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5606
当前页34 / 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 / 实战普通
Le puse muros a mi agente de IA (y ahora rompe la web, pero porque se lo pido)
Empecé a trabajar mis proyectos con agentes de IA usando Codex, y después llegó Claude Code. Al poco...
信息来源:DEV Community · Claude
教程 / 实战普通
Trust nothing your AI assistant tells you it did published: false
I use an AI every day for real work: reading mail, linking documents to files, drafting letters,...
信息来源:DEV Community
教程 / 实战普通
Aleph Alpha 开源德语模型 Kolibri 解析:MoE 架构如何兼顾主权与效率
Aleph Alpha 于 2026 年 10 月 3 日以 Apache 2.0 许可发布面向德英双语的开放权重模型 Kolibri 1,总参数 781 亿、每 token 仅激活 34.6 亿,用 UniBPE 分词器使德语文本比 GPT-5 的分词器少 15% token,并原生支持 262,144 token 上下文(验证至 1,048,576)。
信息来源:Hacker News:AI 热帖 · GPT
教程 / 实战普通
How I built my own AI tools for a small NGO instead of buying software
Small nonprofits have the same paperwork as companies and none of the budget. When I started running...
信息来源:DEV Community
教程 / 实战普通
From Messy Scripts to Production Minded Architecture: Refactoring Job Copilot
Introduction Building a portfolio project often starts with a single script and a dream....
信息来源:DEV Community
教程 / 实战普通
How I Track My AI Coding Costs Per Project (and Bill Them to Clients)
Your Claude Code spend is a real line in your costs. Here's how to attribute it to projects — from raw JSONL logs to invoice-ready numbers.
信息来源:DEV Community · Claude
教程 / 实战普通
Is your AI agent worth its tokens? We measured it with TigerGraph
Title: Is your AI agent worth its tokens? We measured it with TigerGraph Tags: ai, rag, graph,...
信息来源:DEV Community
教程 / 实战普通
MCP for tour guides: building a remote MCP server with ~100 tools and OAuth
I work on Your Next Tours, an app tour guides use to broadcast live audio to their group from their...
信息来源:DEV Community
教程 / 实战普通
I'm building a companion island for my desktop AI assistant: approvals, a mascot, and a 14px wake strip
I'm building a desktop AI assistant, and it has a permission problem that no amount of prompt...
信息来源:DEV Community
教程 / 实战普通
Your AI Cost Model Is Already Wrong: Tokenizers, Context Cliffs and Session Hours
TL;DR Gemini 2.5 Flash Image shuts down on 2 October 2026. That is days away. If any...
信息来源:DEV Community · Gemini
教程 / 实战普通
I fine-tuned Qwen3-14B for my AI companion app for $1.30. The hard part wasn't the model
Soulor AI is an AI companion app with persistent memory and five relationship stages, from Stranger...
信息来源:DEV Community · Qwen
教程 / 实战普通
I Built My First Claude Code Mod Without Writing Code: Claude Wrote It, Validated It, and Hot-Reloaded It
I wanted one thing: to see my context window without typing /context. Not a dashboard. Not a plugin...
信息来源:DEV Community · Claude
教程 / 实战普通
How I Built a Turn-Based AI Speaking Examiner with Node.js
IELTS Speaking is a live interview that runs 11 to 14 minutes. An examiner asks a question, you...
信息来源:DEV Community
教程 / 实战普通
A Sanity Check for AI-Generated Cyber Attack Reconstructions
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
The Developer Triangle: DSA, AI, and the Skill That Actually Gets You Hired (as a Beginner)
If you're just starting out as a developer, you've probably noticed that everyone's advice...
信息来源:DEV Community
教程 / 实战普通
Tala: Free Audio-to-Text for My Designer Friend (No Signup, No Credit Card)
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...
信息来源:DEV Community
教程 / 实战普通
Homelab census: 41 containers, one 6 GB GPU, and where my AI agents run
A homelab census of 41 Docker and 9 LXC containers, and how one 6 GB GPU decides which AI agents run on local Ollama, OpenRouter or a subscription.
信息来源:DEV Community · Ollama
教程 / 实战普通
AI Agent Cost per Month: The Token Maths, Worked Out
AI agent cost per month, worked out: a reproducible token formula, a small-business support example, and current prices from Anthropic, OpenAI and Google.
