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8448
当前页135 / 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
AI Agent Platforms: Agent Frameworks to Full-Stack Platforms
TL;DR "Agent framework" is used for several different kinds of tool: agent SDKs,...
信息来源:DEV Community
教程 / 实战普通
A Psychological State is a Coefficient Vector
Hamming's two kinds of novelty are not two kinds of stuff. They are two things you can do with one...
信息来源:DEV Community
教程 / 实战普通
Web chat is not a coding environment
I have been pairing with someone who writes code in a web chat. Claude.ai, ChatGPT, whichever tab is...
信息来源:DEV Community · ChatGPT / Claude
教程 / 实战普通
Freelance Developer Rates in 2026: How to Price Work an AI Agent Can Half-Do
A client asks for a CSV import feature. Two years ago you would have quoted 20 hours. Today an agent...
信息来源:DEV Community
教程 / 实战普通
What AI think of Code Meridian
Here is the response on what the llm thought after the challenge. I think Human Cognitive Seed is...
信息来源:DEV Community
教程 / 实战普通
Enforce Permissions Inside the pgvector Query, Not After It
A hands-on guide to making access control part of your Postgres vector search so an unauthorized chunk is never even ranked.
信息来源:DEV Community
教程 / 实战普通
How Default Settings and Bad Habits Are Draining Your Claude Code Budget
Introduction Many developers use Claude Code and look for ways to reduce token consumption...
信息来源:DEV Community · Claude
教程 / 实战普通
How to Reduce Claude Code's Initial Context and Avoid Prompt Cache Breaks
Introduction Lately, discussions around token optimization in Claude Code have focused...
信息来源:DEV Community · Claude
教程 / 实战普通
用25行Python代码实现Jev:一个本地运行的分类概率模型
有人用25行Python代码复现了Jev:加载Qwen3-0.6B-GGUF模型,对提示词中的选项标签取logits并归一化为概率,示例中"Phishing"概率达0.885。作者称Jev本质是接收带选项的提示词并输出概率的分类器,速度快、本地运行、数据不外传。该文为戏仿博客,作者同时给出OpenJev等更完整的开源实现链接。
信息来源:Hacker News 热门(buzzing.cc 中文翻译) · Qwen
教程 / 实战普通
RAG vs. Fine-Tuning vs. Long Context
For a couple of years, this was framed as a simple either/or question: retrieve relevant chunks at...
信息来源:DEV Community
教程 / 实战普通
十字路口Crossing解析大模型「斩杀线」:效率如何重塑模型竞争格局
文章以「斩杀线」概念分析2026年模型竞争重心从智能转向智能与成本的前沿。作者复盘小米 MiMo 从 V2-Flash 到 V2.6 的四次迭代,称 9 月 22 日发布并开源的 MiMo-V2.6 系列三款模型智能接近前代两倍。
信息来源:elsewhere:文章(RSS)
教程 / 实战普通
One attacker rented 87,000 IPs with a modified AI CLI
An attacker brute-forced 87,000 IPs on legacy VPNs, rented them as proxies, and automated the whole operation with a modified AI CLI. Plus: identity as the new initial access.
信息来源:DEV Community
教程 / 实战普通
I built a free, BYOK AI coding agent IDE that runs fully offline on local LLMs
I built Forger, a standalone Electron app that bundles a file explorer, Monaco editor, AI chat, Git,...
信息来源:DEV Community
教程 / 实战普通
Semantic Search Without an LLM. Build Blazing-Fast Semantic Search for \$0
Currently, we are in a phase when the term “AI search” refers to the use of effective and slow...
信息来源:DEV Community
教程 / 实战普通
Before Daybreak — the promise is the branching point
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange. What...
信息来源:DEV Community
教程 / 实战普通
CLOSEDQUORUM: The Malware That Lets Four AI Models Vote on How to Attack You
Cisco Talos just documented the first Windows malware that doesn't wait for a human to tell it what...
信息来源:DEV Community
教程 / 实战普通
DuckDuckGo MCP Servers in Claude Code: 8 Tested, 3 Actually Work
Free web search for an agent sounds like a solved problem. There are dozens of DuckDuckGo MCP...
信息来源:DEV Community · Claude
教程 / 实战普通
No CVE needed: how a GitHub issue hijacked an AI agent
No CVE needed: how a GitHub issue hijacked an AI agent
信息来源:DEV Community
教程 / 实战普通
Claude Opus 5.5 Is Now on Google Cloud, and I Think It's a Big Deal for Developers
Anthropic released Claude Opus 5.5 this week, and it's available on Amazon Web Services, Google...
