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5597

当前页16 / 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2026-10-09 02:00

A PSD carries Photoshop's answer key. The UI has none.

This week I wrote a Photoshop file by hand. 390 bytes, two gray layers, the top one set to Soft...

信息来源：DEV Community

教程 / 实战普通2026-10-09 01:57

Elsewhere: Don't Remind Me. Give Me a Reason.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

信息来源：DEV Community

教程 / 实战普通2026-10-09 01:31

I Built a World With Rules. Then I Changed Them.

The Rules Are Hidden. The Timeline Isn't. What happens when you put something inside a...

信息来源：DEV Community

教程 / 实战普通2026-10-09 01:15

WanderLog: an offline field journal that answers "where did I see that kingfisher last time?"

A trail voice memo becomes structured sightings and walks, parsed by open-weight gemma3:4b on your own machine — no dashboard, no cloud, no typing.

信息来源：DEV Community

教程 / 实战普通2026-10-09 01:02

GitHub 漏洞赏金研究员 @vaib25vicky 如何挑选要调查的功能

GitHub 在网络安全意识月活动中专访了漏洞赏金项目 VIP 研究员 @vaib25vicky，其专注授权与访问控制方向。GitHub 今年重构了赏金机制，改为按质量而非数量奖励，并设立邀请制 VIP 计划，严重漏洞最高可获 3 万美元以上赏金。该研究员表示自己按功能而非漏洞类型开展研究，并强调 AI 只能充当助手，所有发现必须自行验证后才能提交。

信息来源：GitHub Blog

教程 / 实战普通2026-10-09 01:00

AI coding agents and Theo's Rust TypeScript compiler: the caveats

AI coding agents produced Theo's Rust TypeScript port. Its project benchmarks are promising; version matching and maintenance still need review.

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:57

Side Quest: an AI that sends you on a walk, and never learns where you are

This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 1 — Touch Grass. ✏️ TODO...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:57

AllergyGuard — Open-Source Offline Dietary Safety & Recipe Transformation Engine

What I Built Shared living arrangements create significant friction when one roommate...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:51

Your coding agent's work is lost in .md file

A good part of what my coding agents make now isn't code. A rollout plan. A comparison of three queue...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:37

The September cut took 17% of my Claude Code week. Subagents were taking 48%.

My Claude Code week started ending on Wednesday. I blamed the September 14 cut, like everyone on...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-09 00:33

What decision models can't do: six honest limits

Two of the six new local decision models are non-commercial, none of them explain themselves, and the confidence number is a claim until you bench it.

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:32

Stop Rebuilding Your Agent Loop Just to Train It with RL

Reinforcement learning for language agents has had an annoying operational tax. If you wanted to run...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:27

Breaking the Subword Boundary: Probing Architectural Vulnerabilities in Modern LLMs (ASTRAL-Bench on Kaggle)

This is a submission for the Kaggle Benchmarking Challenge When we look at standard LLM...

信息来源：DEV Community

教程 / 实战精选2026-10-09 00:21

LangChain 用 Stripe Link 和 Managed Deep Agents 构建可支付的智能体 Restock

LangChain 发布示例项目 Restock，一个在 Slack 上通过 Managed Deep Agents 运行的办公用品购买智能体，演示智能体如何安全完成支付。

信息来源：LangChain：Blog（RSS）

教程 / 实战普通2026-10-09 00:09

Claude 额度快速上手 Managed Agents

使用这些额度最快上手的方式是 Claude Managed Agents。在 Claude Code 中使用 claude-api 技能构建智能体，并用你的额度运行它： /claude-api managed-agents-onboard

信息来源：X：Claude Devs (@ClaudeDevs) · Claude

教程 / 实战普通2026-10-09 00:03

100 Actions, 110 Side Effects: A Crash Test for AI Agent Tools

Your agent chose the right tool. The arguments were valid. The action was allowed. Then the worker...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:03

Spring AI vs LangChain4j in October 2026: Both Shipped Big. Here Is How to Pick.

On September 25, 2026, both of the serious Java options for building AI applications shipped releases...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:02

CodeSmith Context Engineering: Append-Only Conversation History for Agents

Context Engineering: A Conversation History That Never Gets Rewritten Source version of...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:00

智能体代码审查的解剖：Tessl Code Review 如何重构 PR 审查流程

Tessl 发布博客拆解智能体代码审查的完整结构，包括标准、视角、发现、裁决、逐条回应与记忆六个环节。其 Tessl Code Review 内置正确性与数据完整性、安全与隐私、规模与韧性、可维护性与代码质量四个视角，以 skill 形式打包并并行运行，标准以 context 形式存放在仓库中。该工具可免费安装到代码仓库，在下一个 pull request 上运行首个循环。

信息来源：Tessl：产品与工程博客

教程 / 实战普通2026-10-08 23:57

Dev Tool GTM, Done Agentically

I'm Founding Technical GTM at Tabstack. I run GTM with a stack of agents and tools, and I stay in...

