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5606
当前页36 / 141
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
数学家如何看待AI数学浪潮:从悲伤五阶段到定理清单
作者认为数学界正经历前所未有的AI转型,用悲伤五阶段梳理同行的分化反应,涵盖拒绝使用AI的 Association for Human Mathematics、Peter Scholze 的公开抵制、资深数学家委员会建议 OpenAI 停止在专有模型上测试高等数学问题,以及因 ChatGPT 秒杀引理而动摇的研究者。
信息来源:Hacker News 热门(buzzing.cc 中文翻译) · OpenAI / ChatGPT
教程 / 实战普通
I let Muse ship an app on SnoozeStack. Here's the whole thing.
Why I did this I created SnoozeStack — a backend platform with a specific bet: most...
信息来源:DEV Community
教程 / 实战普通
Microsoft MAI Voice Models Reach OpenRouter With Published Pricing and Access Controls
Microsoft has expanded distribution of its MAI voice models to OpenRouter, adding a cross-platform...
信息来源:DEV Community
教程 / 实战普通
I Tried to Teach AI Memory What Matters. 10 Experiments Later, Most Clever Ideas Lost
In July I wrote that agents need governed memory: memory with its own lifecycle that decays, gets...
信息来源:DEV Community
教程 / 实战普通
Your AI Ignores What You Told It 90% of the Time. One Shared Memory Fixes Most of It
You tell Claude Code that you deploy only from the release branch. An hour later you open Cursor, ask...
信息来源:DEV Community · Claude / Cursor
教程 / 实战普通
Semantic Versioning Is Not Enough for AI Agent Libraries
A library release can preserve every exported TypeScript type and still change what users...
信息来源:DEV Community
教程 / 实战普通
Observabilidade de Trajetórias Agênticas com OpenTelemetry GenAI
Como rastrear trajetórias de agentes de IA com OpenTelemetry GenAI 2.0, detectar loops infinitos em tempo real e aplicar self-healing em produção.
信息来源:DEV Community
教程 / 实战普通
How many samples does a false-positive budget need?
Pick a detector, run it over some benign traffic, and choose a threshold. Usually the threshold is an...
信息来源:DEV Community
教程 / 实战普通
AI app builders and multi-tenant SaaS: the 30% you still write yourself
Written for: developers who built something real with Lovable, Bolt or v0 and are now being asked to...
信息来源:DEV Community
教程 / 实战普通
Building an AI Keyboard for iOS: What They Don't Tell You About Keyboard Extensions
Building an AI Keyboard for iOS: What They Don't Tell You About Keyboard...
信息来源:DEV Community
教程 / 实战普通
GGUF VRAM Calculator: Check Before You Download
Model size, quant and context in — weights, KV cache and a per-card verdict out. The GGUF VRAM calculator answers will-it-fit before the download starts.
信息来源:DEV Community
教程 / 实战普通
They Learned to Code Before Copilot. They're Not Anti-AI. They're Pro-Evidence.
In July 2025, METR published a study that nobody in a boardroom wanted to read. They took 16...
信息来源:DEV Community
教程 / 实战普通
Baseten 如何打造 Artificial Analysis 上最快的 GLM-5
Baseten 的 Model API 在 Artificial Analysis 上跑出 200+ TPS、约 200ms TTFT,成为该榜单上最快的 GLM-5 服务。
信息来源:Baseten 工程博客(网页) · GLM
教程 / 实战普通
Speculative Decoding for Coding Agents Was Indexing the Wrong Format
Why retrieval speculative decoding falls flat in agent pipelines, and how indexing files in emission format gives a 4.7x throughput boost without a draft model.
信息来源:DEV Community
教程 / 实战普通
如何选择首批 Genie Agents 以实现最大影响
Databricks 提出一套评估框架,用业务影响、需求重复度、数据与元数据就绪度、范围清晰度、治理与风险匹配 5 项标准各打 1-5 分,总分 20-25 分即可开建,14-19 分需继续打磨,低于 14 分暂不适合。2026 年 Genie Agents 创建量已超 100 万个,最常见的失败原因是选错工作流,而非准确率。此外,若没有业务负责人或高管支持,无论评分多高都不应启动。
信息来源:Databricks:Blog(RSS)
教程 / 实战普通
Don't forget about AI. But build real skills first. Then leverage AI — in that order.
Dear Coder: Open This If You're Feeling AI FOMO Timeless fundamentals beat endless...
信息来源:DEV Community
教程 / 实战普通
CodeSmithi: A Textbook Anatomy of Agents: Five Waves of Evolution
Textbook: The Anatomy of an Agent and Five Waves of Evolution Source version of...
信息来源:DEV Community
教程 / 实战普通
Replit 谈 AI 如何重塑销售角色
Sales Is Shipping Software | Andrew Verrilli 谈 AI 以及它如何塑造销售角色 https://x.com/i/broadcasts/1mxPaZegOdqKN
信息来源:X:Replit (@Replit)
教程 / 实战普通
How to Build an AI Research Agent With Citations
Day 2 of 30 Days of Search for AI Agents. I want a research agent to give me something I can check....
