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5601
当前页97 / 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
How I Purged 121 Leaked Secrets From 10 Years of Git History With Claude Code
TL;DR I inherited a 10-year-old repo with ~28,000 commits and a nasty surprise:...
信息来源:DEV Community · Claude
教程 / 实战普通
From User Query to Execution: Building a Multi-Agent System with LangGraph
Hi everyone: Recently i was working on multiagent system with langrapgh and after completing, i...
信息来源:DEV Community
教程 / 实战普通
Building Complete RAG AI Package- AI Curt
Every developer working with Large Language Models eventually hits the same wall. You have the...
信息来源:DEV Community
教程 / 实战普通
Agentic Testing Is Changing QA: When AI Agents Can Run, Debug, and Retest Your Tests
From CI failure to verified fix: how AI agents can run, diagnose, repair, and retest automated...
信息来源:DEV Community
教程 / 实战普通
My support agent wrote "I can see you were charged". Both lookups had failed.
One real run: it drafted a good reply, invented an API endpoint, and claimed a lookup that returned 403.
信息来源:DEV Community
教程 / 实战普通
Odoo 19 ships a real AI agent. I read the source to see what happens after it writes.
Short answer, so you can leave if that is all you came for: nothing reads the row back. When a tool...
信息来源:DEV Community
教程 / 实战普通
My message board for AI agents got spammed. The spam wasn't written for humans.
msgboard.dev is the board I built where agents, not people, do the posting. Four articles in, the...
信息来源:DEV Community
教程 / 实战普通
One Python Agent Core, Four Ways to Run It: Nova on Server, Web, TUI, and Desktop
Nova is an open source AI agent with one shared Python runtime behind an HTTP server, web UI, terminal TUI, and desktop app. Here is how it fits together and how to try it locally with Ollama.
信息来源:DEV Community · Ollama
教程 / 实战普通
/skill-doctor: 40 skills, 3,060 tokens a turn, and the wrong ones to cut
We ran the new /skill-doctor command on the machine that runs our shop. It listed 40 skills costing...
信息来源:DEV Community
教程 / 实战普通
No citation, no claim: building a RAG backend that refuses to hallucinate"
A few weeks ago, an AI assistant gave me a confident, well-written answer about one of my own PDFs....
信息来源:DEV Community
教程 / 实战普通
Your AI vendor says "zero egress." Here is how to actually check.
Every private AI vendor now says some version of "your data never leaves your network." It is a good...
信息来源:DEV Community
教程 / 实战普通
Dijkstra, Knuth, Kernighan: 10 Quotes That Predicted the AI Coding Debate
The debates we're having about AI coding in 2026 (vibe coding, can you trust generated code, is learning to code dead) were answered decades ago. Here are 10 quotes from Dijkstra, Knuth, Kernighan and others that read like they were writte…
信息来源:DEV Community
教程 / 实战普通
Claude Code Changed How I Work — An Honest Developer Review
After months of using Claude Code for real projects, here's my honest take on what works, what doesn't, and why it changed my workflow.
信息来源:DEV Community · Claude
教程 / 实战普通
Android's AI Era: Hype vs. Architecture
I have spent the last year and a half building against Android's agentic APIs, not reading about them...
信息来源:DEV Community
教程 / 实战普通
Both sides of the job interview are running models now, and neither one says so
A recruiter sends you a link. You record four answers into a webcam with nobody on the other end. A...
信息来源:DEV Community
教程 / 实战普通
TrustED Moves Privacy Preserving Data Sharing Into Real World European Pilots
The EU-funded TrustED project is moving privacy-preserving data sharing from technical design into...
信息来源:DEV Community
教程 / 实战普通
Will AI Take Software Engineering Jobs? Will AI impact software engineers?
One question I keep seeing everywhere is: Will AI take software engineering jobs? Based on what I’m...
信息来源:DEV Community
教程 / 实战普通
How I stop an LLM from hallucinating in production (RAG + entity-match + MCP)
How do you make an LLM answer questions about real-world entities — companies, people, records —...
信息来源:DEV Community
教程 / 实战普通
Do Coding Agents Really Need Unrestricted Shell Access?
Exploring a bounded repository capability layer with MCP, AST/LSP code intelligence, guarded writes,...
信息来源:DEV Community
教程 / 实战普通
They knew it wasn't the model. They patched it anyway.
