AI 专题

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 articles4767

当前页8 / 120

UpdatesPermanent archive

Category articles

按发布Time从新到旧 · 每页 40 stories

TutorialsOrdinary2026-10-11 18:08

Golden Hour: an open model that finds your 40 minutes outside, and where to spend them

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

Source: DEV Community

TutorialsOrdinary2026-10-11 18:02

My browser and IDE won't work until I go outside, and a model on my laptop checks that I really did

AI was going to increase our productivity. It is also apparently going to replaces the human race...

Source: DEV Community

TutorialsOrdinary2026-10-11 17:54

Do AI models understand daily life in Pakistan? lakh/crore, PKT and Urdu tested

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

Source: DEV Community

TutorialsOrdinary2026-10-11 17:27

Your MCP Config Is the Actual Security Boundary. Nobody Audits It

Your MCP config is the actual security boundary. Nobody audits it. I read a lot about MCP...

Source: DEV Community

TutorialsOrdinary2026-10-11 17:26

I Built an Offline Supply-Chain Auditor for Claude Code Mods (stdlib-only Python)

Your Claude Code mods run shell commands with your privileges. A lifecycle hook is one curl | sh away...

Source: DEV Community · Claude

TutorialsOrdinary2026-10-11 17:24

Semantic DLP: Can AI Models Catch the Data Leak?

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

Source: DEV Community

TutorialsOrdinary2026-10-11 17:21

DrishtiPath: Offline AI Navigation Through What You See

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

Source: DEV Community

TutorialsOrdinary2026-10-11 17:07

I let a 322M local model judge every shell command my coding agent runs

laya-guard: A local safety net for coding agents Coding agents run shell commands all the...

Source: DEV Community

TutorialsOrdinary2026-10-11 17:01

Tech Is Brutal Right Now. Stay or Go? Let's Think Clearly.

You sent 200 applications. You heard back from three. Two were rejections and one was a "we've moved...

Source: DEV Community

TutorialsOrdinary2026-10-11 16:02

Your AI Agent Sent That Email Twice. Here's the Idempotency Fix

An agent calls send_email. The mail API is slow, the HTTP client gives up at 30 seconds, and the...

Source: DEV Community

TutorialsOrdinary2026-10-11 15:50

How 8-bit quantization shrinks an LLM to a quarter of its size — and why a single outlier weight can quietly ruin it

A beginner-friendly walk through INT8 quantization: one running example, the math in plain words, and why a single large weight decides how well it works. With an interactive playground.

Source: DEV Community

TutorialsOrdinary2026-10-11 15:31

What If Your AI Rewarded You Credits for Closing the App? 🌱

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

Source: DEV Community

TutorialsOrdinary2026-10-11 15:31

I Improved My Website’s SEO Score from 77 to 96 Using One AI Prompt

How I used an AI-powered SEO evaluation, generated a fix prompt, and let Codex handle the...

Source: DEV Community

TutorialsOrdinary2026-10-11 15:28

Frolic: Tiny Outdoor Side Quests Powered by Open-Source AI

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

Source: DEV Community

TutorialsOrdinary2026-10-11 15:19

Why I Built DSLint: A Design System Linter for Figma

How repeated design-review feedback inspired me to build a plugin that detects design-system drift,...

Source: DEV Community

TutorialsOrdinary2026-10-11 15:03

Goblin Mode: Nature Scavenger Bingo — An Offline-First AI Nature Hunt

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

Source: DEV Community

TutorialsOrdinary2026-10-11 14:51

PageTwins: I Planted One Defect on 100 Landing Pages. Which AI Graders Noticed?

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

Source: DEV Community

TutorialsOrdinary2026-10-11 14:44

fieldcards: a local Gemma turns your photos into a printed scavenger hunt

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

Source: DEV Community

TutorialsOrdinary2026-10-11 14:26

My weather app says '60% rain' all day. So I made TabPFN tell me which hours to go touch grass.

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

Source: DEV Community

TutorialsOrdinary2026-10-11 14:22

Building QuoteThought: How We're Creating a Home for Quotes, Poetry, and Creative Writing

The internet has plenty of places to publish content. You can share a thought on social media,...