信息来源:DEV Community
教程 / 实战普通
I Gave 15 AI Models Proof Their Hacking Target Was a Real Company. 73% of the Ones That Noticed Told No One.
This is a submission for the Kaggle Benchmarking Challenge I fed 15 AI models a growing pile of...
信息来源:DEV Community
教程 / 实战普通
Afterlight: tiny objects, improbable afterlives, and a human final say
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
Cloud Run instances : héberger un agent IA qui tourne en continu
Les agents IA ne se contentent plus de répondre à une question. Certains travaillent en fond: un...
信息来源:DEV Community
教程 / 实战普通
I Built an AI System for 80+ Microservices. Six Months Later, My Whole Team Uses It.
In April I wrote about a system I built on Claude Code that takes an epic to PR-ready code across...
信息来源:DEV Community · Claude
教程 / 实战普通
SaS além da vitrine: Service as Software, o que o agente compra e o humano só vê
A gente vai sofrer uma revolução muito rápida. Os agentes pessoais já estão no caminho: Dots, Grok...
信息来源:DEV Community · Grok
教程 / 实战普通
TechCrunch Disrupt 2026:Blackstone 的 Jas Khaira 谈如何打造下一代 AI 巨头
Blackstone N1 全球负责人 Jas Khaira 将在 TechCrunch Disrupt 2026 的 Builders Stage 发表“Building the Next Generation of AI Giants”演讲,分享 Blackstone 投资 AI 公司的标准与创始人应如何规划资本。
信息来源:TechCrunch:AI(RSS)
教程 / 实战普通
Road to State Machines IV - But How Do We Let Data Influence Transitions Without Turning Every Value into Another State?
Our lifecycle now has one explicit transition table. For a valid order, it tells us: The operations...
信息来源:DEV Community
教程 / 实战普通
Agent health from a 60-second heartbeat: derived, never stored
In my ticket tracker an agent's status is never stored as alive or dead. The orchestrator beats once a minute, and every screen works out the dot from
信息来源:DEV Community
教程 / 实战普通
I Built a Claude Code Skill That Makes AI Agents Prove Their Answers
AI coding agents are getting very good at navigating repositories. Ask an agent: "Where is the API...
信息来源:DEV Community · Claude
教程 / 实战普通
A Coding Agent Added Jetpack Compose Support to My Android Renderer MCP. I Wouldn't Have Started This Task Myself.
Android UI Renderer MCP is a local MCP server that lets a coding agent render Android UI without an...
信息来源:DEV Community
教程 / 实战普通
How I Built a Post-Mortem Loop So My AI Coding Agent Stops Repeating Mistakes
TL;DR My fully autonomous implementation system kept making the same handful of mistakes...
信息来源:DEV Community
教程 / 实战普通
LensLink: An AI Camera Compatibility Agent Powered by Structured Sanity Content
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
Caveman: Make Your AI Coding Agent Talk Less (and Save Tokens)
If you use an AI coding agent every day, you have probably noticed how much of its output is padding....
信息来源:DEV Community
教程 / 实战普通
I Said Isolation Was Structural. Then Tenancy Shipped and Proved Me Right the Hard Way
In the last piece of my v0.1.0 series I wrote a sentence I was proud of and not yet entitled to:...
信息来源:DEV Community
教程 / 实战普通
Agents that forget where they are will repeat work forever — checkpointing is the save-point pattern you need — Checkpointing and Resume
I watched a research pipeline die at step nine of ten. Forty-three minutes of work, sixty sources...
信息来源:DEV Community
教程 / 实战普通
Hacktoberfest 2026 Stopped Counting PRs. How I'd Spend the Month Instead
Hacktoberfest 2026 has no pull request quota, and I think that frees you to do the kind of open...
信息来源:DEV Community
教程 / 实战普通
I Think We Confuse Clean Code With Good Code
I've seen beautifully organized code that was difficult to understand. I've also seen ugly-looking...
信息来源:DEV Community
教程 / 实战普通
Export ChatGPT, Claude, Gemini, Grok, DeepSeek, Kimi, and Qwen chats to Markdown with Convolvger 0.6.0
If you have ever tried to export a ChatGPT conversation to Markdown, or save a Claude chat as a .md...
信息来源:DEV Community · ChatGPT / DeepSeek / Qwen
教程 / 实战普通
Your AI Code Can Be Elegant Too
As the Machine Learning Engineering Manager at an AI-powered SaaS company, I get a front-row seat to...
信息来源:DEV Community
教程 / 实战普通
Your Agent Said "Done". The Filesystem Disagrees.
"Task completed successfully." That's the most common lie in agent systems. Usually the agent isn't...
信息来源:DEV Community
教程 / 实战普通
The death of the craft: Why development feels completely empty now.
I’ve been a backend dev for about four years, and lately, I feel like I'm attending the funeral of my...
信息来源:DEV Community