信息来源:DEV Community · Claude
教程 / 实战普通
Something About Coding Stopped Feeling Good — and It Took Me a While to Figure Out What
Let me tell you about a project that wasn't impressive. Back in university, I built a small .NET...
信息来源:DEV Community
教程 / 实战普通
Stop building side projects. Nobody cares — and here's the uncomfortable math.
Open your GitHub. Go on. Count the repositories that have a README, a clean commit that says initial...
信息来源:DEV Community
教程 / 实战普通
Coding with AI: The Investigator Method
Before I heard about OpenAI, I would never have imagined programming to become what it is today....
信息来源:DEV Community · OpenAI
教程 / 实战普通
Annotation & Comment: A Simpler Approach to AI Image Editing
Introduction Most AI image editing tools today rely on text-only prompts to describe what...
信息来源:DEV Community
教程 / 实战普通
My AI agent said we were under attack. The logs said otherwise.
Two things happened to me in the same afternoon this week. One was real and boring. The other was...
信息来源:DEV Community
教程 / 实战普通
Will Jev Replace LLMs? A Support Ticket Routing Example
LLMs and Jev: When You Need a Decision Instead of a Reply Imagine a support application...
信息来源:DEV Community
教程 / 实战普通
DevDocs — A Developer Agent Grounded in Real Documentation
DevDocs — A Developer Agent Grounded in Real Documentation This is a submission for the...
信息来源:DEV Community
教程 / 实战普通
Opus 5.5 Made Cache Reads 60% Cheaper. I Redid the Math on My Text-to-SQL Architecture
TL;DR: Claude Opus 5.5 came out yesterday with cache reads at $0.20 per million tokens, 60% cheaper...
信息来源:DEV Community · Claude
教程 / 实战普通
Agentic content is a pipeline problem, not a prompt problem
Photo by Carter Hightower on Unsplash For about a year my "AI writing workflow" was a chat window...
信息来源:DEV Community
教程 / 实战普通
The one law the whole series assumes: an AI that goes down silently is worse than one that's dead
AI Harness Engineering · Essay Six · derek wang (derekwang85) The hardest constraint in this...
信息来源:DEV Community
教程 / 实战普通
Sizing the Subnet: What Nobody Tells You About Microsoft Foundry Agent Service Networking Until Production Falls Over
Sizing the Subnet: What Nobody Tells You About Microsoft Foundry Agent Service Networking...
信息来源:DEV Community
教程 / 实战普通
I Ran One Codex Task for 31 Hours. It Survived Restarts and Built an Auditable Textbook Pipeline
A 31-hour AI run sounds like a stunt. The useful result was not the clock. It was continuity. I used...
信息来源:DEV Community
教程 / 实战普通
Nothing in My Framework Could Go Stale on Its Own
Three checks in my own framework broke the same way in one night, and I wrote all three. Two months...
信息来源:DEV Community
教程 / 实战普通
I made my agent prove every quote against the source document
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
AI Is Writing More of the Code — But Developers Are Becoming Responsible for More Than Ever
AI is writing more code. That part is obvious now. Developers can ask an agent to: create a...
信息来源:DEV Community
教程 / 实战普通
Jev is a very good classifier wearing a frontier model's coat
Two years in stealth. Ex-OpenAI. Co-invented ChatGPT. That is the pitch for Jev, and the pitch is...
信息来源:DEV Community · OpenAI / ChatGPT
教程 / 实战普通
# CaseGuard: Winning with Uncertainty-Gated Agentic Fraud Investigation on TigerGraph
A technical breakdown of our submission for the TigerGraph HHGOA Hackathon. 1. Executive...
信息来源:DEV Community
教程 / 实战普通
Análise das Respostas de LLMs em Relação ao Conteúdo Introdutório de Programação: um Comparativo entre o ChatGPT e o Gemini
Dados da obra: Análise das Respostas de LLMs em Relação ao Conteúdo Introdutório de Programação:...
信息来源:DEV Community · ChatGPT / Gemini
教程 / 实战普通
From smartphone to sovereign agent:How native on-device intelligence reshapes the personal computing device
Abstract For fifteen years the smartphone has been a window onto intelligence that lives...
信息来源:DEV Community
教程 / 实战普通
Your agent run passed. Can you prove it was allowed?
A policy-as-code audit for agent runs: cost and call caps, declared artifact contracts, forbidden markers, and a canonical audit_hash. On 13 archived runs, the declared contract, not the data, decided whether they passed.
信息来源:DEV Community
教程 / 实战普通
How We Translate Entire Books with LLMs Without Losing Context
Chunking strategies, context carry-over, and glossary injection for long-form translation ...
信息来源:DEV Community