信息来源:DEV Community · OpenAI / Claude
教程 / 实战普通
Fine Print: an agent that knows when the FAQ and the Official Rules disagree
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
API deprecation for AI models: what breaks when a model is retired
API deprecation for AI models: how OpenAI and Anthropic retire models, the notice you get, what breaks in your code, and why only open weights survive.
信息来源:DEV Community · OpenAI / Claude
教程 / 实战普通
I got tired of tedious dataset curation, so I built REDDIZ — an open-source vision training workstation
Over the past few months, I've spent an unhealthy amount of time fine-tuning Flux and SDXL LoRAs and...
信息来源:DEV Community
教程 / 实战普通
Why "I Searched and Found the Opposite" Was a Methodologically Broken Claim
This week I ran a small experiment: search for evidence that people want confirmation before an AI...
信息来源:DEV Community
教程 / 实战普通
Sizing a sovereign, air-gapped AI stack for oil and gas health, safety and environment (HSE) in Pakistan
GPU memory arithmetic, model licences and a three-year cost comparison for an on-premises HSE platform that never sends data out of Pakistan.
信息来源:DEV Community
教程 / 实战普通
AI Value Creators: Além da Mentalidade de Mero Usuário de IA
Passei os últimos dias lendo AI Value Creators, livro lançado pela O’Reilly reunindo Rob Thomas, Paul...
信息来源:DEV Community
教程 / 实战普通
OfferLens: A Privacy-First Job Offer Reality Checker for Candidates
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built Site...
信息来源:DEV Community
教程 / 实战普通
O SDLC agêntico: um caminho pra sair do loop
Por que se você está inserido no loop, você é o gargalo. A armadilha do loop manual: quando a...
信息来源:DEV Community
教程 / 实战普通
LangGraph Tutorial: 5 Proven Steps to Fix a Fragile Agent
LangGraph Tutorial: 5 Proven Steps to Fix a Fragile Agent I had an agent that worked in the demo and...
信息来源:DEV Community
教程 / 实战普通
Opus 5.5 Video Examples: 13 Code-Rendered Clips and Their Prompts
Claude Opus 5.5 makes video by writing the animation as code. A browser draws that code one frame at...
信息来源:DEV Community · Claude
教程 / 实战普通
🛑 Stop Writing Code Like It's 2026: How I Built an Autonomous Agent Pipeline That Actually Works
"The biggest innovation in software engineering isn't new JavaScript framework - it's the shift from...
信息来源:DEV Community
教程 / 实战普通
An AI hardware advisor that walks every path — and gets its math checked by the rules in Sanity
What I built An agent that answers "what computer do I need to run this AI model?" —...
信息来源:DEV Community
教程 / 实战普通
A junior asked me how I knew the code was wrong. I couldn't answer him.
We were pairing on a Thursday. Nothing dramatic. A junior on my team, maybe eight months in, sharp,...
信息来源:DEV Community
教程 / 实战普通
Receipt Desk: show me the line, or it isn't done
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
I made CodeRabbit's reviews a third less noisy with an open-source Claude Code skill
AI code review has a noise problem. On a public benchmark of 50 real pull requests, CodeRabbit raised...
信息来源:DEV Community · Claude
教程 / 实战普通
5 RAG mistakes that looked fine in the demo and broke in production
Every RAG demo works. You pick five questions, the system answers them beautifully, and everyone...
信息来源:DEV Community
教程 / 实战普通
RL 5: Learning Automata and stochastic environments (1961–1974)
Quick recap, in case you're jumping in from Blog 4. Arthur Samuel's checkers program learned by...
信息来源:DEV Community
教程 / 实战普通
EchoBook: Turning Grandpa's Rambling Voice Memos into a Family Recipe Book, Fully Offline
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend. What I...
信息来源:DEV Community
教程 / 实战普通
My Parents Kept Asking "Is This SMS a Scam?" So I Built Her an Offline AI That Explains Every Message
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...
信息来源:DEV Community
教程 / 实战普通
My Test for a Safety Guard Deleted the Real Revenue Ledger
A field note from the autonomous Claude Code agent I run every day on one Windows PC. The numbers...
信息来源:DEV Community · Claude
教程 / 实战普通
Fine-tuning a 7B model needs 112 GB. The model is only 14 GB of it.
Ask how much memory it takes to fine-tune a 7B model and the instinct is "the model's 14 GB in fp16,...
信息来源:DEV Community
教程 / 实战普通
The More Context You Give Your AI Coding Agent, the Worse It Can Get
We keep hearing the same advice: Give the AI more context. Add the README. Add AGENTS.md. Add...
信息来源:DEV Community