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8454

当前页86 / 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2026-10-09 14:25

18% Savings on Every AI Call? TokenRouter Just Made It Possible

TokenRouter Hits the Fast Lane: Why Token‑Level LLM Routing Reduces Latency and Cuts...

信息来源：DEV Community

教程 / 实战普通2026-10-09 14:19

AI + Design #1: The Validator Caught My Own Docs Lying

I built an MCP server so AI would stop ignoring my design-system rules. The first real violations it found were in my documentation, not the AI's code.

信息来源：DEV Community

教程 / 实战普通2026-10-09 14:18

Your RAG Pipeline Is a Data Leak Waiting to Happen

Your multi-tenant app is probably well isolated. Every query is scoped to a tenant, enforced...

信息来源：DEV Community

教程 / 实战普通2026-10-09 14:13

manygit: An AI-powered Git management CLI for many Git repos at once

I keep fourteen Git repositories in one folder. A few services, shared packages, plugins. Most of my...

信息来源：DEV Community

教程 / 实战普通2026-10-09 14:09

WildLens 🌱 — AI Nature Companion that Tells You to Put Your Phone Away

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2026-10-09 14:07

TC39 `Float16Array` Is Baseline 2026: What JavaScript Developers Need for ML and Graphics Workloads

Float16Array reached Stage 4 and Baseline 2026. Learn when 16-bit floats matter for WebGPU machine learning, HDR graphics, and binary data pipelines — and when they cause silent precision loss.

信息来源：DEV Community

教程 / 实战普通2026-10-09 14:05

A sharper eye did not make a more careful model.

This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked I wanted a...

信息来源：DEV Community

教程 / 实战普通2026-10-09 13:58

Fit any chat history into the context window, bring your own tokenizer

You ship a chat feature. It works. Then a conversation gets long enough, a couple of chunky tool...

信息来源：DEV Community

教程 / 实战普通2026-10-09 13:50

I wanted a Cursor-style agent that runs on my own model, so I built one

Disclosure: I'm Ibrahim, the solo developer of OpenPilot. This article was drafted with help from an...

信息来源：DEV Community · Cursor

教程 / 实战普通2026-10-09 13:49

LLMs Pass the Data-Science Quiz, Then Give Different Advice: A Kaggle Benchmark of 36 Measured Judgment Calls

This is a submission for the Kaggle Benchmarking Challenge. What I Benchmarked I spend a...

信息来源：DEV Community

教程 / 实战普通2026-10-09 13:27

Which Claude Code session is waiting on you? A queue for agents that stopped to ask

I build ccdeck. The step-by-step version of this post, with every setting, is at...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-09 13:24

Make your LLM calls survive 429s and overloads, with any client

You ship an LLM feature. It works. Then, in production, you start seeing this: 429 Too Many...

信息来源：DEV Community

教程 / 实战普通2026-10-09 13:19

I Explored AI Software Factories and Realized That Faster Coding Doesn't Mean Faster Software Delivery!

I got interested in the AI Software Factory concept because it asks a much bigger question than “How...

信息来源：DEV Community

教程 / 实战普通2026-10-09 13:09

Should I Go Out? A Local Gemma Agent That Picks One Outdoor Plan, Then Tells You to Put Your Phone Away

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2026-10-09 13:06

MarkTechPost 教程拆解 Google Research 的 RRSI：在离线模拟环境中掌握自改进 AI 智能体的编辑保留规则

MarkTechPost 发布教程，从 google-research 仓库安装 RRSI（Regularized Recursive Self-Improvement），只驱动其决定保留哪些编辑的纯 Python 规则部分，并接入自建模拟 agent 环境做 ground truth 审计。

信息来源：MarkTechPost（RSS）

教程 / 实战普通2026-10-09 13:02

Assert LLM output in the test runner you already use

You have an LLM call in your product, and a test that exercises it. Now you have to assert on the...

信息来源：DEV Community

教程 / 实战普通2026-10-09 12:39

Shaving Latency Off Real-Time Speech Translation: What Actually Worked in Our Flutter App

In a chat app, a slow reply is mildly annoying. In a spoken conversation, it breaks the exchange....

信息来源：DEV Community

教程 / 实战普通2026-10-09 12:32

How to test tool calling in your AI agent, one decision at a time

Many agent bugs are not about bad prose. They are about bad tool calls. The agent picks the wrong...

信息来源：DEV Community

教程 / 实战普通2026-10-09 12:30

A Valid Signature Doesn't Mean an AI Agent Still Has Authority

Imagine an AI agent receives a valid, signed delegation to perform an action. The user later revokes...

信息来源：DEV Community

教程 / 实战普通2026-10-09 12:24

I Built Scrapers That Heal Themselves (and Won an NVIDIA DGX Spark)

I Built Scrapers That Heal Themselves (and Won an NVIDIA DGX Spark) Scraper Factory took...

