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8439
当前页18 / 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
Introducing Codra: The Open-Source AI Code Review Engine
Code review is broken. Between context switching, subjective nitpicks, and the ever-growing backlog...
信息来源:DEV Community
教程 / 实战普通
Prompt Pad: What Is Open Source?
Chances are you're already using open-source software without realizing it. In this episode of...
信息来源:DEV Community
教程 / 实战普通
Priced to Lose: Why "Add $20 a Month for AI" Is Not a Business Model
Most teams spend a year perfecting an AI feature and ten minutes deciding what to charge for it. Then...
信息来源:DEV Community
教程 / 实战普通
Building a browser-based vocal splitter: decode locally, queue the job, delete the files
Most tutorials about vocal separation start with "run Demucs on your GPU". That is a fine answer if...
信息来源:DEV Community
教程 / 实战普通
Claude Code's auto-compaction took me 2 minutes, so I moved it to the background
If you run long Claude Code sessions you know the moment. The context hits the auto-compact...
信息来源:DEV Community · Claude
教程 / 实战普通
Exploring MCP: From My First Integration to Architectural Decisions
During my vacation, I decided to spend some time learning more about the Model Context Protocol, or...
信息来源:DEV Community
教程 / 实战普通
I Built a Judge My AI Couldn't Influence. In 51 Runs, It Never Gave a B.
I built an autonomous scientific discovery engine called RUMI. I let it run for up to 21 hours per...
信息来源:DEV Community
教程 / 实战普通
Five terminals, four cd's, and which one was waiting? Why I built Quarters
If you use a terminal coding agent on more than one project, you probably know my old routine. A...
信息来源:DEV Community
教程 / 实战普通
Day 15/90: Deterministic Intent Routing — Does Your Request Reach the Right Workflow?
An AI application can produce a clear, confident response after sending a request to the wrong...
信息来源:DEV Community
教程 / 实战普通
Which day should we drive? Watching border queues with Home Assistant and a vision model
Every holiday season we sit in the same queue and wonder if we picked the wrong day. So I made Home Assistant watch public traffic cams and let an LLM score what it sees.
信息来源:DEV Community
教程 / 实战普通
Logging a Change Is Not the Same as Being Able to Undo It
There's a draft spec going around for giving AI agents real undo — not a confirmation dialog before...
信息来源:DEV Community
教程 / 实战普通
I Built a Daily Sports Card Game in a Month With AI Agents. Here's Everything It Broke.
I'm not an engineer. I come from the sales world. But between June 18 and July 16, I pushed 172...
信息来源:DEV Community
教程 / 实战普通
Where Claude's usage limits went: from SSE to protobuf frames
I maintain Claude Monitor, an open-source browser extension that shows claude.ai's usage limits: the...
信息来源:DEV Community · Claude
教程 / 实战普通
I scored 12 AI models on whether they admit they don't know. My own token limit nearly broke the test.
Most AI leaderboards ask whether the model got it right. I wanted to know something else: when it's...
信息来源:DEV Community
教程 / 实战普通
What You See Is What You Sign: the consent record agents are missing
There's a good argument going around right now that an agent's log tells you what it did but keeps no...
信息来源:DEV Community
教程 / 实战普通
Comparing Batch and Real-Time LLM Inference Economics
Batch inference costs 50% less than real-time inference at Anthropic, OpenAI and Google, in exchange...
信息来源:DEV Community · OpenAI / Claude
教程 / 实战普通
I built a malware-triage AI skill — then realized malware could talk it into lying
I'm a cybersecurity student, and I wanted to see how well an AI agent could help with the first,...
信息来源:DEV Community
教程 / 实战普通
Why KV-Cache Memory Tricks — Not New Math — Drove This Week's Biggest Inference Wins
LLM inference digest (Oct 28–Nov 4, 2026): elastic KV-cache offloading, MoE-tuned speculative decoding, and day-0 serving for Mistral Large 4.
信息来源:DEV Community · Mistral
教程 / 实战普通
James Shore 讲解如何测量 AI 对软件交付速度的影响
James Shore 在其系列文章第二部分提出测量 AI 对交付速度影响的方法。他指出交付速度不等于生产力,代码行数和 PR 都不可靠,建议采用随机分组、先估时后分配的组内重复测量实验,并提醒速度提升需按任务占比折算为整体收益,引用 METR 研究称工程师高估 AI 提速近 50%。
信息来源:O'Reilly Radar(热点 RSS)
教程 / 实战普通
Mitigating WebSocket Retry Storms: Preventing Server-Side Thread and Event-Loop Starvation
Mitigating WebSocket Retry Storms: Preventing Server-Side Thread and Event-Loop...
