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8440
当前页54 / 211
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
Enterprise Software in 2026: From First Conversation to Production Ownership
A research-backed, end-to-end enterprise delivery playbook: negotiation, specifications, SLAs, AI agents, quality gates, metrics, and accountable ownership.
信息来源:DEV Community
教程 / 实战普通
You QA'd 12 AI conversations last month. Your AI had 3,400 conversations. Here's the sampling plan that actually finds problems.
The owner of a home-services franchise did the diligent thing: every Friday, she pulled two random AI...
信息来源:DEV Community
教程 / 实战普通
[Spanish] Entrenando un kantoku artificial — Capítulo 1: por qué no usé una red neuronal
Primero, ¿qué es el gateball? El gateball es un deporte de equipo que nació en Japón en...
信息来源:DEV Community
教程 / 实战普通
How a 270M-parameter model on your phone turns a dictated note into contacts
Circles is a birthday reminder built around people’s circles: a friend, their partner, their kids,...
信息来源:DEV Community
教程 / 实战普通
邵猛计划本地部署 Ming-3.0-tts 做阅读与配音助手
邵猛打算本地试跑 0.5B 的 Ming-3.0-tts 声音合成与克隆模型,看中其体积小可本地运行。他正为儿子的学习做 AI 辅助,继开源打字游戏后,计划做书籍阅读助手(支持全篇通读、停顿或指定区域提示)和视频德语配音,结合 ASR 与多模态视频理解做音画同步。他立 Flag 一周后投入日常学习并开源。
信息来源:X:邵猛 (@shao__meng)
教程 / 实战普通
Gemini 4 Argon vs GPT-6 Astra vs Claude Opus 5.5: What Google’s New Model Actually Wins
Every frontier launch now arrives with a table where the new model wins. Gemini 4 Argon is more...
信息来源:DEV Community · GPT / Claude / Gemini
教程 / 实战普通
Doze: teach it once. Let the AI sleep.
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady. ...
信息来源:DEV Community
教程 / 实战普通
A Map, Not a Megadump: Sentinel-IR-MCP 0.2.0 Adds TypeScript, 0.2.1 Makes Missing Analysis Visible
When an AI agent opens a codebase, should it read every file first, or should it get a compact map...
信息来源:DEV Community
教程 / 实战普通
How to Prevent AI Agents from Accidentally Injecting GPL Violations into Commercial Codebases: A LicenseGuard MCP Server
How to Prevent AI Agents from Accidentally Injecting GPL Violations into Commercial...
信息来源:DEV Community
教程 / 实战普通
SlothTidy: A Zero-Friction, 100% Local AI File Daemon That Organizes Your Downloads While You Rest 🦥
Stop dragging PDFs and screenshots out of ~/Downloads. SlothTidy uses small open-weight models via Ollama and llama.cpp to automatically classify, rename, and organize your files 100% offline.
信息来源:DEV Community · Llama / Ollama
教程 / 实战精选
Anthropic 指南:何时把子智能体合并进主 Agent 循环
Anthropic Applied AI 团队发布指南,讲解何时把 orchestrator 下的路由器、规划器和领域子智能体合并进单个主 Agent 循环。文中对比显示,带 skills 的单智能体在质量上常优于一提示全包和子智能体设计,且成本和延迟更低,一家客户改用单循环后运行时间约快 2x。
信息来源:Claude:Blog(网页) · Claude
教程 / 实战普通
Cerebras 如何用 59 片 WSE-3T 晶圆部署 3T 参数 Kimi K3
Cerebras 详解如何把约 3T 参数的 Kimi K3 拆分到多片 WSE-3T 晶圆上运行,实现 1000-2000+ tokens/s 的多万亿参数模型推理。
信息来源:Cerebras:Blog(网页) · Kimi
教程 / 实战普通
My Video Editor Now Writes Audio Description for Your Videos
A while ago I wrote about Ultra Video Editor, the free, open-source video editor I've been building....
信息来源:DEV Community
教程 / 实战普通
Ithaka Gave You the Journey: AI-Assisted Development
A three-year reflection on AI-assisted development, from early ChatGPT experiments to the specification-driven discipline behind DevSpark.
信息来源:DEV Community · ChatGPT
教程 / 实战普通
Gemma 4 checks my Pix receipts while I sleep: 12 of 12 verdicts right, even when it misreads
This is a submission for the Hacktoberfest 2026 Open-Source AI Challenge, Week 3: Slow and Steady. ...
信息来源:DEV Community
教程 / 实战普通
I'm 16 and spent a year training my own 780B language model. Here's what I learned
Hi, I'm Afonso. I'm 16, and for about the past year I've been building Ganymede, my own large...
信息来源:DEV Community
教程 / 实战普通
There Are Two Dockerfiles. Your Agent Should Touch Neither.
Flisk's local image is not the image you ship. A coding agent that "fixes" either file is editing the wrong source of truth.
信息来源:DEV Community
教程 / 实战普通
I tuned an OCR pipeline for weeks. A vision model beat it in nine seconds.