信息来源：DEV Community

教程 / 实战普通2026-10-08 23:54

Codex Pricing in 2026: Every Plan, Usage Limit and Credit Rate, Explained

Codex pricing is not one number: Codex is bundled into ChatGPT Free, Go, Plus, Pro, Business and Enterprise, each with its own usage allowance, and...

信息来源：DEV Community · ChatGPT

教程 / 实战普通2026-10-08 23:42

Building Resilient LLM Function Calling in Node.js: Circuit Breakers, Fallbacks, and Schema Validation

Function calling (a.k.a. tool use) is what turns an LLM from a text generator into something that can...

信息来源：DEV Community

教程 / 实战普通2026-10-08 23:38

TrustBoundary Bench: when JSON formatting masquerades as an AI security failure

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

信息来源：DEV Community

教程 / 实战普通2026-10-08 23:32

Acoustic Atlas: An Offline Open-Weight Model That Finds the Best-Sounding Places to Touch Grass

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

信息来源：DEV Community

教程 / 实战普通2026-10-08 23:30

EventSource can't POST. Your LLM stream needs it to.

You want to stream a chat completion. The response is a text/event-stream, so the browser's built-in...

信息来源：DEV Community

教程 / 实战普通2026-10-08 23:15

Cloudflare AI Bot Controls Can Affect Googlebot: What Website Owners Need to Check

Cloudflare has clarified that its AI traffic controls can affect more than specialist AI crawlers....

信息来源：DEV Community

教程 / 实战普通2026-10-08 23:00

Tripo 演示用 P2.0 几分钟搭建关卡 Blockout 素材包

Tripo 演示如何在几分钟内搭建关卡 blockout 素材包：先用 Tripo P2.0 生成完整环境，导入 Blender 后执行 Separate → By Loose Parts 拆分。作者称得到原生四边面拓扑、可用于生产的资产，将数小时的工作缩短到几分钟。

信息来源：Tripo（官方 X）

教程 / 实战普通2026-10-08 22:56

A Game That Replaces Doomscrolling, Powered by Local AI (Ollama)

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

信息来源：DEV Community · Ollama

教程 / 实战普通2026-10-08 22:55

Human-in-the-Loop

Should Agentic AI be in complete control of my codebase?

信息来源：DEV Community

教程 / 实战普通2026-10-08 22:31

How I Broke 37 Circular Imports in a Python Codebase With Claude Code

TL;DR I had a ~180k-line Python service with 37 circular import chains, held together by...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-08 22:31

What My AI Broke This Week #1: Nothing. It Was Me, Three Times

This week the agent broke nothing. I broke three things, and it spent the week politely proving...

信息来源：DEV Community

教程 / 实战普通2026-10-08 22:30

How to Protect Local Credentials from a Coding Agent with Agent Guard

ou have a local project that a coding agent needs to work on, and the same Mac also holds the AWS...

信息来源：DEV Community

教程 / 实战普通2026-10-08 22:13

5 Best AI-Native API Platforms for Developers in 2026

APIs have always been an important part of software development. But in 2026, they are becoming even...

信息来源：DEV Community

教程 / 实战普通2026-10-08 22:11

I asked 63 models the same 76 questions, with and without web search

The 2026 standard deduction for a single filer is $16,100. I asked 63 models what it was. Asked from...

信息来源：DEV Community

教程 / 实战普通2026-10-08 22:10

grasscast: a "should I go outside?" forecast that learns your taste from a few dozen outings (TabPFN + Temporal)

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

信息来源：DEV Community

教程 / 实战普通2026-10-08 22:09

Teaching AI Security: Hands-On LLM Hardening with Docker Desktop and Security Gateways

A complete guide to teaching AI security on student laptops with zero API costs using Docker, Ollama,...

信息来源：DEV Community · Ollama

教程 / 实战普通2026-10-08 21:57

Same bug, two IDs: an open RL dataset shares 15% of CyberGym's bugs, and a plain ID join misses 38% of them

Open RL environments are great for research. They also open another route for benchmark overlap. Here...

信息来源：DEV Community

教程 / 实战普通2026-10-08 21:53

I Tested Whether Frontier AI Can Do a Texas Real Estate Agent's Desk Work — Here's What 3 Models Taught Me (and What the 4th Taught Me About Benchmarks)

I'm a Texas real estate agent (eXp Realty). I spend my mornings doing desk work that has to be...

信息来源：DEV Community

教程 / 实战普通2026-10-08 21:37

Local LLM on a Laptop: 7 Surprising Speed Facts

Published: 2026-10-03 Table of contents What a local LLM actually is Why run a model on...

信息来源：DEV Community

教程 / 实战普通2026-10-08 21:28

Chrome DevTools MCP for Claude Code: Let It Read the Console, Network, and Performance (2-Minute Setup)

Stop being the copy-paste middleman between DevTools and Claude Code. The official Chrome DevTools MCP lets the agent read console errors, network req

信息来源：DEV Community · Claude