49

AI Execution Governance, Part 10: Can Revocation Stop a Call That Is Already Running?

A tool call has passed the gate and is running. Now the role is revoked. Does it stop, or does it...

信息来源：DEV Community

教程 / 实战普通2026-11-04 08:41

How uv add silently downgraded my pypdf security patch (and how I fixed it)

I merged two PRs to fix my dependency alerts on GitHub. Both had empty diffs. GitHub kept showing 11...

信息来源：DEV Community

教程 / 实战普通2026-11-04 08:21

My x402 API made $0.08 in its first week. Here is who actually came.

A few weeks ago I put a small API online that agents pay per call with x402, USDC on Base. It scans...

信息来源：DEV Community

教程 / 实战普通2026-11-04 08:00

Baseten 如何优化 DeepSeek V4.1 Flash 1017 推理速度

Baseten 用内部 harness 对 DeepSeek V4.1 Flash 1017 的 80+ 个 kernel 和瓶颈做优化，打造出 Fast 变体，在 Artificial Analysis 上达到 991 output tokens/s 和最低单任务耗时。

信息来源：Baseten 工程博客（网页） · DeepSeek

教程 / 实战普通2026-11-04 07:30

OpenAI Says ChatGPT’s Search-Like Query Volume Is About One-Fifth of Google’s

OpenAI says ChatGPT’s web-search-like query volume is roughly 20% of Google’s traditional search...

信息来源：DEV Community · OpenAI / ChatGPT

教程 / 实战普通2026-11-04 07:27

I ran the same multi-agent experiment twice. Half the conclusions flipped.

In August I ran a controlled experiment on my open-source multi-agent pipeline: the same task, done...

信息来源：DEV Community

教程 / 实战普通2026-11-04 07:09

Indirect Prompt Injection: How to Protect Your AI Agent with Spotlighting and Prompt Shields

While my AI agent was reading a web page, the page tried to give it orders. The page started with...

信息来源：DEV Community

教程 / 实战普通2026-11-04 06:56

How I Overhauled DocsGPT's Ingestion Engine & Supercharged RAG Context: My Hacktoberfest 2026 Journey

How I Overhauled DocsGPT's Ingestion Engine & Supercharged RAG Context: My Hacktoberfest 2026...

信息来源：DEV Community

教程 / 实战普通2026-11-04 06:40

Switch from zero: ship a human-in-the-loop data quality agent to your team chat

I spent the Flip the Switch hackathon building Shield, an agent that checks a daily table, explains...

信息来源：DEV Community

教程 / 实战普通2026-11-04 06:28

That's a Wrap on Hacktoberfest 2026! 🎃👻

Hacktoberfest 2026 wrapped up on October 31st! Thank you to everyone who built, hosted, mentored,...

信息来源：DEV Community

教程 / 实战普通2026-11-04 06:20

How to Switch AI Character Chat Apps Without Losing Your Chats, Personas and Lore

Switching AI character chat apps is common: features change, free tiers shrink, rules shift, or...

信息来源：DEV Community

教程 / 实战普通2026-11-04 06:01

Ctrl+C in a Coding Agent Is Just Byte 0x03. Raw Mode Decides What Happens Next

Agent TUIs can put the terminal in raw mode, so Ctrl+C arrives as byte 0x03, not SIGINT. Here's what that means for Esc, exit and the tests they spawn.

信息来源：DEV Community

教程 / 实战普通2026-11-04 06:00

Anthropic FlashProve Shows How AI Outputs Could Become Cryptographically Verifiable

Anthropic has introduced FlashProve, an open-source research prototype designed to cryptographically...

信息来源：DEV Community · Claude

教程 / 实战普通2026-11-04 05:43

The Biggest Problem With AI Test Automation Isn't Writing Tests

A few years ago, creating automated tests was one of the biggest bottlenecks in software...

信息来源：DEV Community

教程 / 实战普通2026-11-04 05:39

What I Learned Managing a Full Project with Antigravity

How my workflow evolved from solo prompting in AI Studio to managing a multi-model AI team, running...

信息来源：DEV Community

教程 / 实战普通2026-11-04 05:07

为什么人类洞察是构建更好智能体的战略优势

LangChain 博客提出高效 human-in-the-loop 工作流的三条原则：由领域专家定义质量标准、在完整会话上下文中评估智能体、把人工反馈转化为可复用的评测数据。LangSmith 的标注队列支持以单次 run 或完整 thread 为审核单元，评审者给出分数与理由，这些标签可用于对齐 LLM judge、更新在线评估器并构建 golden dataset。

信息来源：LangChain：Blog（RSS）

教程 / 实战普通2026-11-04 04:06

I'm sure there's lot's of other weird trends AI loves to create, but this one is quite funny

Wikipedia dropped this UUID in 2014. Now it's everywhere ...

信息来源：DEV Community

教程 / 实战普通2026-11-04 03:25

Why freezing completed Markdown blocks reduces streaming rendering work

An AI response arrives as text deltas. A Markdown renderer normally receives a document. Connecting...

信息来源：DEV Community

教程 / 实战普通2026-11-04 03:02

8 jq Commands That Show What Your Coding Agent Actually Did, From Its Transcript

Claude Code and Codex log every session to JSONL on your disk. Eight jq commands pull out the shell commands, edits, errors, denials, slow calls and model.

信息来源：DEV Community · Claude

教程 / 实战普通2026-11-04 02:08

An AI Supervisor Ran a Call Center Team for Three Weeks. Then Someone Checked Its Weekly Report

Talk time with partners rose by a third to 80%, depending on how you count. Only one of the nine...