I spent weeks tuning a local OCR pipeline. Downscaling, adaptive thresholding, per-word confidence...
信息来源:DEV Community
教程 / 实战普通
What interactive video world models actually do on one GPU (and a tool to check)
Interactive video "world models" are having a moment — Matrix-Game, HY-World, and others generate...
信息来源:DEV Community
教程 / 实战普通
LazyReader - a TL;DR machine that runs entirely in your browser (no servers, no keys, no excuses)
Disclosure: this project and post were created with AI assistance - the code was written by an AI...
信息来源:DEV Community
教程 / 实战普通
DuckDB 2.0's agent mode is a footer, and -json throws it away
The first time I ran DuckDB 2.0 today, it printed one line before my query: duckdb agent mode on:...
信息来源:DEV Community
教程 / 实战普通
SkillSentry — The Laziest Way to Keep Your AI Agent's Skills Honest
This is a submission for the Hacktoberfest Week 3 DEV Challenge Prize Categories: Best Use of...
信息来源:DEV Community
教程 / 实战普通
I Fixed WebGPU on Linux. Then Forgot How I Did It.
I spent a ridiculous amount of time trying to get WebGPU working properly on my Linux machine. I...
信息来源:DEV Community
教程 / 实战普通
GAI: Let AI Generate Your Git Commit Messages Locally
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady. ...
信息来源:DEV Community
教程 / 实战普通
Your AI agent runs with all your permissions. I built a cage for each tool call, in Rust
A subagent got a simple task: read a project's docs and say how to run it. It read docs/readme.txt,...
信息来源:DEV Community
教程 / 实战普通
Why We Built a Self-Improving AI Coding Runtime Using Only Python's Standard Library (Zero Dependencies)
Runesmith is an open-source runtime that wraps whatever AI model you have (a free Gemini or Groq key,...
信息来源:DEV Community · Gemini
教程 / 实战普通
Google Clarifies Search and AI Visibility Controls for Website Owners
Google has updated its guidance for website owners on controlling how content appears in Google...
信息来源:DEV Community
教程 / 实战普通
How to Get Historical Stock Prices via Search API
Day 21 of 30 Days of Search. TL;DR To get historical stock prices with Valyu Search API,...
信息来源:DEV Community
教程 / 实战普通
39 screenshots and not one useful name, so a local Gemma names them for me
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...
信息来源:DEV Community
教程 / 实战普通
Who Watches the Watchers? I Built a Tamper-Evident Seal for Agent Guardrails
Today OpenAI disclosed something that should make every agent builder uncomfortable: its own AI...
信息来源:DEV Community · OpenAI
教程 / 实战普通
I built a Claude Code skill that de-slops AI-generated web design
You know the look. You ask any AI to "make me a landing page" and you get: giant rounded cards,...
信息来源:DEV Community · Claude
教程 / 实战普通
I built a human approval gate my coding agents can't click themselves
My coding agents kept doing the same thing: printing "please click Allow" into a terminal nobody was...
信息来源:DEV Community
教程 / 实战普通
AI Made Coding Cheaper. So Why Is Building Software Still So Expensive?
I can generate a full authentication flow with a database schema, API routes, and unit tests in under...
信息来源:DEV Community
教程 / 实战普通
OpenClaw 用户构建方式对比
你在终端里构建 OpenClaw 用户在时间线里构建 我们不一样 看 Roboclaw 和 @vincent_koc 在这里构建: https://team.openclaw.ai/chat/roboclaw/x-2112983910850363434-baseten-decision-models-e70fd350 这是 Roboclaw 创建的 PR:https://github.com/openclaw/openclaw/pull/179819
信息来源:X:OpenClaw (@openclaw)
教程 / 实战普通
🛑 Why I Refuse to Give AI Root Access: Meet LazyLoop AI for Paranoid, Lazy Developers 🦥
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...
信息来源:DEV Community
教程 / 实战普通
Teaching a 35B voice model to speak Turkish on one 16 GB card
Fish Audio's Drama 3 is a 35 billion parameter mixture of experts model that turns text into speech...
信息来源:DEV Community
教程 / 实战普通
The Controller That Runs Your AI Data Center Had Hard-Coded Credentials
TL;DR On September 22, 2026, NVIDIA disclosed CVE-2026-65113, a hard-coded-credentials...
信息来源:DEV Community · NVIDIA
教程 / 实战普通
Multi-tier model routing on GKE: balancing Gemini 4 Argon reasoning depth with latency and cost
Build a high-throughput model routing gateway on GKE to dynamically route requests between Gemini 4 Argon, Gemini 3.8 Flash, and local Gemma 4 models.
信息来源:DEV Community · Gemini
教程 / 实战普通
Reviewing AI-generated PRs: the 10-minute checklist
AI-generated PRs have a tell: they're too clean. Perfect formatting, thorough comments, confident...
信息来源:DEV Community
教程 / 实战普通
Codex Website Assessment Skill Hints at Faster Issue Triage for Developers
A Codex-oriented skill appears to point developers toward a more repeatable way to assess whether a...
信息来源:DEV Community