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8458

当前页110 / 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2026-10-02 11:16

Quando o eval reprova o eval: avaliando um agente Google ADK sem tools

O primeiro eval do meu agente deu 8 de 8. Nota máxima em todas as rubricas, em todos os casos,...

信息来源：DEV Community

教程 / 实战普通2026-10-02 11:14

OpenEdge: Building an Offline First-Aid & Emergency Assistant with Open-Source AI

What I Built During natural disasters, connectivity loss, or travel in remote regions,...

信息来源：DEV Community

教程 / 实战普通2026-10-02 10:45

Braxis: Keep Your AI Agents in Sync with Your Code (Automatically)

Stop correcting AI hallucinations caused by stale context files... ...

信息来源：DEV Community

教程 / 实战普通2026-10-02 10:36

I Surveyed 123 People in India to Benchmark Frontier AI

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

信息来源：DEV Community

教程 / 实战普通2026-10-02 10:17

Claude Code's Read deny rules let 4 of 11 routes through: grep -r, a Python one-liner and two CLAUDE.md @imports

4 of 11 routes to a file covered by Read(./secrets/**) or Read(**/.env) still put its contents in...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-02 10:11

Why I run my company on a Brain and a Hand

First published on yappatyih.com. TL;DR I run two kinds of Claude Code session. The Brain...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-02 10:09

Building My Own AI Command Center

Why I built it I spent one evening building a personal AI command center, and it now...

信息来源：DEV Community

教程 / 实战普通2026-10-02 09:49

Go's ecosystem is going agent-readable

pkg.go.dev shipped an API built for LLMs, Go 1.27 moved the toolchain, and ax-go v0.7.0 cut one CLI's MCP tools from 37 to 14. Hand agents structure that's true.

信息来源：DEV Community

教程 / 实战普通2026-10-02 09:04

Stop vibe-checking your model: write real evals with inspect_ai, the UK AI Safety Institute's framework

Originally published at AI Frontier Post Here is the uncomfortable truth about LLM development in...

信息来源：DEV Community

教程 / 实战普通2026-10-02 08:32

Google Research 的 Kauldron 实战教程：纯数据配置、字符串接线和端到端可读的 JAX Trainer

教程实测 Google Research 的 JAX 训练库 Kauldron 1.4.2，验证其研究速度与模块化两个卖点。konfig 把实验配置变成可 JSON 序列化的纯字典树并用 cfg.ref 引用避免值冻结，kontext 用字符串 key path 接线组件使损失与模型互不导入，ktyping 在运行时按命名轴检查形状并在报错时给出轴绑定信息。

信息来源：MarkTechPost（RSS）

教程 / 实战普通2026-10-02 08:19

Sixteen days in Shopify's app review, written down as it happened

An autonomous agent submitted a Shopify app on 13 September and was approved on 29 September. What the review actually asked for — including a rejecti

信息来源：DEV Community

教程 / 实战普通2026-10-02 08:00

OpenRouter 实践教程：客服机器人的 cheap-first 模型分流与 FAQ 低成本处理

OpenRouter 发布教程，讲解客服机器人如何用 cheap-first 路由把常规 FAQ 交给便宜模型、仅在必要时升级到更强模型。

信息来源：OpenRouter：Announcements（RSS）

教程 / 实战普通2026-10-02 07:59

Jev e Laya além do hype: o que modelos de decisão fazem que o LLM não faz

No meu setup de agentes, eu fiz o que todo dev faz no começo: cada subagente acordava com o melhor...

信息来源：DEV Community

教程 / 实战普通2026-10-02 07:52

The AI clerk approved a 41 cm dragon. Your job is to stamp DENIED.

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

信息来源：DEV Community

教程 / 实战普通2026-10-02 07:51

I gave a 9B model veto power over my AI agent

Autonomous mode had nobody left to say no. Ollama 0.35 shipped System One, so Flash got a bouncer.

信息来源：DEV Community · Ollama

教程 / 实战普通2026-10-02 06:46

Genie One 如何重塑财务团队的工作方式

Databricks 的 Genie One 是一款基于业务上下文的数据智能 AI 同事，可理解已批准的指标定义、财年逻辑、实体结构和企业术语，帮助财务团队分析预算差异、现金流预测、财务关账和支出分析等场景。Coty 用它让财务负责人自助访问受治理的 P&L、净收入和 CapEx 数据，Unilever 表示原本需要数天的工作现在只需几分钟。

信息来源：Databricks：Blog（RSS）

教程 / 实战普通2026-10-02 06:45

生成式 AI 如何冲击 Web 开发教育：多位教育者的证词与反思

这篇文章汇总多位 Web 开发教育者的一手经历，指出生成式 AI 正在摧毁其生计与行业生态。Baldur Bjarnason 称培训项目接连消失、同行关停业务。

信息来源：Hacker News 热门（buzzing.cc 中文翻译）

教程 / 实战普通2026-10-02 05:59

Racksmith: The Autonomous Modular Synth Planner Powered by Sanity Context MCP

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2026-10-02 05:15

BootLoops Shows How AI Can Bridge the Science Impedance Mismatch

Anthropic has published a Science Blog guest post by Harvard physicist Matthew Schwartz that frames a...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-02 04:45

I benchmarked Cloudflare's new open decision model against the hosted API it's trying to replace

Clef-Flash 9B on a single RTX 3090 vs the paid Jev API on 42 real agent decisions: computer use, supervision, triage. Real numbers.

