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17 / 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2026-10-08 21:20

IRL Quest — AI That Gives You a Reason to Put Your Phone Down 🌿

IRL Quest 🌿 AI that gives you a reason to put your phone down. Built for the Hacktoberfest...

信息来源：DEV Community

教程 / 实战普通2026-10-08 21:15

Group chat orchestration: the pattern that works beautifully until it doesn't

I once watched a group chat of eleven agents spend forty minutes debating whether a research summary...

信息来源：DEV Community

教程 / 实战普通2026-10-08 21:05

We migrated 70,000 tests from Jest to Vitest. Yes, in 2 months

YOU got it right. We migrated 70,000 tests (reads: 70 thousand) from Jest to Vitest. The logical...

信息来源：DEV Community

教程 / 实战普通2026-10-08 21:02

My agent met the real web. 403s, challenges, and the coming tollbooth.

200 real URLs, one vanilla agent, zero challenge solving — 82.5% readable, 72 hosts blocking every AI crawler, zero x402 yet, and one site running a declared paywall with the gate up.

信息来源：DEV Community

教程 / 实战普通2026-10-08 21:00

I run a one-person game studio on Claude Code. Two months, 7 games, about $1 in ad revenue.

15 subagents, one producer, and the rules I had to write after things went wrong.

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-08 21:00

GPT-2 is the transformer plus five decisions, and inference is a different program

Originally published at cchinchilla.dev. Part 6 of From code to weights, a 12-part series on ML...

信息来源：DEV Community · GPT

教程 / 实战普通2026-10-08 20:45

IBM 如何将 Spyre 打造为原生 PyTorch 设备

IBM 通过 torch-spyre 将 Spyre 接入 PyTorch 的 device、allocator、stream 与编译器抽象，使其成为原生 PyTorch 设备。

信息来源：PyTorch：Blog（RSS）

教程 / 实战普通2026-10-08 20:45

EU AI Transparency Rules Take Effect in 2026: What Businesses Must Disclose

The EU AI Act will introduce new transparency duties for businesses that provide or deploy certain AI...

信息来源：DEV Community

教程 / 实战普通2026-10-08 20:29

How We Remove Watermarks from Video Fast: Motion-Adaptive Frame Skipping + Temporal EMA

(and the bug that froze our masks — a regression story about wiring performance switches to product...

信息来源：DEV Community

教程 / 实战普通2026-10-08 20:13

My AI memory bank grew to 240k tokens per session. Here is what I got wrong.

In December 2025 I shipped a small CLI called Context Bank. The idea was simple and, I still think,...

信息来源：DEV Community

教程 / 实战普通2026-10-08 20:05

The AI Security Paradox: Why Old Laws Create Digital Enclosures

If you think AI cybersecurity is currently being handled by smart people with everything under...

信息来源：DEV Community

教程 / 实战精选2026-10-08 20:00

Anthropic 用 Claude Managed Agents 构建定时智能体自动化的实践指南

Anthropic 发布基于 Claude Managed Agents（beta）的每日简报参考实现，按计划读取 Slack 和 GitHub 来源并向 Slack 发布简报。

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

教程 / 实战普通2026-10-08 19:52

TrailWhisper — The 100% Offline Nature Guide Built to Turn Off Your Screen

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 19:24

How to build an AI agent that reads 10-K Risk Factors

Day 8 of 30 Days of Search. A company can report strong growth and still disclose risks that...

信息来源：DEV Community

教程 / 实战普通2026-10-08 19:13

Building SortSense: A Local AI File Organizer Built in a Single Hack Day

Building SortSense: A Local AI File Organizer Built in a Single Hack Day hacktoberfest...

信息来源：DEV Community

教程 / 实战普通2026-10-08 18:57

Stop describing UI to your AI agent in words. Point at it.

I built an MCP server that lets you click a layer on your running web page or Android app, drag it, and hand the exact element to Claude Code, Cursor or Codex.

信息来源：DEV Community · Claude / Cursor

教程 / 实战普通2026-10-08 18:41

Freeze the Benchmark Card Before an Agent Score Ships

A coding-agent score is evidence only when the dataset, the metric, and the control surface are...

信息来源：DEV Community

教程 / 实战普通2026-10-08 18:33

How Our Engineering Team Uses AI, Part II: Meat Proxies

Originally published on metalbear.com. In January we published How Our Engineering Team Uses AI. The...

信息来源：DEV Community

教程 / 实战普通2026-10-08 18:21

Prompt Heist: a game where you talk your way past Gemma-powered guards (and learn how to defend AI apps)

What we built Prompt Heist is a browser game about prompt injection. You are the Cipher...

信息来源：DEV Community

教程 / 实战普通2026-10-08 18:14

Building TrialBridge: An AI clinical trial matcher built in a single hack day

We, Team Latent, built TrialBridge during the Hacktoberfest Hack Day Coimbatore x (INIT Club &...

