AI Tutorials & Practice
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。
Category articles4779
当前页64 / 120
UpdatesPermanent archive
Category articles
按发布Time从新到旧 · 每页 40 stories
TutorialsOrdinary
I build a Tool for Open source Maintainers
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...
Source: DEV Community
TutorialsOrdinary
Benchmarking Jev: what a decision model can (and can't) do in an agent harness
Model under test: jev-1.13.0 · Date: Sep 2026 · Code & raw results:...
Source: DEV Community
TutorialsOrdinary
AI crawlers in WordPress logs: GPTBot shows up, Google-Extended never does
Google-Extended and Applebot-Extended, two of the names that robots.txt guides list most often for...
Source: DEV Community
TutorialsOrdinary
Hands-off DJ for my child's baptism: Spotify, djay, an iPad, and an agent that ignored the brief
My child's baptism party was at a pub. I wanted proper music — a black music jukebox, not a Spotify...
Source: DEV Community
TutorialsOrdinary
I was sure Figma would reject my cover art. The email asked about something else.
A few years ago, my Figma skills were roughly limited to whatever I could make from templates...
Source: DEV Community
TutorialsOrdinary
What If Your AI Agent Never Had to Leave the Browser? (Demo 🚀)
I haven't written anything lately because, honestly, I just didn't have the headspace for it. There...
Source: DEV Community
TutorialsOrdinary
Omnichannel AI agents: sharing long-term memory between a voice and a chat agent with Amazon Bedrock AgentCore Memory, Strands and Amplify Gen 2
🏃 TL;DR In the first article I built semantic product search on Amazon DynamoDB Vector...
Source: DEV Community
TutorialsOrdinary
Building and Training LLM from scratch (No GPU)
Building a 10M Parameter LLM from Scratch on Google Colab Free Tier How I trained a...
Source: DEV Community
TutorialsOrdinary
SpellBook of Skill: The Twin Project Nobody Asked For, But I Built Anyway 🧙🏻♂️
Overview Hey everyone 👋 A while back I launched Spellbook of Prompt, my curated...
Source: DEV Community
TutorialsOrdinary
Drafts, audit logs, or 'don't': three ways platforms handle AI agent writes
Sanity writes to a draft by default, Notion logs it afterwards, Supabase tells you not to connect at all. Three quotes from three docs, and the gap all three leave open.
Source: DEV Community
TutorialsOrdinary
OpenAI + Vercel Makes the Architecture Even More Interesting
On September 10, 2026, Vercel announced integration for building and deploying OpenAI Agents API...
Source: DEV Community · OpenAI
TutorialsOrdinary
I Built My Own AI Copilot for Excel Desktop — Without Paying for Microsoft 365 Copilot
I use Excel a lot. And like many Excel users, I eventually wanted something more powerful than...
Source: DEV Community
TutorialsOrdinary
Building a Client-Side DAG Runtime with Kahn's Algorithm
How to build a high-performance, browser-native DAG workflow execution engine using Kahn's topological sort, safe variable interpolation, and wavefront concurrency.
Source: DEV Community
TutorialsOrdinary
Your AI-built app works. That doesn't mean it's safe to take money on.
Lovable, Bolt, Replit, v0 and Cursor will get you from an idea to a deployed, working product in a...
Source: DEV Community · Cursor
TutorialsOrdinary
I automated most of my DB Admin job — then open-sourced it!
2am. Checkout's down. I'm on the floor, laptop on a pizza box, praying to EXPLAIN ANALYZE. Again. 8...
Source: DEV Community
TutorialsOrdinary
The Leverage Subsidy: When the Backstop Builds the Tail It Truncates
Fat Tail Notes · Part 15 · V10-P4 Part 14 showed that a transparent backstop gets front-run, and...
Source: DEV Community
TutorialsOrdinary
How to stop AI from confidently shipping broken code (a pattern that actually works)
The scariest diff passed every test — and would've lost a customer money. The scariest diff AI ever...
Source: DEV Community
TutorialsOrdinary
When is an aggregate really anonymous? Differencing attacks on AI query layers
A sum is not anonymization. Whether a number over special-category personal data (Art. 9 GDPR) says...
Source: DEV Community
TutorialsOrdinary
A 1,145-Star CLI Promised "Nothing Leaves Your Machine". It Executes a Hidden Payload at Import Time.
A 1,145-star dev tool that claimed to run entirely locally fetched and executed code at import time. The five static checks that now gate every repo I install for my coding agents - and where they still fail.