Source: DEV Community

TutorialsOrdinary2026-10-11 14:01

TrailMate: an offline AI companion that gets you outside

What I Built Most AI apps keep us on our screens. TrailMate is built to do the opposite:...

Source: DEV Community

TutorialsOrdinary2026-10-11 13:58

TerraPulse 🌿 — The Screenless Outdoor & Trail Agent

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

Source: DEV Community

TutorialsOrdinary2026-10-11 13:43

Outward: an adventure story that only moves forward when you go outside

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

Source: DEV Community

TutorialsOrdinary2026-10-11 13:36

No, Seriously. Neural Networks Cannot Produce Genuine Intelligence.

Hey everyone 👋, I want to start by saying something that I know is going to make a certain type of...

Source: DEV Community

TutorialsOrdinary2026-10-11 13:30

Sphinx — your neighbourhood, turned into riddles

What I Built The screen shows one line: I am stone, flat, and written on. One of...

Source: DEV Community

TutorialsOrdinary2026-10-11 13:23

The Last Responsible Moment: All Three Models Passed—So What Did the Benchmark Actually Measure?

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

Source: DEV Community

TutorialsOrdinary2026-10-11 13:03

55+ Shipped Games Later — 10 Unity Lessons I Wish I Knew on Day One

Five years ago I thought being a good Unity developer meant knowing the API. Then I started...

Source: DEV Community

TutorialsOrdinary2026-10-11 12:37

FitGuru: Building a Private, On-Device AI Workout Coach in Kotlin(Multimodel AI)

published: false description: "We built a phone-side workout coach at Innovhacks 4.0 - MediaPipe...

Source: DEV Community

TutorialsOrdinary2026-10-11 11:55

Normalization vs denormalization in a real Postgres schema: what I fixed, and the copy I kept

If you own a product, you should know it all the way down. In many products, the database is the main...

Source: DEV Community

TutorialsOrdinary2026-10-11 11:46

Replit App Not Working? Why It Breaks After You Publish, and How to Fix It

Replit app not working after publishing, showing a blank page or a disabled database? What 296 real reports show breaks in production, and how to fix each one.

Source: DEV Community

TutorialsOrdinary2026-10-11 11:35

Touch Grass, Babu: I Built an Offline AI Mom Who Locks Your Apps Until You Touch Grass

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

Source: DEV Community

TutorialsOrdinary2026-10-11 11:08

Benchmarking Frontier AI on Curved Tire Sidewall OCR

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

Source: DEV Community

TutorialsOrdinary2026-10-11 10:57

LORE WALK: I built an app that wants you to put it away

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

Source: DEV Community

TutorialsOrdinary2026-10-11 10:37

Paper Trail: Gemma writes my neighbourhood into a paper zine, so my phone can stay home

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

Source: DEV Community

TutorialsOrdinary2026-10-11 08:59

What LLMs 'Know' That You Don't Know They Know: Stop Inventing Prompt DSLs and Ride 50 Years of Unix Pre-Training Gravity

Why did a 1976 Makefile (Part 3.6) and a 1983 Unix init.d directory (Part 3.7) outperform 2,000 lines of English prompt rules? Because prompt engineering is static symbol linkage against 50 years of pre-trained computer science canon.

Source: DEV Community

TutorialsOrdinary2026-10-11 07:23

My Release Pipeline Refused to Ship My Release. It Was Right.

I pushed the v0.2.0 tag. The release workflow built the wheel, generated the SBOM, wrote the...

Source: DEV Community

TutorialsOrdinary2026-10-11 07:22

The Missing Piece: Why AI Models Hallucinate Answers When They Should Abstain

This is a submission for the Kaggle Benchmarking Challenge "The answer isn't always there. Does...

Source: DEV Community

TutorialsOrdinary2026-10-11 06:37

Does your coding agent understand you in your native language?

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

Source: DEV Community

TutorialsOrdinary2026-10-11 06:15

AI Agents Are Not Users: Building an Identity Model That Reflects That

In April 2026, an AI coding agent deleted the entire production database of PocketOS, a B2B platform...

Source: DEV Community

TutorialsOrdinary2026-10-11 06:08

theAuth Audit Trails: Compliance Logging for AI Agent Actions

theAuth is open-source auth for AI agents and humans. Star the repo on GitHub · Read the docs · Run...

Source: DEV Community