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8454
当前页93 / 212
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
Claude Code Stop hooks: making the agent finish its homework"
Every coding agent I use has the same habit. It does the work, writes a lovely summary, and stops....
信息来源:DEV Community · Claude
教程 / 实战普通
I Pre-Registered a Side Project. My Favourite Idea Did Not Survive.
Earlier this year I built a test-quality harness called killcheck and wrote about it here. The short...
信息来源:DEV Community
教程 / 实战普通
Let the model read the invoice, not approve it: an n8n pattern for AP automation
Most "AI invoice automation" demos stop at the fun part: a model reads a PDF and spits out JSON. The...
信息来源:DEV Community
教程 / 实战普通
🤖📞How AI Calling Agents Actually Work: STT, LLM, TTS & the 1-Second Rule Nobody Talks About
Ever wondered how an AI can call you, understand what you say, respond naturally, and even book an...
信息来源:DEV Community
教程 / 实战普通
Before You Call an LLM Endpoint "Nerfed": A Small Statistics Checklist in Python
Every few weeks someone posts "provider X is serving a watered-down model" with a handful of...
信息来源:DEV Community
教程 / 实战普通
Building a Resilient Vision-Guided Desktop RPA Engine in Python (Without $15k/yr Enterprise Licenses)
Ditch brittle coordinate clicks and predatory RPA fees. Build a self-healing, local vision-guided GUI automation engine in Python.
信息来源:DEV Community
教程 / 实战普通
ARD Solves Discovery. But What Happens After Your AI Finds the Tool?
Agentic Resource Discovery may solve one of the biggest scaling problems facing AI agents: How does...
信息来源:DEV Community
教程 / 实战普通
A gully cricket umpire you can shout at
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...
信息来源:DEV Community
教程 / 实战普通
How We Got Our Docs to 100 on the Agent-Friendly Docs Scorecard
We took routebase.dev from 87 to 100 on the open Agent-Friendly Docs Scorecard in one day. What failed, the four fixes, and the CDN header detail that nearly broke it.
信息来源:DEV Community
教程 / 实战普通
Build an Odoo MCP Server: Let AI Agents Query Your ERP (Sales, Inventory, Customers)
description: "A practical, ~200-line guide to building a read-only MCP server that connects Claude...
信息来源:DEV Community · Claude
教程 / 实战普通
Ankita v2.5.0: a desktop companion island that never misses an approval
Ankita v2.5.0: a desktop companion island that never misses an approval Version 2.5.0 of...
信息来源:DEV Community
教程 / 实战普通
Malware asks four AIs before it acts
Malware that has no orders inside: CLOSEDQUORUM asks DeepSeek, Qwen, Mistral and Gemini what to do next. The pattern is no longer in the binary, it is in the outbound traffic.
信息来源:DEV Community · DeepSeek / Qwen / Gemini
教程 / 实战普通
The model knew the rule. It still used last week's offset.
This is a submission for the Kaggle Benchmarking Challenge A Kaggle benchmark about the most boring...
信息来源:DEV Community
教程 / 实战普通
I Put ChatGPT in Charge of Claude Code
I Put ChatGPT in Charge of Claude Code I love Claude Code. I have spent an unreasonable...
信息来源:DEV Community · ChatGPT / Claude
教程 / 实战普通
I let an AI agent make an infrastructure change
I let an AI agent make an infrastructure change An AI agent recently took an...
信息来源:DEV Community
教程 / 实战普通
Fine-Tuning Reduced My LLM Token Usage by 66% — Here's What I Learned
Fine-tuning is usually discussed as a way to improve LLM accuracy. But there is another benefit that...
信息来源:DEV Community
教程 / 实战普通
I Linted 14 Public AI SDK Repos. 12 Ship a Call With No Token Ceiling.
A field study of 116 generation call sites across 14 public repositories, including five of the SDK vendor's own. The output cap is the one almost nobody sets.
信息来源:DEV Community
教程 / 实战普通
My checklist for reading computer use benchmarks
I read about 40 benchmark repositories and 230 sources to understand computer use scores. I came out with five questions I now ask before I believe any of them.
信息来源:DEV Community
教程 / 实战普通
How I built in-browser animated subtitles with Whisper on WebGPU (no upload)
Most "auto captions" tools start the same way: upload your video, wait, download the result. I wanted...
