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5618

当前页58 / 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 / 实战精选2026-09-25 20:00

Anthropic 员工实测 Claude Code 的 effort 档位如何影响 Fable 5.1 与 Opus 5.5 输出质量

Anthropic 员工 Thariq Shihipar 深入评测了 effort 设置对 Claude Code 中 Fable 5.1 和 Opus 5.5 输出的影响。

信息来源：Anthropic：Claude.dev 开发者博客（RSS） · Claude

教程 / 实战普通2026-09-25 19:50

Claude on Google Cloud workshop | NYC | 9/30

On Wednesday, September 30, Anthropic and Google Cloud are co-hosting a hands-on developer workshop...

信息来源：DEV Community · Claude

教程 / 实战普通2026-09-25 19:42

Not Another LLM: I Tried Laya, a 421M-Parameter AI Decision Engine

What happened when I tried a model that doesn't generate text at all I spend a lot of...

信息来源：DEV Community

教程 / 实战普通2026-09-25 19:38

Agentic DevOps with GitHub Actions and Microsoft Foundry

As AI agents become a bigger part of the conversation around software development, I started thinking...

信息来源：DEV Community

教程 / 实战普通2026-09-25 19:19

How Does a Vector Database Work?

Most explanations of vector databases turn into a wall of math. Here's the one-minute version...

信息来源：DEV Community

教程 / 实战普通2026-09-25 19:07

The Cryptid Field Office: an AI triages sightings, a person signs off

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2026-09-25 19:05

Thirty-Four Out of Thirty-Four. Then Zero Out of Ten.

I added one column to my crawler dashboard — verified against checked, counted per path. On the pages that exist, every check passed. On three paths that do not exist, all of them claiming to be ClaudeBot, every check failed.

信息来源：DEV Community

教程 / 实战普通2026-09-25 19:01

AIで増えたドキュメントの認知負荷を、Mermaidとカスタムテーマで軽くする

...

信息来源：DEV Community

教程 / 实战普通2026-09-25 19:00

I almost translated my product. The demand was 90.6% English, and most of it wasn't from English-speaking countries

I had localisation on the roadmap. Italian first, since that's where I am and where a visible share...

信息来源：DEV Community

教程 / 实战普通2026-09-25 18:55

A blank page and a green test: the bug an agent can't see

A template that cannot resolve a path renders an empty string. For a human that is a blank spot on the page. For an agent it is a green test. Here is how the library turns silence into something a test can see.

信息来源：DEV Community

教程 / 实战普通2026-09-25 18:53

Your ledger is losing money and your tests will never tell you

Most of the bugs I have chased in payment systems were not logic bugs. The formula was right. The...

信息来源：DEV Community

教程 / 实战普通2026-09-25 18:52

Your first AI SRE: I gave the worst hour of on-call to a team of agents, and they diagnosed the incident, scored their own confidence, and opened the fix.

The most dreaded, most mechanical part of on-call is the first hour of root-cause analysis. Turns out...

信息来源：DEV Community

教程 / 实战普通2026-09-25 18:47

11810799000 doesn't want his 12324312000 to be called 0.000038195235563656617

The title is the puzzle. It's a sentence where every word has been turned into a number. Can you...

信息来源：DEV Community

教程 / 实战普通2026-09-25 18:42

1Presence: What We Built and How It Works

Originally published on the 1Presence blog on 27 August 2026, the day we launched. Jon here, founder...

信息来源：DEV Community

教程 / 实战普通2026-09-25 18:30

EU Welcomes First IPCEI AI Design, Building a Cross-Border AI Sovereignty Push

The European Commission has welcomed the design of the first Important Project of Common European...

信息来源：DEV Community

教程 / 实战普通2026-09-25 18:22

UMKM-Bench: I tested 8 LLMs on how Indonesians really text online shops

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

信息来源：DEV Community

教程 / 实战普通2026-09-25 18:00

How to test whether a model can tell your MCP tools apart

You can read your own tool descriptions all day and not know whether a model can tell them apart. I...

信息来源：DEV Community

教程 / 实战普通2026-09-25 17:57

The Hard Part of AI Coding Agents Isn't Writing Code — It's Preserving Engineering Context

AI coding agents have become surprisingly good at reading a codebase and making changes across...

信息来源：DEV Community

教程 / 实战普通2026-09-25 17:42

Refactor Agent Skills for 10x Cost Efficiency

Engineering teams embracing modern coding agents frequently hit the same inflection point: developer...

信息来源：DEV Community

教程 / 实战普通2026-09-25 17:30

Combining Vector and Full-Text Search with Reciprocal Rank Fusion

A practical guide to fusing two ranked search result lists into one better list using RRF, with correct Python and SQL code.

信息来源：DEV Community

教程 / 实战普通2026-09-25 17:03

Can AI Detect a Market Crisis Before Humans Do?

How artificial intelligence is learning to recognize the hidden signals of financial stress before...

