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39 / 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
🎬 I Stopped Making Motion Graphics Manually. Here’s How I Use AI Instead.
What if you could create professional motion graphics for your videos without spending hours manually...
信息来源:DEV Community
教程 / 实战普通
Maya 2 TTS: Eleven Indian Languages, One Awkward Folder Name
Maya Research open-sourced Maya 2 TTS for 12 languages under Apache 2.0. What shipped, where the benchmark claims stop, and the 5 GB catch nobody mentions.
信息来源:DEV Community
教程 / 实战普通
anthropic-sdk-go 1.81 traces your Claude calls and forwards your OTel baggage
Originally published on ImportStatic. If your Go service registers a global OpenTelemetry tracer...
信息来源:DEV Community · Claude
教程 / 实战普通
Day 09/90: When Retrieved Content Becomes an Instruction — Prompt Injection in RAG
What happens when a RAG system retrieves the right document, but that document tells the AI to ignore...
信息来源:DEV Community
教程 / 实战普通
My Crawler Now Tells You What It Missed
PageSift 0.80: extraction results that warn when they're incomplete, a rebuilt PDF layer that preserves structure, hand-written Office/EPUB parsers, and a fuzz pass — with correctness held to a no-speed-regression rule.
信息来源:DEV Community
教程 / 实战普通
I gave 8 models a sandbox and no task. Here is what each one did with the freedom.
Every benchmark tells a model what to do. I wanted to see what happens when nobody does. So I gave...
信息来源:DEV Community
教程 / 实战普通
Where else should this diff have gone? Five shapes from 90 daily code reviews
One view out of three. Two templates out of three. Three prompt builders out of four. Six languages...
信息来源:DEV Community
教程 / 实战普通
I broke my own tool's scoring model and rebuilt it. Here's what changed in rubric v2
When I published the calibration study showing the GEO score does not predict citations, one question...
信息来源:DEV Community
教程 / 实战普通
Three traps I fell into while building a behaviour lab for AI agents
A methods note. One person's lab; a full run of one model costs $1-41. Every claim below comes from a...
信息来源:DEV Community
教程 / 实战普通
👻 Memory Ghost: Bringing Forgotten Files Back to Life with Local AI | Gemma 3 + Ollama
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...
信息来源:DEV Community · Ollama
教程 / 实战普通
The agent ended its turn. That is not the same as done.
A frontier model ended two unattended builds after 16 and 37 of 300 allowed calls with the words \"I'll get to them next.\" Turn-end is not completion. Here is a stop-check that reads the diff and re-runs the tests before your pipeline bel…
信息来源:DEV Community
教程 / 实战普通
Your agent needs a stand-in, not the password: a surrogate-token proxy in Node.js
Meta's Muse gives its agent a stand-in token and swaps the real credential in at the network boundary. After two October incidents around that agent, here is how to build the same boundary for your own stack in a single Node.js file with n…
信息来源:DEV Community
教程 / 实战普通
百度千帆Token Plan个人版实战训练营收官:四节课回顾Agent降本与上下文工程
百度千帆Token Plan个人版实战训练营正式收官,四节课覆盖入门、进阶、实战与案例,演示用一套额度创建API Key接入DeepSeek、GLM等主流模型。进阶课拆解Coding Agent烧Token的根因,指出粗放上下文管理单次请求可能携带超10万tokens。案例课以Token Plan为资源管控底座,结合DeepSeek Harness开发养老照护决策平台。
信息来源:公众号:百度智能云(文心) · DeepSeek / GLM
教程 / 实战普通
What breaks when you run coding agents on gpt-oss-120b locally
I built Stepswitch, a free, MIT-licensed orchestrator for coding agents. It splits a task into steps...
信息来源:DEV Community · GPT
教程 / 实战普通
GhostShell AI — Hacktoberfest Week 4: Ghost in the Machine
This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 4: Ghost in the...
信息来源:DEV Community
教程 / 实战普通
EU AI Act Transparency Rules Begin: What AI Chatbot Providers Must Change
The European Commission has begun enforcing new EU AI Act transparency requirements that affect AI...
信息来源:DEV Community
教程 / 实战普通
5 Best Open-source LLM Gateways 💎
TL;DR An open-source LLM gateway gives applications one place to connect to model...
信息来源:DEV Community
教程 / 实战普通
Test the migration before it tests production: rehearsing AI-generated database changes
The pre-merge checklist catches a bad migration's shape: no rollback, a table rewrite hiding in one...
