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87 / 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 06:00

My support chatbot scored 0.92. It was also lying to customers.

Twelve of my thirteen test prompts scored a perfect 1.00. Two independent evaluation runs agreed:...

信息来源：DEV Community

教程 / 实战普通2026-10-09 05:35

AI Coding Tools Are Great Until the Only Test Is a Device in Someone's Hand

Most "how I use AI coding tools" posts come from someone who lives in one web framework all day. That...

信息来源：DEV Community

教程 / 实战普通2026-10-09 05:34

AI Models Have a Spine Until You Give Them a Manager

Frontier models shrug off a confident liar and even a fake majority, then fold the moment a senior reviewer pulls rank. A benchmark on who caves to authority and who keeps their answer.

信息来源：DEV Community

教程 / 实战普通2026-10-09 05:25

MIT 教授 Sasha Rakhlin 谈 AI 如何重塑高校科研与研究生培养

MIT 统计与数据科学中心主任 Sasha Rakhlin 发文分析 AI 对学术界的影响，指出数学领域已有模型达到国际数学奥林匹克金牌水平，并在一年后产出新研究成果。他建议院系重新界定学术贡献与署名责任，并建设共享 AI 科研基础设施，以保留实验失败等未发表的经验知识。

信息来源：MIT News（RSS）

教程 / 实战普通2026-10-09 05:06

Benchmarking LLMs on ETL Logic Synthesis: Can AI Truly Replace Data Pipeline Scripting?

A custom benchmark evaluating modern LLMs on translating visual Knime/ETL logic into idiomatic, vectorized Python code with strict edge-case verification.

信息来源：DEV Community

教程 / 实战普通2026-10-09 05:06

NVIDIA 开发者如何用 GPT-6 Astra 等前沿 AI 智能体构建 Omniverse 仿真应用

NVIDIA 开发者用 GPT-6 Astra 等前沿 AI 模型配合 Omniverse 库，通过自然语言指令构建仿真应用。仓库仿真在 80 台传送带、40 个机械臂和 800 个箱子下以全高清 30 帧/秒运行两分钟，完成 640 次成功放置。另有机器人线缆布线、CAD 转 SimReady 资产、人形机器人仓库仿真及自动驾驶测试等案例。

信息来源：NVIDIA Blog（RSS） · GPT / NVIDIA

教程 / 实战普通2026-10-09 04:46

TerraQuest: Put the Phone in Your Pocket, Let an Open-Weight Model Name the Animals and Plan

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 04:45

Google Requires Manual Fact-Checking for AI Content Before Website Publication

Google has updated its guidance for using generative AI content on websites, making manual...

信息来源：DEV Community

教程 / 实战普通2026-10-09 04:38

Offline Adventures - lets start journey with AI

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 04:34

Grok Bot 一键配置模拟掌机

把最难搞的问题交给 Grok @Bot

信息来源：X：Elon Musk (@elonmusk, xAI) · Grok

教程 / 实战普通2026-10-09 04:30

Study of 9 Million AI Answers Challenges the Link Between Sentiment and Citations

Positive brand sentiment may be valuable for customer trust, but it is not a dependable shortcut to...

信息来源：DEV Community

教程 / 实战普通2026-10-09 04:24

TouchGrass: The Open-AI Agent That Succeeds When You Stop Using It

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 04:15

Running 15 Claude Code Sessions at Once

TL;DR: Ten or more parallel Claude Code sessions work if you treat them as a small distributed...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-09 04:10

GroundSignal — The Sidewalk Told on Itself

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 04:00

I got Jev to zero mistakes. I'm still using Flash-Lite.

Jev is a brilliant decision model. Gemini Flash-Lite is the model nobody talks about, and it’s fast,...

信息来源：DEV Community · Gemini

教程 / 实战普通2026-10-09 03:52

The future, after AI

I've been using AI coding tools for a while now, and the progress is honestly insane. Something that...

信息来源：DEV Community

教程 / 实战普通2026-10-09 03:06

Bedrock and LangChain disagree on what input_tokens means — never price it without knowing who counted

I was adding cache-read and cache-write columns to a usage ledger, and I put two usage payloads side...

信息来源：DEV Community

教程 / 实战精选2026-10-09 03:01

如何在单张 RTX 5090 上用 MiniMax H3 生成实时视频

ComfyUI 博客作者用智能体搜集各类优化，把 MiniMax H3 实时视频生成压缩到单张 RTX 5090（32 GB 显存）上运行，生成 30 秒视频耗时 23.51 秒，达 1.28 倍实时吞吐。

信息来源：Comfy Blog

教程 / 实战普通2026-10-09 02:35

Meta Muse and MCP Security: When Trusted AI Tools Become the Attack Surface

The most dangerous AI attack may not break the model. It may simply convince the AI to use a trusted...

信息来源：DEV Community

教程 / 实战普通2026-10-09 02:05

MCP Servers Are a New Attack Surface, and Most Teams Are Not Looking

Over the last year, the Model Context Protocol (MCP) has become the default way to connect an AI...