信息来源：DEV Community

教程 / 实战普通2026-11-04 01:55

Your AI agent skills are probably out of date. Mine were. Here's how I handled it.

My old agent skill was one long file and it told every agent I used to run MinIO for local S3. Then...

信息来源：DEV Community

教程 / 实战普通2026-11-04 01:45

Qwen weight editing: how Astra reduced thinking loops

Qwen gained reported math accuracy after a targeted loop repair. The actual prompt shows Python and practice feedback; smaller Gemma found no established gain.

信息来源：DEV Community · Qwen

教程 / 实战普通2026-11-04 00:31

Why 80% on OSWorld Required VM Snapshot Rollbacks

If you have ever watched an autonomous computer-use agent work through a desktop operating system,...

信息来源：DEV Community

教程 / 实战普通2026-11-04 00:26

Flipper got archived, so I built an Android inspector that needs no SDK

GitHub: https://github.com/ESeungJun/droidlens Installers for macOS, Windows and Linux are on the...

信息来源：DEV Community

教程 / 实战普通2026-11-04 00:00

NVIDIA 如何用 AI 智能体简化 AI 工厂运维

NVIDIA 开发 AI Factory Operations Agent，用于简化其内部 DGX SuperPOD 运维、减少 SRE 手动排查工作。该智能体基于 NVIDIA NemoClaw 蓝图与 OpenShell 框架构建，子智能体通过 MCP 通信，可跨层关联根因并通过聊天界面给出建议。

信息来源：NVIDIA Technical Blog：Agentic AI / Generative AI · NVIDIA

教程 / 实战普通2026-11-04 00:00

LangChain 讲解如何为 Deep Agents 优化浏览器工具，Stagehand 在 WebVoyager 上以 $1.98 通过 90% 任务

LangChain 为 Managed Deep Agents 选型浏览器工具，对比七个工具集后在 WebVoyager 100 个任务上选用 Stagehand（90% 通过、总成本 $1.98、中位 17.4s），Playwright MCP 为 78%、$26.71。

信息来源：LangChain：Blog（RSS）

教程 / 实战普通2026-11-04 00:00

NVIDIA 教程：用 NeMo 把 Agent 失败转化为测试并修复 harness

NVIDIA 发布教程，演示用 NeMo Compass 从 agent trace 中定位失败，用 NeMo Eval Author 生成评测，再修改 harness 指令完成一轮优化。

信息来源：NVIDIA Technical Blog：Agentic AI / Generative AI · NVIDIA

教程 / 实战普通2026-11-03 23:53

Knowledge graphs, explained for AI memory (and how Palace uses one)

Most AI memory systems today come down to the same recipe. Split text into chunks, turn each chunk...

信息来源：DEV Community

教程 / 实战普通2026-11-03 23:30

How to Scale AI-Assisted Global Content Without Losing Local Relevance

Scaling content across countries has long created a tension between consistency and relevance. AI can...

信息来源：DEV Community

教程 / 实战普通2026-11-03 23:02

I Built an AI Team That Researches Stocks and Debates Investment Decisions 🤖

What if you had an entire team of AI agents researching stocks for you? Imagine one agent analyzing...

信息来源：DEV Community

教程 / 实战普通2026-11-03 22:11

Is Your Mac's Python Is Too Old for Your MCP Server?

I built an MCP server that pulls my Oura Ring data into Claude Desktop. It's a small Python project...

信息来源：DEV Community · Claude

教程 / 实战普通2026-11-03 22:11

GitHub Octoverse 2026: AI Agents, Citizen Developers, and the New Security Reality

TL;DR Code is being written three times faster than anyone can review it: GitHub logged...

信息来源：DEV Community

教程 / 实战普通2026-11-03 22:09

Which local model should a coding agent run?

One harness, same conditions, four dimensions, and the raw receipts of every call — this round, seven...

信息来源：DEV Community

教程 / 实战普通2026-11-03 22:00

Prompt Pad: Lock Your AI's Output Schema in Google AI Studio

If you've ever tried to parse an LLM response in code, you know the pain: the format changes slightly...

信息来源：DEV Community

教程 / 实战普通2026-11-03 21:56

Your Agent Has a Side Door: Testing MCP Policy Beyond the Tool List

At MCP Dev Summit Toronto, Accenture's Michael Forrester told a story about an employee who wanted...

信息来源：DEV Community

教程 / 实战普通2026-11-03 21:53

Rack Before You Remember

What racking wine teaches about agent memory The mead's lees on October 21, with the racking cane...

信息来源：DEV Community

教程 / 实战普通2026-11-03 21:41

Stop trusting your AGENTS.md: the drift-check that makes it a contract

Back in September I published Stop bloating your AGENTS.md: reference your conventions instead of...

信息来源：DEV Community

教程 / 实战普通2026-11-03 21:40

OpenRouter Alternatives: 5 AI API Gateways Worth Considering in 2026

When an application sends requests to more than one AI model, keeping those integrations organized...

信息来源：DEV Community

教程 / 实战普通2026-11-03 21:36

I Let AI Build a Feature Without Giving It the Full Context

If you give an AI a vague prompt, it will give you a confident answer. And that confidence will cost...

信息来源：DEV Community

教程 / 实战普通2026-11-03 21:30

How I keep faces the same when editing photos with Nano Banana and GPT Image

The most common complaint about AI photo editing is not quality. It's "that's not me anymore". You...

信息来源：DEV Community · GPT