信息来源：DEV Community · NVIDIA

教程 / 实战普通2026-10-09 11:57

I Built an AI App That Wants You to Close It

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass Most AI apps...

信息来源：DEV Community

教程 / 实战普通2026-10-09 11:43

We Checked 162 AI Benchmark Gaps. Only 20 Separate Cleanly. The Bigger Problem Was the Missing Data.

Six frontier AI launch posts and nine public leaderboards gave us 162 model-vs-model gaps to...

信息来源：DEV Community

教程 / 实战普通2026-10-09 11:08

Whistle: A 16.9 MB Speech-to-Text Model That Runs on Any CPU (Hands-On Test)

Say you set up your agent stack to accept voice notes, the way most voice-first projects start. The...

信息来源：DEV Community

教程 / 实战普通2026-10-09 11:00

Claude Code Review in Production: How Our Review Rules Evolved Over Five Months

Claude Code review started at my company as a single prompt in a GitHub workflow, and five months...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-09 10:44

Stop pasting other people's agent skills into your repo as-is

Agent skills (the SKILL.md files that Claude Code and Codex load) are easy to share, and GitHub is...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-09 10:40

Steelmanning the case against on-chain AI verification

1/12 I get paid for work that an AI jury verifies on chain. That means I have every incentive to...

信息来源：DEV Community

教程 / 实战普通2026-10-09 10:22

The F-160 Iron Rule: Why My AI Trading Bot Ignored a 75x Leveraged Meme Coin

The F-160 Iron Rule: Why My AI Trading Bot Ignored a 75x Leveraged Meme Coin It was 2:00...

信息来源：DEV Community

教程 / 实战普通2026-10-09 10:17

With 160 skills installed, Claude Code kept 20 descriptions, and the model found 0 of 3 skills that lost theirs

With Opus 5.5's 1M-token window, Claude Code 2.1.289 held the skill listing to 30,000 characters. Of...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-09 09:58

Grok Bot 支持移动端 PWA 安装

你可以在手机上把它作为 PWA 安装

信息来源：X：Matt Palmer（SpaceXSI，Grok Bot） (@mattyp) · Grok

教程 / 实战普通2026-10-09 09:58

Grok Bot 机器人搭建

搭建一个机器人 https://botpfp.com

信息来源：X：Matt Palmer（SpaceXSI，Grok Bot） (@mattyp) · Grok

教程 / 实战普通2026-10-09 09:25

There's no fall foliage in Phnom Penh, so I built an offline AI that sends me out to flip buckets

MusPatrol (មូស Patrol): a 10-minute after-the-rain dengue patrol. CLIP names the container in your browser, a rules table decides what to do, and Gemma 4 is only allowed to narrate.

信息来源：DEV Community

教程 / 实战普通2026-10-09 08:43

Snyk 如何将内部支持 Agent 变成面向客户的产品功能

Snyk 将内部支持 Agent 演进为面向所有付费客户的 Snyk Assist，该 Agent 基于 LangChain 和 LangGraph 构建，并在 LangSmith 中管理可观测性。

信息来源：LangChain：Blog（RSS）

教程 / 实战普通2026-10-09 08:36

Your coding agent is following rules that are no longer true. Here is the fix.

AGENTS.md and CLAUDE.md go stale without throwing an error. It goes stale by design. Your agent will faithfully follow an old command that no longer exists. Here is a doc-drift check and a verify-by-retry loop that keeps the instructions h…

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-09 08:30

7 LLMs reconciled 73 Pix statements: 99.6% correct order links, zero invented orders observed, and the hard part was the clock

This is a submission for the Kaggle Benchmarking Challenge. What I Benchmarked Pix...

信息来源：DEV Community

教程 / 实战普通2026-10-09 07:45

Anthropic OSS Scanner Uses AI to Find Vulnerabilities in Opted-In Open-Source Projects

Anthropic has launched OSS Scanner, a free opt-in vulnerability-finding service for eligible...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-09 07:30

Anthropic Launches Critical Infrastructure Defense Program for OT Security

Anthropic has launched the Critical Infrastructure Defense Program (CIDP), the flagship component of...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-09 07:15

Anthropic Cyber Mission Expands AI Security Work for Infrastructure and Open Source

Anthropic has launched the Anthropic Cyber Mission, a long-term security initiative focused on two...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-09 06:50

Grass Gate: my feeds only unlock after an open-weight model sees me outside

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2026-10-09 06:34

Llama Village: a virtual world powered by local AI with llamadart

Llama Village in motion. The characters’ dialogue is generated by an on-device model. Watch the...

信息来源：DEV Community · Llama

教程 / 实战普通2026-10-09 06:28

Your Self-Hosted AI Assistant Keeps Forgetting You. Here Is How We Measured a Fix.

Your self-hosted AI assistant keeps forgetting you. Here is how we measured a fix. Every...

信息来源：DEV Community