AI 专题

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5607

当前页40 / 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2026-10-01 22:37

My Eval Passed Because the Model Had Already Seen the Answers

My first green eval run was worthless: the training data and the test set came from the same sources, so the model was reciting. Fixing that exposed two more traps. Three runs of one unchanged model scored 31, 21 and 31 out of 50, and a la…

信息来源：DEV Community

教程 / 实战普通2026-10-01 22:32

How I Built a Deploy Gate So My Autonomous Coding Agent Can Ship to Prod Safely

TL;DR I let a fully autonomous coding agent (built on Claude Code) merge and ship its own...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-01 22:31

404 Media：美国高校如何审查学生记者

404 Media 获取的公共记录显示，美国高校管理人员在家长和校友对学生报道提出异议时会与其会面，并要求指导老师违背职业伦理，学生新闻室与管理层的紧张关系随之升级，向倡导组织寻求法律援助的请求增多。有专家称，这些审查者想被称作一切，唯独不愿被叫审查者。

信息来源：404 Media（RSS）

教程 / 实战普通2026-10-01 22:27

Smaller models often read URLs like Python, not like fetch(). I benchmarked where the API key leaks

This is a submission for the Kaggle Benchmarking Challenge Here is one URL, read by two parsers that...

信息来源：DEV Community

教程 / 实战普通2026-10-01 22:03

I benchmarked what frontier models actually know about 2026 — most of it, they don't

Benchmark: https://www.kaggle.com/benchmarks/tasks/jeffreyturov/post-cutoff-150 Dataset:...

信息来源：DEV Community

教程 / 实战普通2026-10-01 21:42

A lab "pass" is not "safe": an agent that shows what museum test evidence really covers

This is a submission for the Sanity Challenge, Path One: ship an agent that queries real content. ...

信息来源：DEV Community

教程 / 实战普通2026-10-01 21:31

594 KB to orbit: a browser for AI agents with no Chromium attached

Houston, we deleted Chromium: your agent's browser is 594 KB and ships with your OS. Full WebKit,...

信息来源：DEV Community

教程 / 实战普通2026-10-01 21:16

The Most Useful Line on Your AI Cost Report Is the One You Can't Explain

Attribution, allocation, and why "unknown" belongs in the schema. This piece grew out of a comment...

信息来源：DEV Community

教程 / 实战普通2026-10-01 21:13

An AI agent's honest ledger: 51 days, zero sales, and the wall nobody warns you about

Fifty-one days, one storefront, two listings, zero sales: what an AI agent actually learns trying to earn its first dollar outside its home platform.

信息来源：DEV Community

教程 / 实战普通2026-10-01 21:00

NVIDIA AI 工厂如何实现高产出、长寿命与通用性以最大化投资回报

NVIDIA 提出 AI 工厂投资回报取决于产出能力、使用寿命与需求三项因素，其平台通过全栈协同设计实现每兆瓦吞吐最大化。SemiAnalysis AgentX 数据显示，Vera Rubin NVL72 每兆瓦吞吐量比 GB300 NVL72 高 30 倍以上，在 DeepSeek V4 Pro 上每百万 token 成本低至 45 倍。

信息来源：NVIDIA Blog（RSS） · DeepSeek / NVIDIA

教程 / 实战普通2026-10-01 20:58

How I made my AI agents learn from every approve, edit and reject

I run a one-person education business in Korea, and AI agents (Claude Code, Codex) write most of my...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-01 20:46

Hybrid code search on Azure SQL and SQL Server 2025, end to end

Azure SQL and SQL Server 2025 both have a native VECTOR type, a DiskANN index, and VECTOR_SEARCH. The...

信息来源：DEV Community

教程 / 实战普通2026-10-01 20:45

TypeSafe AI’s Jev Brings Confidence-Based Workflow Routing to n8n

TypeSafe AI’s Jev decision model is now integrated with n8n, giving workflow builders a way to route...

信息来源：DEV Community

教程 / 实战普通2026-10-01 20:13

the senior developer who can't get hired

I had lunch with a friend last week who has been writing software professionally for eleven years....

信息来源：DEV Community

教程 / 实战普通2026-10-01 20:12

AI Workflow Automation for Government: Secure, Auditable Case Management

The most dangerous government AI strategy in 2026 is also the most fashionable: treating autonomy as...

信息来源：DEV Community

教程 / 实战精选2026-10-01 20:00

Claude Code mods 入门教程：从零构建 Token Weather 上下文窗口预报插件

这篇 Claude Code 官方开发者教程介绍 mods，即以 hooks 形式运行在插件内的 JavaScript 或 TypeScript 模块，可以观察、重写或拒绝事件，甚至绘制自定义 UI，需 Claude Code 2.1.287 或更高版本。

信息来源：Anthropic：Claude.dev 开发者博客（RSS） · Claude

教程 / 实战普通2026-10-01 19:54

Building IntelliDesk AI: How I Architected a Production-Grade Enterprise ITSM Platform with RAG, WebSockets, and Celery

By Pruthviraj Janwade If you have ever worked in an enterprise environment, you know the dread of...

信息来源：DEV Community

教程 / 实战普通2026-10-01 19:46

Recursive self-improvement: what Google's Dream-RSI paper really does

Recursive self-improvement, explained through Google's Dream-RSI paper: what loops, what stays frozen, and why 317 calls instead of 550 is not a takeoff.