信息来源：DEV Community

教程 / 实战普通2026-10-09 02:00

A PSD carries Photoshop's answer key. The UI has none.

This week I wrote a Photoshop file by hand. 390 bytes, two gray layers, the top one set to Soft...

信息来源：DEV Community

教程 / 实战普通2026-10-09 01:57

Elsewhere: Don't Remind Me. Give Me a Reason.

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 01:31

I Built a World With Rules. Then I Changed Them.

The Rules Are Hidden. The Timeline Isn't. What happens when you put something inside a...

信息来源：DEV Community

教程 / 实战普通2026-10-09 01:15

WanderLog: an offline field journal that answers "where did I see that kingfisher last time?"

A trail voice memo becomes structured sightings and walks, parsed by open-weight gemma3:4b on your own machine — no dashboard, no cloud, no typing.

信息来源：DEV Community

教程 / 实战普通2026-10-09 01:02

GitHub 漏洞赏金研究员 @vaib25vicky 如何挑选要调查的功能

GitHub 在网络安全意识月活动中专访了漏洞赏金项目 VIP 研究员 @vaib25vicky，其专注授权与访问控制方向。GitHub 今年重构了赏金机制，改为按质量而非数量奖励，并设立邀请制 VIP 计划，严重漏洞最高可获 3 万美元以上赏金。该研究员表示自己按功能而非漏洞类型开展研究，并强调 AI 只能充当助手，所有发现必须自行验证后才能提交。

信息来源：GitHub Blog

教程 / 实战普通2026-10-09 01:00

AI coding agents and Theo's Rust TypeScript compiler: the caveats

AI coding agents produced Theo's Rust TypeScript port. Its project benchmarks are promising; version matching and maintenance still need review.

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:57

Side Quest: an AI that sends you on a walk, and never learns where you are

This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 1 — Touch Grass. ✏️ TODO...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:57

AllergyGuard — Open-Source Offline Dietary Safety & Recipe Transformation Engine

What I Built Shared living arrangements create significant friction when one roommate...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:51

Your coding agent's work is lost in .md file

A good part of what my coding agents make now isn't code. A rollout plan. A comparison of three queue...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:37

The September cut took 17% of my Claude Code week. Subagents were taking 48%.

My Claude Code week started ending on Wednesday. I blamed the September 14 cut, like everyone on...

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-09 00:33

What decision models can't do: six honest limits

Two of the six new local decision models are non-commercial, none of them explain themselves, and the confidence number is a claim until you bench it.

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:32

Stop Rebuilding Your Agent Loop Just to Train It with RL

Reinforcement learning for language agents has had an annoying operational tax. If you wanted to run...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:27

Breaking the Subword Boundary: Probing Architectural Vulnerabilities in Modern LLMs (ASTRAL-Bench on Kaggle)

This is a submission for the Kaggle Benchmarking Challenge When we look at standard LLM...

信息来源：DEV Community

教程 / 实战精选2026-10-09 00:21

LangChain 用 Stripe Link 和 Managed Deep Agents 构建可支付的智能体 Restock

LangChain 发布示例项目 Restock，一个在 Slack 上通过 Managed Deep Agents 运行的办公用品购买智能体，演示智能体如何安全完成支付。

信息来源：LangChain：Blog（RSS）

教程 / 实战普通2026-10-09 00:09

Claude 额度快速上手 Managed Agents

使用这些额度最快上手的方式是 Claude Managed Agents。在 Claude Code 中使用 claude-api 技能构建智能体，并用你的额度运行它： /claude-api managed-agents-onboard

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

教程 / 实战普通2026-10-09 00:03

100 Actions, 110 Side Effects: A Crash Test for AI Agent Tools

Your agent chose the right tool. The arguments were valid. The action was allowed. Then the worker...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:03

Spring AI vs LangChain4j in October 2026: Both Shipped Big. Here Is How to Pick.

On September 25, 2026, both of the serious Java options for building AI applications shipped releases...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:02

CodeSmith Context Engineering: Append-Only Conversation History for Agents

Context Engineering: A Conversation History That Never Gets Rewritten Source version of...

信息来源：DEV Community

教程 / 实战普通2026-10-09 00:00

智能体代码审查的解剖：Tessl Code Review 如何重构 PR 审查流程

Tessl 发布博客拆解智能体代码审查的完整结构，包括标准、视角、发现、裁决、逐条回应与记忆六个环节。其 Tessl Code Review 内置正确性与数据完整性、安全与隐私、规模与韧性、可维护性与代码质量四个视角，以 skill 形式打包并并行运行，标准以 context 形式存放在仓库中。该工具可免费安装到代码仓库，在下一个 pull request 上运行首个循环。

信息来源：Tessl：产品与工程博客

教程 / 实战普通2026-10-08 23:57

Dev Tool GTM, Done Agentically

I'm Founding Technical GTM at Tabstack. I run GTM with a stack of agents and tools, and I stay in...

信息来源：DEV Community