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184 / 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
My 5 trading bots reported every sale as a success. None of them ever sold anything.
I spent a few months building an automated trading system: five bots wired together in n8n, a couple...
信息来源:DEV Community
教程 / 实战普通
个人AI如何判断任务优先级与时机
Kim 探讨个人AI的核心挑战:AI能完美完成任务,却可能把时间花在错误的事情上。她认为智能体需理解个人情境与优先级变化,记忆与纠错机制是关键--记住截止日期、关联过往承诺、察觉计划变更,并让假设可见可更新。真正考验是处理混乱日常:捕捉易被忽略的承诺并解释为何需要关注,最终把决定权留给用户。
信息来源:X:Kim (@kimmonismus)
教程 / 实战普通
Compare Against the Schema They Shipped, Not the One You Expected
My harness flagged the model for sending the wrong arguments. It compared what the model actually...
信息来源:DEV Community
教程 / 实战普通
You Aren't Choosing an AI Tool. You're Choosing Who Gets Paged at 2 AM.
Part of AI Leadership in the Real World — how leaders turn scattered pilots into governed, adopted,...
信息来源:DEV Community
教程 / 实战普通
Gitignore Is Not a Model Boundary
Gitignore will not stop a coding agent from reading the files you refused to commit. The privacy...
信息来源:DEV Community
教程 / 实战普通
Securing a RAG Pipeline — The Threats I Designed Against and the Ones I Didn't
Most RAG tutorials end when the pipeline answers a question correctly. That's where the security...
信息来源:DEV Community
教程 / 实战普通
I Built a RAG Pipeline From Scratch Without Using LangChain — Here's Every Decision I Made
Every RAG tutorial starts the same way. from langchain import ... Enter fullscreen mode ...
信息来源:DEV Community
教程 / 实战普通
Your prompt system has no tests, and that is why you cannot tell it is broken
Tags: ai, python, testing, showdev Code fails loudly. A prompt system fails in silence, and it...
信息来源:DEV Community
教程 / 实战普通
The Overhead Ratio Is Lying to You — I Built an AI Tool to Prove It
This is a submission for Weekend Challenge: Generosity Edition What I Built GlassPocket —...
信息来源:DEV Community
教程 / 实战普通
I let software run my station for 8 weeks, unattended. What I learned.
Hi, my name is Yaniv Morozovsky, and I have worked in the radio industry for more than three decades....
信息来源:DEV Community
教程 / 实战普通
I built an AI agent that clicks buttons on real websites (and here is what I learned about not trusting the model)
Support chatbots answer questions. They have got good at it. But a lot of support is not a question —...
信息来源:DEV Community
教程 / 实战普通
The Frozen Route Workshop
The projector showed a 201. A student clapped once, then went quiet when the whiteboard still said...
信息来源:DEV Community
教程 / 实战普通
The money was already approved. It stopped at a sheet of paper nobody could read.
This is a submission for Weekend Challenge: Generosity Edition TL;DR: The money was already...
信息来源:DEV Community
教程 / 实战普通
OpenPledge: See Exactly Where Your Donation Goes (Blockchain + AI for Charity)
OpenPledge is a transparent micro-donation app. Every gift is recorded on the Solana blockchain, thanked with an AI note and a real voice message, and shown in an open impact dashboard — so you can trust exactly where your money went.
信息来源:DEV Community
教程 / 实战普通
Mozaik in Plain English: A Gentle Introduction to Concurrent AI Agents
Most AI agent tutorials show you a pipeline. Agent A extracts data, hands it to Agent B, B hands it...
信息来源:DEV Community
教程 / 实战普通
This blog is written by an agent — here's the publisher, and the three times it shipped something else
The essays on this blog argue, at some length, that a tool's success message is not evidence....
信息来源:DEV Community
教程 / 实战普通
Inside the Memory Decision Loop: How AI Agents Decide What to Remember, Update, or Forget
Most people who add "memory" to an AI agent do the same thing: embed every message, throw the vector...
信息来源:DEV Community
教程 / 实战普通
Claude Code 创作者 Boris Cherny 谈如何学习用好 Claude Code:不存在唯一诀窍
Claude Code 创作者 Boris Cherny 在 Y Combinator Startup School 2026 上被问如何学会用好 Claude Code 时表示,别听 LinkedIn 网红,模型使用没有所谓一招制胜的诀窍。
信息来源:X:Rohan Paul (@rohanpaul_ai) · Claude
教程 / 实战普通
Flash Onyx 2.4: I held a 31B local model to Fable 5.1's bar until it stopped guessing the answer first
A prompt-only release for a local gemma4 model. 81 lines out, 73 in, and the whole point is that it now works the number out before it says it.
信息来源:DEV Community
教程 / 实战普通
I Ran DeepSeek V4 Flash Across Two DGX Sparks Over Ethernet
TL;DR: Two 128GB GB10 computers can run the official FP8 DeepSeek V4 Flash 0731 checkpoint as one...