信息来源：DEV Community

教程 / 实战普通2026-10-08 18:12

RepairVision: An Intelligent Repair Café Platform for Multimodal Fault Diagnosis and Sustainable Electronics Repair

Every week, perfectly fixable things end up in the bin. A kettle with a tripped fuse. A lamp with a...

信息来源：DEV Community

教程 / 实战普通2026-10-08 18:01

Prompt Heist: I Built an Ancient-Kingdom Game That Teaches AI Security

I built Prompt Heist for the Hacktoberfest Hack Day (Coimbatore x Init Club and Idea Club). It is a...

信息来源：DEV Community

教程 / 实战普通2026-10-08 17:53

700 manuscripts, 48 hours, three withdrawals. The verifier won.

OpenAI published hundreds of AI-produced math results before fully formalizing them. Two days later, three are gone — and that is the system working, not failing.

信息来源：DEV Community · OpenAI

教程 / 实战普通2026-10-08 17:52

Web Components did not fail!

My comment to yesterdays Dev.to post: Web components failed. We can fix them became a full post: ...

信息来源：DEV Community

教程 / 实战普通2026-10-08 17:47

My RAG system didn't need more agents. It never saw the evidence

GroundedDocs answers questions over a document set with exact citations and refuses when the evidence...

信息来源：DEV Community

教程 / 实战普通2026-10-08 17:39

FloraQuest: Offline-First Trail Botanist & Wild Forager (Tuned with Tinker, Backboard Memory, Deployed on Render)

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 17:27

I showed AI the buggy code. Its tests started protecting the bug.

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

信息来源：DEV Community

教程 / 实战普通2026-10-08 17:11

Your repo is not trusted context. What I changed after giving coding agents real repositories

I use coding agents across real repositories every day. I run a small security firm, and between...

信息来源：DEV Community

教程 / 实战普通2026-10-08 17:10

Spellcheck can't fix "chai GPT": building an LLM caption checker on $5 a month

Here's a line from YouTube's auto-captions on a lecture about attention in neural...

信息来源：DEV Community · GPT

教程 / 实战普通2026-10-08 17:09

I Benchmarked My AI Carb Counter on 400 Meal Photos: 8 Models, 1 Holdout Set

I build Soba, an iPhone app that looks at a photo of a meal and estimates the carbs in it. People...

信息来源：DEV Community

教程 / 实战普通2026-10-08 17:03

Trailnote: Plan the Walk. Make the Note. Put the Phone Away.

🌿 Trailnote — An AI Trail Companion That Tells You to Put Your Phone Away My submission...

信息来源：DEV Community

教程 / 实战普通2026-10-08 16:42

I built an AI browser extension in a month with an AI coding assistant. The code was the easy part.

Store reviews, users who couldn't reach the store, payments and analytics. What building a solo AI side-panel extension actually took.

信息来源：DEV Community

教程 / 实战普通2026-10-08 16:40

I Built an AI Chinese Tutor That Actually Knows the HSK Syllabus

Most AI chat tools are terrible language tutors. Ask a generic chatbot to practice Chinese with you...

信息来源：DEV Community

教程 / 实战普通2026-10-08 16:36

Enterprise SaaS Integration Checklist: APIs, SSO, Data & Monitoring

The biggest enterprise integration risk in 2026 is not AI. It is operational neglect. This week,...

信息来源：DEV Community

教程 / 实战普通2026-10-08 16:27

A Benchmark Card Makes an Agent Score Auditable

A published coding-agent score describes one frozen task slice, and it does not describe an entire...

信息来源：DEV Community

教程 / 实战普通2026-10-08 16:26

Seu classificador de intenções é 12 pontos pior em português: um benchmark de Laya, Strands Decider e embeddings Qwen3

Um benchmark reprodutível de pequenos modelos de decisão e de embeddings para classificar o objetivo do cliente em português do Brasil, e o que uma tradução paralela para o inglês revela sobre o custo do idioma.

信息来源：DEV Community · Qwen

教程 / 实战普通2026-10-08 16:23

Your intent classifier is 12 points worse in Portuguese: benchmarking Laya, Strands Decider and Qwen3 embeddings

A reproducible benchmark of small choice deciders and embeddings for customer-goal classification in Brazilian Portuguese, plus what a parallel English translation reveals about the cost of language.

信息来源：DEV Community · Qwen

教程 / 实战普通2026-10-08 16:20

From Finance to AI Engineering: 6 lessons I learned building a Multi-Agent Support system on Amazon Bedrock AgentCore

After ten years in asset management, I started a full-stack developer path in 2024 and spent my time...

信息来源：DEV Community

教程 / 实战普通2026-10-08 15:58

I gave an AI my first app spec. It cut half of it and took the other half too literally

A native app on both stores, in five languages, built by one person with an AI as the developer. This...

信息来源：DEV Community

教程 / 实战普通2026-10-08 15:38

Retrieval confidence can't tell your RAG chatbot when the answer is missing

I ran 65 questions against our own knowledge base and checked which ones the retrieved text actually...

信息来源：DEV Community