信息来源:DEV Community
教程 / 实战普通
One word beats two witnesses: "update" framing hijacks agent memory
All numbers come from pre-registered or clearly marked exploratory experiments; code and raw results...
信息来源:DEV Community
教程 / 实战普通
I Think We're Forgetting How to Be Bored
You know the moment. You're waiting for the kettle, or the elevator, or a page to load, or a friend...
信息来源:DEV Community
教程 / 实战普通
i built a place to keep the stories only one person in your family knows
every family has one person who knows all the stories. the recipe nobody wrote down. the night train...
信息来源:DEV Community
教程 / 实战普通
Touch Grass
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...
信息来源:DEV Community
教程 / 实战普通
I gave a language model hands inside Android — and it built me an app factory
How I built an AI assistant with a real shell inside Android — no PC, no cloud, no programming skills required.
信息来源:DEV Community
教程 / 实战普通
Prompt Injection Is a Data-Flow Problem Across Retrieval, MCP, and Tools
A system prompt says, “Never send customer data to external services.” A retrieved document says,...
信息来源:DEV Community
教程 / 实战普通
A Step-by-Step Guide to Create a Speaking Practice App with AWS Bedrock
Have you ever felt that rock climbing is easier than starting a conversation? Or does an unexpected...
信息来源:DEV Community
教程 / 实战普通
⚡️ 675 B LLM Shatters Expectations – One GPU, Sub‑Second Latency!
# Mistral Large 4: The First Open‑Weight Giant That Actually Works at Scale The...
信息来源:DEV Community · Mistral
教程 / 实战普通
Outside in 20: open AI that gives your phone a stopping point
Entry for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass. What I...
信息来源:DEV Community
教程 / 实战普通
Why My LLM Feature Cost More Than It Should: Field Notes on Prompt Caching, Cache Breakpoints, and the Timestamp That Killed Every Hit
Headline: Prompt caching saves money only when the cached prefix is byte-identical across requests,...
信息来源:DEV Community
教程 / 实战普通
AI Should Propose. Systems Should Verify.
AI Should Propose. Systems Should Verify. An AI agent can produce the correct action and...
信息来源:DEV Community
教程 / 实战普通
Stop dragging boxes in Draw.io: Turn plain text into interactive architecture maps
Every time I need to draw an architecture diagram or document a workflow, the same thing happens: I...
信息来源:DEV Community
教程 / 实战普通
Markdown Is Everywhere, and It All Started with a README
Original article: Markdown Is Everywhere, and It All Started with a README Have you noticed that...
信息来源:DEV Community
教程 / 实战普通
Vibe Coding Hasn't Won. The Industry Is Misreading Its Own Data.
Originally published at zalcro.ai/guides/vibe-coding-hasnt-won The most repeated statistic in...
信息来源:DEV Community
教程 / 实战普通
Structured outputs as application contracts
Your LLM Output Should Have a Contract, Not a Vibe So there I was, an AI engineer at a...
信息来源:DEV Community
教程 / 实战普通
Shopping for Skills and MCP Servers (Without Getting Burned)
A year or two ago, giving an AI assistant new abilities meant waiting for the company behind it to...
信息来源:DEV Community
教程 / 实战普通
I Built a 188M Mixture-of-Experts LLM From Scratch on a Free GPU
By Shivam Kumar, founder of VisionQuantech. This is the honest version — what's proven, what's...
信息来源:DEV Community
教程 / 实战普通
I let my AI agents merge to production. Once.
I automated almost my entire pipeline this year, and I'd fight you to keep it that way. An agent...
信息来源:DEV Community
教程 / 实战普通
Nine Bugs That Taught Me Reliability: Post-Mortem of a Zero-Cost Hybrid AI System
canonical_url: https://arielchangdev.github.io/angelina-finance-agent/ Building a hybrid local+cloud...
信息来源:DEV Community
教程 / 实战普通
Building an Agentic System in .NET, Part 6: Redaction, Audit and the Safety Layer
Prompt injection is OWASP's LLM01:2025, the top vulnerability in LLM based systems, and yet most...
信息来源:DEV Community
教程 / 实战普通
From Dev.to Comment to Production in 24h: Building an Inspectable Math Verification Contract in Pythos (and Fixing the Pearson Trap)
Earlier this week, I published an article here on DEV: "Why We Stopped Letting LLMs Do Raw Math:...
信息来源:DEV Community