信息来源:DEV Community · DeepSeek
教程 / 实战普通
18 malicious npm packages are still remote-controlling AI coding agents (verified today)
TL;DR While building a public advisory database for the Model Context Protocol...
信息来源:DEV Community
教程 / 实战普通
How AI context compression actually works, part 1
I build Compresso, a local AI compression layer, using different techniques like Headroom, Rtk and...
信息来源:DEV Community
教程 / 实战普通
Beyond Vibes: Architecting Closed-Loop AI Agents with Local SLMs, Deterministic Evals, and Human Learning Loops
How to build a production-grade drafting agent on local SLMs (Llama 3.2 3B) using deterministic Python verification, tri-state guardrails, QWK-calibrated evals, and continuous few-shot learning.
信息来源:DEV Community · Llama
教程 / 实战普通
Your AI context gets worse the longer you work
I had my own infrastructure context server running behind my editor, the way I do every day, and...
信息来源:DEV Community
教程 / 实战普通
AI Writes Locally Correct Code. Which Is Why Your Linter Is Silent
I've been writing Android for thirteen years. For the last two of them, a large share of the code...
信息来源:DEV Community
教程 / 实战普通
The receipt should come from the person who received it
This is a submission for Weekend Challenge: Generosity Edition What I Built Every...
信息来源:DEV Community
教程 / 实战普通
The Harness Is Not Intelligence: What Is Actually Improving in AI Agents?
A few months ago, I wrote about a feeling I still have today: AI models, and especially coding...
信息来源:DEV Community
教程 / 实战普通
HealthMitra: An AI Voice Health Companion for India, Built in 10 Days
How I built HealthMitra, a Hindi/English voice agent for India's health-access gap, on LiveKit and Murf Falcon — plus three real bugs it took to get the multi-agent handoffs working.
信息来源:DEV Community
教程 / 实战普通
I parsed 76,801 lines of my own Claude Code history. Three things nearly broke my parser.
Claude Code writes every session to ~/.claude/projects as JSONL. I wanted to know what I'd actually...
信息来源:DEV Community · Claude
教程 / 实战普通
13 of 14 Models Write Messier Code Than the Human Who Fixed the Same Bug
We measured whether AI-written code is messier than human-written code, across 500 real bugs where a...
信息来源:DEV Community
教程 / 实战普通
We Could Have Shipped on Local Models Alone
Update — v0.1.0 released. CauterRule is now live on GitHub and PyPI. It turns repeated agent...
信息来源:DEV Community
教程 / 实战普通
Your Google ADK Agent Has Four Places to Put Context. Choose Carefully.
The first version of an agent usually has one place for context: the prompt. The user request goes...
信息来源:DEV Community
教程 / 实战普通
OpenRouter 实战避坑指南:同一模型在不同供应商表现差异巨大
Olly(iMessage AI 助手)作者基于经 OpenRouter 路由的开源模型处理约 1800 万条消息(约三分之一经 OpenRouter 开源模型)的实战经验,总结使用 OpenRouter 的十大坑。
信息来源:Mohamed Moustafa 技术博客(网页)
教程 / 实战普通
Principal Propagation with an MCP Server on SAP BTP — End to End
A practical guide to wiring up an MCP server on SAP BTP Cloud Foundry so that an LLM agent's requests reach your on-premise ABAP system under the calling user's identity, not a shared service account.
信息来源:DEV Community
教程 / 实战普通
I Added Circuit Breakers to a Rails App and Had to Patch the Gem Twice
📖 Originally published on meridianbuild.dev my engineering blog documenting the real bugs and...
信息来源:DEV Community
教程 / 实战普通
JetBrains says rtk costs more. My dashboard says 11.6M saved. Both are right.
JetBrains spent about $320 of API credit in July to test rtk, the shell proxy tens of thousands of us...
信息来源:DEV Community
教程 / 实战普通
Hybrid Search in Postgres with pgvector: Field Notes on HNSW, tsvector, and Why Pure Vector Search Missed Exact Matches
Headline: pgvector is a Postgres extension that adds vector column types and...
信息来源:DEV Community
教程 / 实战普通
GiveRoute — Stop Dumping Donations, Route What’s Actually Needed
This is a submission for Weekend Challenge: Generosity Edition What I Built Anyone who...
信息来源:DEV Community
教程 / 实战普通
Harness Engineering: Designing the Runtime Capability Envelope Around an Agent
"Please be careful" is not a security control An agent at a Fortune 500 financial services...
信息来源:DEV Community
教程 / 实战普通
Here’s the trust layer I built to prevent AI's mistakes
The moment I stopped trusting the agent I built a trading agent. It worked in backtests. Clean...
信息来源:DEV Community