信息来源:DEV Community
教程 / 实战普通
StateRoot: shared intelligence and versioned work across AI agents
Hi DEV, I use several AI agents on cheaper subscriptions, switching to conserve usage limits and...
信息来源:DEV Community
教程 / 实战普通
Your LiveKit agent works great on WebRTC. The phone network will humble it
A voice agent that works perfectly in your browser can fall apart the moment someone calls it from a...
信息来源:DEV Community
教程 / 实战普通
I migrated off my no-code stack and regretted it. For nine days.
I migrated our whole setup off a pile of tools onto one app a couple of months ago. For the first...
信息来源:DEV Community
教程 / 实战普通
Two Months, Five People: Building the Backend Behind Foodmartex’s Next Chapter
Over the past two months, our five-person team at Foodmartex has built catalogue-grounded AI...
信息来源:DEV Community
教程 / 实战普通
The KV Cache From Scratch
In every part of this series, one thing kept showing up: the notebook. In Part 1 it grew by 72 KB...
信息来源:DEV Community
教程 / 实战普通
Weight-Space Programming: how GPT-6 Astra edited Qwen's weights and took MATH-500 from 7.9% to 48.1%
MIT CSAIL's weight-space programming: GPT-6 Astra edited 0.016% of Qwen3.5-0.8B's weights with no gradients and lifted MATH-500 from 7.9% to 48.1%. How it works.
信息来源:DEV Community · GPT / Qwen
教程 / 实战普通
Did Someone Repost My Malfoid AI Portrait? Finding Crops, Flips and Screenshots With Perceptual Hashes (Python, Tested)
You made a Malfoid (Female Malfoy / Fem Draco) portrait, posted it, and a week later a picture that...
信息来源:DEV Community
教程 / 实战普通
How a GPT-5.4 harness scored above GPT-6 Astra and Claude Code on ExtractBench
On LlamaIndex ExtractBench (370 documents, 4,869 pages), my open-source harness KYNEX scores 92.97...
信息来源:DEV Community · GPT / Claude
教程 / 实战普通
Your Agent Logs What It Did. It Has No Record of What It Meant To Do.
@allenheltondev published a post yesterday called What the heck do I alert on anymore?. He runs an AI...
信息来源:DEV Community
教程 / 实战普通
My PR demo videos make themselves now, in my voice
How I built a free pipeline that runs on my MacBook: it films the real app, narrates in a clone of my...
信息来源:DEV Community
教程 / 实战普通
DeepSeek Harness Creator Mode: When the Agent Builds Its Own Plugins — and Why That Needs Guardrails
On 2 November 2026, DeepSeek's Harness team announced Creator Mode for DeepSeek Harness, its...
信息来源:DEV Community · DeepSeek
教程 / 实战普通
Filtering After Retrieval Leaks Your Documents. Put the ACL Inside the Query.
In permission-aware RAG, filtering documents after retrieval is a data leak; the access-control predicate belongs inside the retrieval query itself.
信息来源:DEV Community
教程 / 实战普通
My linter reported 700 problems. Almost all of them were wrong.
AI coding agents read your AGENTS.md or CLAUDE.md on every request. Those files rot like any other...
信息来源:DEV Community · Claude
教程 / 实战普通
Signal #127: Raycast Gets Leaner, Vercel Starts Charging for Memory, and Biome Crosses 500 Rules
This week's tooling news is a mix of quiet performance work and forced decisions. Raycast isolated...
信息来源:DEV Community
教程 / 实战普通
Before you install that agent skill, vet it: building a checker that only blocks on proof
Installing an agent skill is an act of trust. A pack — a SKILL.md plus whatever scripts and...
信息来源:DEV Community
教程 / 实战普通
I Put a Local 7B Model Inside SSMS 21 & 22 (No Cloud, No API Keys)
TL;DR: I built a free, open-source SSMS 21 & 22 extension that plugs a locally-hosted 7B model...
信息来源:DEV Community
教程 / 实战普通
ChessMaster: Building a Personal Chess Coach on Stockfish and Claude
ChessMaster transforms raw game data into actionable coaching insights. Chess.com and Lichess show...
信息来源:DEV Community · Claude
教程 / 实战普通
How the Strands Agent Loop Actually Works
Starting from the smallest agent that runs and ending in the source where the loop turns out to be a recursion.
信息来源:DEV Community
教程 / 实战普通
My Rust target/ said 325 GB. My disk said 1.65 GB free.
so last week my Mac said the disk was full. like, actually full. 1.65 GB left out of 494 GB. I ran...
信息来源:DEV Community
教程 / 实战普通
When Cursor's MCP Connection Drops Mid-Workflow and the Agent Retries Blind
Quick guidance on when cursor's mcp connection drops mid-workflow and the agent retries blind.
信息来源:DEV Community · Cursor