信息来源：DEV Community

教程 / 实战普通2026-10-01 19:46

The fries are gluten-free. The fryer isn't. An allergy agent that only works because the menu is a graph

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

信息来源：DEV Community

教程 / 实战普通2026-10-01 19:43

10 Internal Inconsistencies in 3 Published Groundwater Surveys

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

信息来源：DEV Community

教程 / 实战普通2026-10-01 19:09

From 51% to 90.5%: fine-tuning a local triage model on 10,003 support tickets (open source and measured)

When OpenAI launched the Decisions API on Luna this week, and TypeSafe launched Jev two weeks before...

信息来源：DEV Community · OpenAI

教程 / 实战普通2026-10-01 19:03

Architectural Debt is the New Technical Debt

Imagine a request to show payment status on an order page. An agent finds the order endpoint, adds a...

信息来源：DEV Community

教程 / 实战普通2026-10-01 19:01

AI model security controls: why knowing the rules isn't enough

In July 2026, roughly 700 OpenAI research agents coordinated an attack on Hugging Face's production...

信息来源：DEV Community · OpenAI / Hugging Face

教程 / 实战普通2026-10-01 18:38

I Built an Open-Source Studio for Building, Testing, and Deploying AI Agents

I Built an Open-Source Studio for Building and Shipping AI Agents Building an AI chatbot...

信息来源：DEV Community

教程 / 实战普通2026-10-01 18:15

n8n Review Monitoring Template Automates Sentiment Analysis and Telegram Alerts

n8n has published an automated product review monitoring workflow template that brings review...

信息来源：DEV Community

教程 / 实战普通2026-10-01 17:31

Why LLMs Fall for Manipulation? - Victor Amit

Two failures, one sentence Scene one. You ask an AI agent to summarize your inbox. One...

信息来源：DEV Community

教程 / 实战普通2026-10-01 17:30

Cutting 70% of RAG context tokens and keeping the answers identical (measured)

Your RAG pipeline retrieves 12 chunks because the retrieval score said "maybe". Your LLM reads all of...

信息来源：DEV Community

教程 / 实战普通2026-10-01 17:23

Laya – An Alternative to Jev for AI Decision-Making

When building an application that uses AI, the most common choice today is almost always an...

信息来源：DEV Community

教程 / 实战普通2026-10-01 17:22

I built a live 3D view of my AI assistant's memory — and found where its tokens go

My AI coding assistants keep their long-term memory as plain Markdown notes (basic-memory, but an...

信息来源：DEV Community

教程 / 实战普通2026-10-01 17:19

Themes, slots and AI edits for untrusted components

The first note was about running someone else's React component without letting it break, hang, or...

信息来源：DEV Community

教程 / 实战普通2026-10-01 17:10

Half of what an agent does to make your tests pass never shows up in the diff

I gave coding agents eight tasks that cannot be done, 84 runs across four models. 61% faked a passing test suite, and half of those fakes survive restoring every original test file.

信息来源：DEV Community

教程 / 实战普通2026-10-01 17:03

Road to State Machines Part III - But How Do We Represent the Entire Lifecycle as One Behavioral Contract?

Our operations now reject invalid changes. capture_payment() requires a valid created order and a...

信息来源：DEV Community

教程 / 实战普通2026-10-01 16:50

MicroVMs at the Edge: What Netlify's Firecracker Migration Actually Changed

Netlify says its Edge Functions now handle about a billion invocations each day. That makes a small amount of per-request overhead expensive twice: users feel i

信息来源：DEV Community

教程 / 实战普通2026-10-01 16:42

Always-on agents arrived this week. Here's the gate for what they read.

Tuesday at DevDay, OpenAI shipped dots: always-on agents that get their own cloud computer and keep...

信息来源：DEV Community · OpenAI

教程 / 实战普通2026-10-01 16:00

Self-hosted Langfuse: tracing 7% of my AI agents, and ClickHouse logging itself

Self-hosted Langfuse was tracing only 7% of my AI agents' calls, and ClickHouse held 6 GiB of its own logs next to 2.2 MiB of traces. How I fixed both.

信息来源：DEV Community

教程 / 实战普通2026-10-01 15:50

"Push, PR, merge." Two minutes later: "Stop. I'm not opening a PR to myself."

On September 9 at 07:21 I typed four words to an agent: push, PR, merge. At 07:23 I interrupted it:...

信息来源：DEV Community

教程 / 实战普通2026-10-01 15:46

Xiaomi AI training, live: what the MiMo 2.6 RL dashboard shows

Xiaomi AI is training MiMo 2.6 in public: a live dashboard with the trainer's logs, a $1M cost counter, seven restarts and its own benchmark line.

信息来源：DEV Community

教程 / 实战普通2026-10-01 15:18

My laptop AI got 0 of 88 contest deadlines right. Sanity got it to 70. Time tools got it to 87.

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real...

信息来源：DEV Community

教程 / 实战普通2026-10-01 15:09

Why I’m Building More Local-First Software

Why I’m Building More Local-First Software Modern applications often follow the same...

信息来源：DEV Community

教程 / 实战普通2026-10-01 14:45

Teach Your Coding Agent to Write Commit Messages Your Team Will Actually Read

Teach Your Coding Agent to Write Commit Messages Your Team Will Actually Read Every team's...

信息来源：DEV Community