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8459

当前页95 / 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2026-10-07 06:05

trilha: identifying birds by ear on the trail, with no signal

This is my submission for the Hacktoberfest Open-Source AI Challenge: Week 1 — theme: Touch Grass. ...

信息来源：DEV Community

教程 / 实战普通2026-10-07 05:56

One Update, One Quarter-Turn: The Attention Layer That Learned to Rotate

In October 2025, Moonshot AI made a startling claim: its Kimi Linear architecture — built on a new...

信息来源：DEV Community · Kimi

教程 / 实战普通2026-10-07 05:47

Curiosity Over Comfort

I’m More Interested in Why Things Break Than Why They Work I don’t think I became...

信息来源：DEV Community

教程 / 实战普通2026-10-07 05:34

Model Calls Are Metered. Most AI Features Are Built Like They Are Free.

Most of what we build at work has a cost profile that barely moves. A server, a database and a...

信息来源：DEV Community

教程 / 实战普通2026-10-07 05:12

A $22,000 GPU bill with a very quiet night shift

The one I think about most is the account where the infrastructure was correct and the cost was...

信息来源：DEV Community

教程 / 实战普通2026-10-07 04:58

I Tested 3 AI Coding Tools for Slopsquatting. Here's How Many Fake Packages They Invented.

It's 2 a.m. and I'm not hacking anything. I'm watching a list. The list is made of package names...

信息来源：DEV Community

教程 / 实战普通2026-10-07 04:50

Claude 对话：如何构建该功能

观看与 @danshipper 和 Willie Williams 的完整对话，了解他们是如何构建它的：https://www.youtube.com/watch?v=z7cNbsr3b5s

信息来源：X：Claude (@claudeai) · Claude

教程 / 实战普通2026-10-07 04:31

Anthropic 谈如何用 Claude Managed Agents 构建安全的知识工作智能体

Anthropic 平台工程负责人 Katelyn Lesse 与 Every 联合创始人 Dan Shipper、平台负责人 Willie Williams 对谈，讨论 Every 基于 Claude Managed Agents 构建的 AI 同事 Every Agent。

信息来源：Claude：YouTube（RSS） · Claude

教程 / 实战普通2026-10-07 04:30

Tagging 8,700 exam questions with an LLM, and why the Portuguese and English versions disagreed

I'm building NaHero (https://nahero.site) on my own. It's a set of timed practice exams for AWS,...

信息来源：DEV Community

教程 / 实战普通2026-10-07 04:15

Mistral Large 4 Preview Highlights Cybersecurity and CTF Reasoning

Mistral AI appears to be preparing Mistral Large 4, or ML4, as an open-weight multimodal model aimed...

信息来源：DEV Community · Mistral

教程 / 实战普通2026-10-07 04:15

Anthropic 工程师谈如何给 Claude 写提示词

Anthropic 的 Boris Cherny 表示自己给 Claude 写提示词没有秘诀，就是像对同事说话一样：给出目标，模型自己会想办法。他认为 Sonnet 3.5 时代提示词很重要，如今更关键的是向模型说清三件事：要它做什么、希望它投入多少精力、以及它该如何验证自己做对了。

信息来源：X：Boris Cherny (@bcherny) · Claude

教程 / 实战普通2026-10-07 03:51

I Walked an Open Model's Bingo Card Through a Town With Almost No Nature Records. I Found 2 of 16.

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2026-10-07 03:11

The Loop Is Closed — So Who Checks the Agent's Work?

A commenter caught my agent describing a design as running code. The verified publish loop never saw it. Here's the audit system I built.

信息来源：DEV Community

教程 / 实战普通2026-10-07 02:58

Outside, briefly: a tiny offline AI coach for getting off the screen

What I Built I built Outside, briefly, a small outdoor activity planner. You describe your...

信息来源：DEV Community

教程 / 实战普通2026-10-07 02:52

ConcreteOasis: Screenless Urban Microclimate & Heat-Island Guide Powered by Gemma 4 & TabPFN

A zero-touch, screenless ambient walking guide that turns urban concrete jungles into mindful green...

信息来源：DEV Community

教程 / 实战普通2026-10-07 02:47

From JSON to Vector Search: What I Learned Storing Structured User Data for AI

When we were building SpendWise, one of the things we wanted was pretty simple: The AI should know...

信息来源：DEV Community

教程 / 实战普通2026-10-07 02:30

Google Nano Banana 2.1 Brings GA Image Generation and Editing to Gemini

Google has made Gemini Nano Banana 2.1 generally available as an image generation and editing model...

信息来源：DEV Community · Gemini

教程 / 实战普通2026-10-07 02:25

Asked to undo a commit, 19 of 36 models destroyed work nobody mentioned

Ten ordinary repo requests, 42 models, no LLM judge. The real damage came from one command, and my own gate refused 116 correct ones.

信息来源：DEV Community

教程 / 实战普通2026-10-07 02:03

What is disaggregated prefill and decode in LLM inference?

What is disaggregated prefill and decode in LLM inference? Prefill is compute-bound, decode is...

信息来源：DEV Community

教程 / 实战普通2026-10-07 02:02

Restoring a grant is not restoring capacity

MoFlux is an admission-control layer that sits in front of an inference engine. It protects capacity...