信息来源:DEV Community
教程 / 实战普通
Find the Concurrency Where Free Stops Being Cheaper
Free capacity has no price, but it does have a shape. That shape bends at some concurrency level you...
信息来源:DEV Community
教程 / 实战普通
Secrets Leak Through Your Tooling, Not Your Prompt
Most secret leaks in AI-assisted work do not happen in the sentence you type. They happen in the...
信息来源:DEV Community
教程 / 实战普通
Prompt injection in AI agents: real attack patterns and the defenses that actually work
Why a better system prompt won't save your AI agent from prompt injection, and the structural limits that will.
信息来源:DEV Community
教程 / 实战普通
Your Website Changed. Did the AI Get the Memo?
The gap between publishing a correction and seeing it reflected in an AI-generated answer is becoming...
信息来源:DEV Community
教程 / 实战普通
Data apps, defined: levels, principles, and a scorecard builders can actually use
The Data App Framework, v2.0 · October 2026 Venkata M Sangaraju, Sr. Database Engineer On October 8,...
信息来源:DEV Community
教程 / 实战普通
How I built a zero-install Remote MCP Server for Cursor & Claude (and why local npm packages suck)
Anthropic’s Model Context Protocol (MCP) is arguably the most exciting architectural standard to hit...
信息来源:DEV Community · Claude / Cursor
教程 / 实战普通
NecroCode: The Open-Source Codebase Necromancer & Spectral Auditor 👻
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...
信息来源:DEV Community
教程 / 实战普通
No MCP? No problem. How I got Instinct AI to call a flight API
Instinct is an AI assistant you text on WhatsApp, iMessage or SMS. It works through the accounts you...
信息来源:DEV Community
教程 / 实战普通
How we built an MCP App for a cash-on-delivery store in Uzbekistan
By the Birinchi Shop team In Uzbekistan most online shopping still ends with cash. You pick a...
信息来源:DEV Community
教程 / 实战普通
I Built an Agent Loop by Hand. Then I Tried to Migrate It to the OpenAI Agents SDK
A few weeks ago I wrote a small Kubernetes operations agent without using any agent framework. It is...
信息来源:DEV Community · OpenAI
教程 / 实战普通
Your AI Agent Doesn't Need More Prompts. It Needs an Operating System.
If you run an AI agent on anything real — a production repo, a scheduled job, a business process —...
信息来源:DEV Community
教程 / 实战普通
Never Trust an AI That Says “I’ve Checked”
A solo builder in Japan on designing for the day updates stop: static hosting, honest missing-data...
信息来源:DEV Community
教程 / 实战普通
Doc-driven development for AI Agents (ddd skill)
Stop reading code. Start reading what your app does. Project page · Github repo AI writes the...
信息来源:DEV Community
教程 / 实战普通
The MCP Transport Layer Blind Spot
This was first published on my site and is cross-posted here; the version on my site is canonical and...
信息来源:DEV Community
教程 / 实战普通
Building an annotation-driven MCP server in Java
Exposing a Java method to an AI agent should take one annotation, not a protocol implementation. How I built java-mcp-server on Spring Boot 3, and what I'd change next.
信息来源:DEV Community
教程 / 实战普通
I Joined an AI Competition With 7 Days Left. 940 Teams Had the Same Score.
So I went sideways instead. Here is what happened, and what a week spent teaching a computer to read...
信息来源:DEV Community
教程 / 实战普通
Calaveras for Dead Code: an in-browser ofrenda where an open model writes epitaphs for abandoned software 💀🌼
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...
信息来源:DEV Community
教程 / 实战普通
AI Workflow Orchestration
AI Workflow Orchestration A deep-dive walkthrough of building AI pipelines that run...
信息来源:DEV Community
教程 / 实战普通
How to Measure Whether AI Document Processing Reduces Insurance Intake Review Time
Quick answer: Measure intake review time per submission packet, from receipt to ready-to-quote, and...
信息来源:DEV Community
教程 / 实战普通
Get rid of Tab-Hell
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
Titanic Séance: ask the 891 passengers what the night would have done to you
Titanic Séance is a small web app where you tell the spirits who you would have been in April...
信息来源:DEV Community
教程 / 实战普通
How I built undo for my desktop AI companion: a backup before every destructive write
An AI companion that can edit your files will eventually delete the wrong one. That is not a...
信息来源:DEV Community