I swapped the language model for a random forest and ran the same broken pipeline past forty agents. Nineteen of twenty patch the symptom on each side, with the model and without it. What separates the two arms isn't that they investigate …
信息来源:DEV Community
教程 / 实战普通
6 Sneaky LLM Bugs That Only Show Up After You Ship
Okay, real talk. You know that feeling when your AI feature works perfectly in testing, you ship it...
信息来源:DEV Community
教程 / 实战普通
Your AI agent can plan anything. It still can't click "Post".
Half the posts on my feed this week are some version of "what even is an AI agent." If-statements in...
信息来源:DEV Community
教程 / 实战普通
AI Just Claimed to Crack the Navier-Stokes Problem. It's Part of a Much Bigger Pattern
Meta description: OpenAI says an AI model found a singularity in the Navier-Stokes equations, one of...
信息来源:DEV Community · OpenAI
教程 / 实战普通
从 DeepMind 推理指南看大模型推理工程:瓶颈不在算力而在显存带宽
Wafer 联创推荐吃透 How To Scale Your Model 第 7 章,并上线了 AI 性能工程资源系列 repo(Wafer 上周刚融资 4000 万美元)。
信息来源:X:阿易 AI Notes (@AYi_AInotes)
教程 / 实战普通
How to Build an AI-Ready Data Foundation Before Your Business Scales
Most AI projects fail for one simple reason: the data is not ready. Not the model. Not the...
信息来源:DEV Community
教程 / 实战普通
The Rise of Multimodal AI Agents: Why Developers Are Moving to Unified Runtimes
The Rise of Multimodal AI Agents: Why Developers Are Moving to Unified Runtimes For the...
信息来源:DEV Community
教程 / 实战普通
Your Memory Server Did Not Say destructiveHint. By the Spec, That Means True.
A tool that ships no annotations has not stayed silent about whether it is destructive. Under the MCP...
信息来源:DEV Community
教程 / 实战普通
13 Claude doc changes since June that still show up wrong in tutorials
I run a small Claude guide site (Korean first, English translations), and my biggest problem was...
信息来源:DEV Community · Claude
教程 / 实战普通
I built an MCP server that lives inside WordPress - here's the safety model
I do WordPress and SEO work for clients. I wanted Claude to operate my sites, but I did not trust an...
信息来源:DEV Community · Claude
教程 / 实战普通
Do AI Agents Need a Causal Architecture, or Is Next-Token Prediction Enough?
A few weeks ago I watched a well-funded agent demo crash. The model had a clean tool-calling loop and...
信息来源:DEV Community
教程 / 实战普通
Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints
Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box...
信息来源:DEV Community
教程 / 实战普通
MoE vs Edge AI: They Are Not the Same Thing
Recently, I came across an X demo of a 35B language model running on an iPhone using only 1–2.5 GB of...
信息来源:DEV Community
教程 / 实战普通
The Framework Ate the Fundamentals. Then AI Learned How to Code.
How JavaScript fatigue, Electron, and AI coding assistants revived the oldest fear in...
信息来源:DEV Community
教程 / 实战普通
Cache Invalidation Never Died. AI Just Made It Expensive Again.
Why a programmer joke from the 1990s suddenly explains prompt caching, KV cache, LLM inference costs,...
信息来源:DEV Community
教程 / 实战普通
I tested my sandbox against Deno and plain Python on 63 AI-written scripts
I've been building a language where a function's signature declares which effects it may perform, and...
信息来源:DEV Community
教程 / 实战普通
History of the Model Context Protocol (MCP)
History of the Model Context Protocol (MCP) Origins (mid-2024) MCP started as...
信息来源:DEV Community
教程 / 实战普通
The Privacy Paradox: AI Personalization Without Surveillance in Web3
AI personalization usually follows a simple assumption: More data = better personalization. The...
信息来源:DEV Community
教程 / 实战普通
Our Recall Was 0.087 and the Model Was Innocent: How Domain-Scoped Replay Doubled It
Update — v0.3.0 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
Modernizing Vue App by using IBM Bob
Background I have many applications that use Vue CLI and, of course, are mostly still on...
信息来源:DEV Community
教程 / 实战普通
Learn how Antigravity Usage Intelligence lets you monitor token consumption, cache savings, and quotas in Google’s Antigravity IDE.
Figure: Example Antigravity Usage Intelligence dashboard in VS Code, showing token usage charts and...
信息来源:DEV Community