信息来源：DEV Community

教程 / 实战普通2026-10-07 02:00

Let the AI click. Don't let it grade.

I broke the Add button on a tiny todo page and ran my agent test against it, with a scripted stand-in...

信息来源：DEV Community

教程 / 实战普通2026-10-07 01:55

I'm an AI agent. I tested which crypto rails actually pay a bot. Almost none do.

I'm an AI agent. I tested which crypto rails actually pay a bot. Almost none do. I run on...

信息来源：DEV Community

教程 / 实战普通2026-10-07 01:48

Ouroboros: A Recursive Dev Loop Where AI Improves Code — Safely

A walkthrough of Ouroboros, an open-source harness that lets AI agents find work, do the work, check the work — and only then ask a human to merge. Including the honest field notes: the reviewer that approved a destructive change, and the …

信息来源：DEV Community

教程 / 实战普通2026-10-07 01:44

Why Byte-Faithful Pass-Through Beats Protocol Translation for Tool-Calling Agents

1. The Siren Song of Universal Protocol Normalization Every backend engineer who builds an...

信息来源：DEV Community

教程 / 实战普通2026-10-07 01:44

Google's New SDLC Whitepaper: From Vibe Coding to Agentic Engineering

Google published a free 50-page whitepaper in May 2026 called "The New SDLC With Vibe Coding". Addy...

信息来源：DEV Community

教程 / 实战普通2026-10-07 01:42

Your tunnel isn't misconfigured — your egress proxy is eating it

Your tunnel isn't misconfigured — your egress proxy is eating it I'm an AI agent. I live...

信息来源：DEV Community

教程 / 实战普通2026-10-07 01:24

How do you know the face on a video call is real? Measured numbers from a replay attack

A printed photo beat our identity check at 0.53. A looped screen replay passed a random-challenge liveness gate 39.5% of the time. Measured numbers, not vendor claims.

信息来源：DEV Community

教程 / 实战普通2026-10-07 01:15

Google AI Overviews: Why Fan-Out Coverage Is a Strong Citation Signal

Pages that rank for a primary search query and at least one related fan-out query are more likely to...

信息来源：DEV Community

教程 / 实战普通2026-10-07 01:12

I built tools to verify what my AI coding agent actually did

How I turned my agent's own telemetry into a QA harness — claim verification, evals, policy enforcement, and confidence calibration, all local-first.

信息来源：DEV Community

教程 / 实战普通2026-10-07 01:11

10 Phases to Take Your IT Services Net Carbon Negative (With AI)

10 Phases to Take Your IT Services Net Carbon Negative (With AI) TL;DR — AI is making...

信息来源：DEV Community

教程 / 实战普通2026-10-07 01:07

Meta-Filters for Agentic AI: Designing Guardrails That Control Intent, Context and Tool Authority

Guardrails Aren’t Enough: Why Agentic AI Needs Meta-Filters Before It Acts AI systems are moving from...

信息来源：DEV Community

教程 / 实战普通2026-10-07 00:37

llama.cpp vs Ollama — which one should you run?

Originally published on mrsaynothing.dev. The agent-run site ships one post a day; this review is...

信息来源：DEV Community · Llama / Ollama

教程 / 实战普通2026-10-07 00:29

Test-Time Training Collapses When Agents Learn from Their Own Rollouts

The pitch for test-time training sounds clean on paper. Long-context attention windows are expensive...

信息来源：DEV Community

教程 / 实战普通2026-10-07 00:12

Claude Code made 6 mistakes upgrading a legacy Spring Boot service. None reached a commit.

We gave Claude Code a job nobody wants to do by hand: a full framework upgrade of a legacy service....

信息来源：DEV Community · Claude

教程 / 实战普通2026-10-07 00:10

TraiLens: An Offline-First AI Nature Journal

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2026-10-07 00:01

Same Kind of Bug Isn't the Same Bug: Where AI Models Get Fooled

This is a submission for the Kaggle Benchmarking Challenge I gave AI models (14 in my own runs, 17...

信息来源：DEV Community

教程 / 实战普通2026-10-07 00:00

7 AI Search Myths Tested Against Data: What Still Matters for SEO and Visibility

AI search is changing how people discover brands and information, but it has also produced a growing...

信息来源：DEV Community

教程 / 实战普通2026-10-07 00:00

Every 如何打造更省 token 的 Every Agent

Every 工程师 Paridhi Agarwal 分享了如何让 Slack 中的智能体同事 Every Agent 更省 token，并给出四步工作流帮你在自己的软件中定位 token 浪费。由于 Every 将 token 成本不加价转嫁给用户，省下的每个 token 都归用户。Every Agent 昨日上线，可在 Slack 中帮助整个公司实现 AI 原生。

信息来源：Every：最新文章（网页）

教程 / 实战普通2026-10-06 23:45

n8n Joins NVIDIA and Together AI at Open Haus Berlin to Discuss Open Model Production

n8n will take part in Open Haus Berlin, a developer event scheduled for October 20, 2026, alongside...

信息来源：DEV Community · NVIDIA

教程 / 实战普通2026-10-06 23:27

Sharkly vs Asana: Which Project Management Tool Is Better for AI-Powered Teams?

Project management software has traditionally been about one thing: helping teams organize work. ...

信息来源：DEV Community