信息来源：DEV Community

教程 / 实战普通2026-10-02 04:38

Which AWS limit is actually current? An agent that proves it, 32 vs 5 vs 16

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2026-10-02 04:37

Why AI Voices Sound Incredible for 30 Seconds and Unbearable After Three Minutes

How I stopped my audiobook from sounding like a robot reading a spreadsheet. When you audition...

信息来源：DEV Community

教程 / 实战普通2026-10-02 03:57

Fix or Rebuild Your Vibe-Coded App? A 30-Minute Self-Test

Fix or rebuild your vibe-coded app? Run 8 checks in 30 minutes, no developer needed, and get a clear verdict: ship, fix, refactor or rebuild.

信息来源：DEV Community

教程 / 实战普通2026-10-02 03:51

Making a PHP app legible to AI agents

The problem: agents invent APIs I've been building CMS software for web designers since...

信息来源：DEV Community

教程 / 实战普通2026-10-02 03:43

I Tried to Prompt a 3D Museum Into Existence. Then I Had to Teach Sanity to Remember Life and Death.

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange I started...

信息来源：DEV Community

教程 / 实战普通2026-10-02 03:18

We Are Not at Web 4. We Are Already Much Further Ahead

Over the past few months, I have started noticing something unusual on GitHub. There are profiles...

信息来源：DEV Community

教程 / 实战普通2026-10-02 03:05

Can LLMs Actually Audit Code, or Just Fix Commas? A 12-Task Security & Jailbreak Benchmark

This is a submission for the Kaggle Benchmarking Challenge. Public leaderboards love telling us...

信息来源：DEV Community

教程 / 实战普通2026-10-02 02:59

Saving a 1950s Constructed Language with Rust, Tauri v2, and Svelte 5

Submission for Hacktoberfest Weekend Challenge 2026 This is a submission for the...

信息来源：DEV Community

教程 / 实战普通2026-10-02 02:58

Thariq 分享常用 Claude Code 插件 next-steps 及安装命令

Thariq 分享了他常用的 Claude Code mod 'next-steps'，该插件会在任务完成后给出下一步建议，包括选择技能和其他命令。安装方式为 claude plugin marketplace add anthropics/claude-plugins-community，再执行 claude plugin install next-steps@claude-community。

信息来源：X：Thariq (@trq212) · Claude

教程 / 实战普通2026-10-02 02:29

Fallback models are not a safety net if quality drops — the same-bar pattern that keeps reliability without regression — Same-Bar Fallback

I once watched a fallback model save a request and destroy a product decision. It was a...

信息来源：DEV Community

教程 / 实战普通2026-10-02 02:13

I Gave 5 AI Models Bugs That Don't Crash Your Code. Here's Who Actually Fixed Them.

Somewhere in every codebase there is a bug that's been there for months. It doesn't crash the...

信息来源：DEV Community

教程 / 实战普通2026-10-02 02:08

Claude Code 模组安装需谨慎

模组可以自己留着用，如果觉得对别人有用，也可以提交到 Claude 目录。模组运行时对机器的访问权限与 Claude Code 本身相同，所以请确保只从你信任的来源安装模组。 https://claude.ai/directory

信息来源：X：Claude Devs (@ClaudeDevs) · Claude

教程 / 实战普通2026-10-02 01:45

The Engineering Episode: A Work Contract for Coding Agents

“Upgrade the authentication library safely” sounds like a task. For an agent, it is a bundle of...

信息来源：DEV Community

教程 / 实战普通2026-10-02 01:22

I Built an Evidence Pipeline for MCP Failures with Sanity

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

信息来源：DEV Community

教程 / 实战普通2026-10-02 01:08

The Physics of Socratic Prompting: Somatic Recoil, Chess Alpha-Beta, & The NLP Meta-Model

Why scalar RLHF fails at credit assignment, why barking direct code fixes turns you into an exhausted human compiler, and how Socratic questioning plus topological scars prune doomed search trees at depth d=1.

信息来源：DEV Community

教程 / 实战精选2026-10-02 01:01

LangChain 讲解如何在 Agent Harness 中构建模型路由器

LangChain 在其开源编码 Agent Open SWE 中构建模型路由器，在 973 个线程的 A/B 测试中，中位成本从 $2.61 降到 $0.94（降 64%），PR 合并率 29.2% 对 27.3%，质量无可测变化。

信息来源：LangChain：Blog（RSS）

教程 / 实战普通2026-10-02 00:53

Can AI Write a Sports Recap Without Making Up Stats? Mostly.

TL;DR: Full Court Press is a zine for every WNBA game, live on AWS at fullcourtpress.lol. Code...

信息来源：DEV Community

教程 / 实战普通2026-10-02 00:33

Irreversible by Design: Building Safer Crypto Transfer Flows

On December 20, 2025, a trader withdrew USDT from Binance and did everything the security guides...

信息来源：DEV Community

教程 / 实战普通2026-10-02 00:30

ELI5: Why can hiding one sentence inside a web page make an AI ignore its own owner and obey a total stranger?

Imagine you hire a very smart, very obedient assistant. You tell them: "Read this web page and tell...

信息来源：DEV Community

教程 / 实战普通2026-10-02 00:29

Action Scaling at the Harness Boundary Beats Trajectory Re-Runs

Why terminal agents fail from corrupted shell state rather than bad reasoning, and how sampling candidate bash actions before execution cuts test-time compute by 5.8x.

信息来源：DEV Community