Source: DEV Community
TutorialsOrdinary
An AI builds to the contract it can read, not the one you meant
AI Harness Engineering · Essay Four · derek wang (derekwang85) A century before anyone called...
Source: DEV Community
TutorialsOrdinary
The Great Regulatory Illusion: Why Bureaucracy Will Break AI (And Why Open-Source Meritocracies Must Save It)
Imagine a world where training a model with too many parameters or open-sourcing weight files lands...
Source: DEV Community
TutorialsOrdinary
A six-asset acceptance test for AI game art generators
Disclosure: I maintain FrameSprite, a browser-based AI game asset and sprite animation tool. This...
Source: DEV Community
TutorialsOrdinary
Dev log #22 Tearing out the old: Deleting 3,800 lines of legacy p2p code
Hi, glad you found your way here. I'm Yash, a developer who contributes to open source, mostly p2p...
Source: DEV Community
TutorialsOrdinary
Is AI Cheugy?
cheu·gy ˈchü-gē - cheugier; cheugiest. slang: uncool, unfashionable It's happened enough times...
Source: DEV Community
TutorialsOrdinary
Building an MCP Server for Your Django App: What We Learned Doing It for Real
MCP — the Model Context Protocol — has gone from a niche Anthropic spec to something every AI-forward...
Source: DEV Community · Claude
TutorialsOrdinary
A Working CLAUDE.md/AGENTS.md Template You Can Copy Today
If you've added a CLAUDE.md or AGENTS.md file to your repo and felt like your coding agent still...
Source: DEV Community · Claude
TutorialsOrdinary
Securing WebMCP Tools
Building a security workbench for the tools agents call on the web The...
Source: DEV Community
TutorialsOrdinary
When AI Agents Hammer tools/list: Building a Caching-Aware MCP Server (SEP-2549)
Part 2 of 2. Part 1 covered statelessness; here I tackle caching. Part 1 was about statelessness,...
Source: DEV Community
TutorialsOrdinary
I Rebuilt Jev's Structure with Qwen (Not Its Capabilities)
Jev does not generate an answer string. It makes a typed decision in one forward pass. So,...
Source: DEV Community · Qwen
TutorialsOrdinary
Your AI Agent Can Call APIs Now
Your AI Agent Can Call APIs Now. Who Is Checking What It Does? The real problem with agentic AI...
Source: DEV Community
TutorialsOrdinary
Stage 5 of enterprise AI adoption: governance hardening
This is part 5 of a series that started with the full reference diagram in part 0, covered identity...
Source: DEV Community
TutorialsOrdinary
A New Model Dropped. Don't Just Swap the ID.
The new model is out. The benchmarks look great. Your provider has already scheduled the sunset date...
Source: DEV Community
TutorialsOrdinary
Beyond the Veto: Implementing 'Conditional Approval' and Dynamic Risk Tuning in AI Trading Systems
Beyond the Veto: Implementing 'Conditional Approval' and Dynamic Risk Tuning in AI Trading...
Source: DEV Community
TutorialsOrdinary
5 Coding Habits That Improved My Problem Solving in 2026 (In the AI Era)
AI can write code faster than ever. But there's a problem. Writing code and solving problems are...
Source: DEV Community
TutorialsOrdinary
One Predicate, Two Meanings, Three Bugs: Building a Contradiction Resolver with the Sanity App SDK
by shahbaz_ali. Built for the DEV × Sanity Challenge. #sanitychallenge When two of your company's...
Source: DEV Community
TutorialsOrdinary
Jev vs a 310M encoder I trained myself: 750 rows, three tasks, two different winners
TL;DR: I ran three Japanese classification tasks (250 rows each, same gold labels) through six...
Source: DEV Community
TutorialsOrdinary
Our 3 a.m. batch job was running at Beijing's afternoon peak rate
DeepSeek's API charges two different prices for the same tokens. Which one you pay depends on what...
Source: DEV Community · DeepSeek
TutorialsOrdinary
CLAUDE.md rule vs PreToolUse hook: both held 5 of 5, then the user said 'I authorize it'
We gave Claude Code the same "never edit protected/" rule two ways, as one line in CLAUDE.md and as...
Source: DEV Community · Claude
TutorialsOrdinary
Nova Adiutrix: My Second Agent Built My First Project's To-Do List
TL;DR: I shipped the second project in my AWS nanodegree, an AI support agent on Amazon Bedrock....
Source: DEV Community
TutorialsOrdinary
Fliproom: a room changeover is a content problem
Built for Sanity Challenge, Path Two. What I Built Fliproom turns a room changeover into...
Source: DEV Community