信息来源：DEV Community

教程 / 实战普通2026-09-25 17:00

How to Monitor GPU Usage and Temperature on a Remote Server

Your training run died at epoch 47. The logs show nothing useful — just a silent hang and a CUDA...

信息来源：DEV Community

教程 / 实战普通2026-09-25 16:56

How fast is Laya on a CPU? Reading the 4-core server benchmarks

Can you run Laya without a GPU? Yes, and the upstream project now publishes enough CPU measurements...

信息来源：DEV Community

教程 / 实战普通2026-09-25 16:42

The Hidden Bill: Where AI Agent Costs Actually Come From

The model's per-token price is the cheapest part of running an AI agent. The real bill comes from the loop around it. Here's where the money actually goes.

信息来源：DEV Community

教程 / 实战普通2026-09-25 16:24

I tried to catch Next.js contradicting itself. It never did.

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2026-09-25 16:14

Your API's newest users are agents...

Who called your API last? For us, the honest answer is more and more often an agent. Claude Code...

信息来源：DEV Community · Claude

教程 / 实战普通2026-09-25 15:59

如何在无需重建的前提下为遗留软件加入 AI

为遗留软件添加 AI 不必重写系统，把 AI 当作叠加在现有软件之上的新层即可。常见做法包括 API 与中间件层、基于既有数据的 RAG、事件驱动集成，以及 Martin Fowler 提出的 Strangler Fig 模式。建议先从搜索、摘要、报表等只读场景起步，并注意商业语言模型 API 按 token 计费带来的持续运营成本。

信息来源：Artificial Intelligence News（网页）

教程 / 实战普通2026-09-25 15:57

A stop rule that trusts one score is worse than a dumb budget

Field note 009. A replication of a published agent-loop benchmark, and what it hides. ...

信息来源：DEV Community

教程 / 实战普通2026-09-25 15:56

Stop Paying Full Price For Every LLM Call

An LLM bill has 2 parts: rate and volume. You can adjust both. But a default request barely changes...

信息来源：DEV Community

教程 / 实战普通2026-09-25 15:08

I built a public, cryptographically signed test registry for AI agents (student project)

Hi everyone! 👋 I’m a final-year BTech CSE student. The Problem I Noticed As AI agents start doing...

信息来源：DEV Community

教程 / 实战普通2026-09-25 14:52

Building FraudGraph Agent: Autonomous Fraud Investigation & Policy-Compliant Next-Best Action with TigerGraph

How we combined TigerGraph 4.2.5, Model Context Protocol (MCP), calibrated Graph ML, Vector GraphRAG, and deterministic policy enforcement to build an enterprise-grade autonomous fraud investigator.

信息来源：DEV Community

教程 / 实战普通2026-09-25 14:37

An Agent That Knows When It Doesn't Know - Fraud Investigation on TigerGraph

What We Built We built an agentic fraud investigation system on TigerGraph for the...

信息来源：DEV Community

教程 / 实战普通2026-09-25 14:28

I wanted an AI tutor that would notice when I didn't actually get something, so I built one

I've been working on something called Vectra, and I've been thinking about this problem for a...

信息来源：DEV Community

教程 / 实战普通2026-09-25 14:26

Building TRACE: Graph-Based Fraud Investigation with TigerGraph and Gemini

A fraud alert tells you where to look. It does not tell you what happened. An unfamiliar device...

信息来源：DEV Community · Gemini

教程 / 实战普通2026-09-25 14:22

How I Built a Multi-Asset Investment Platform with Next.js, PostgreSQL, Docker and AI

Most investment dashboards are easy to build when every asset comes from one provider. The real...

信息来源：DEV Community

教程 / 实战普通2026-09-25 14:02

Cosine Gating Won't Save You From Sycophancy: A Self-Refutation Observed by Three Judges

A pilot said the gating made the model MORE sycophantic (+10pp). The full run said +0.5pp of pure noise. Three independent judges then all said: not only useless, slightly harmful. A 38-hour CPU-run experiment log, with data.

信息来源：DEV Community

教程 / 实战普通2026-09-25 14:00

Bringing TypeSafe AI Jev Model to Go

The Jev model from TypeSafe AI introduces a System One approach, delivering structured data rapidly...

信息来源：DEV Community

教程 / 实战普通2026-09-25 13:50

应用宝团队端对端开发流程的关键点 - AI 负责认知，脚本负责执行 - 长链路必须状态化 - 知识库必须结构化 - Agent 必须职责隔离 - 执行步骤必须脚本化

信息来源：X：洪明 (@hongming731)

教程 / 实战普通2026-09-25 13:50

TigerGraph Agentic Fraud Investigation Hackathon 2026 Team GOA-T

Team Thota Sai Eswar Srinath — Team Leader & Agentic Architecture Nikhil Kadiri —...

信息来源：DEV Community

教程 / 实战普通2026-09-25 13:34

I spent hours on App Store screenshots, so I built a tool that makes them

The most useful thing I learned building this: if you want an image model to work well with text,...

信息来源：DEV Community