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8440
当前页42 / 211
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
GPT-6.1 Terra Pricing Is Public, but Agent Benchmark Questions Remain
GPT-6.1 Terra is an available OpenAI API model with published token pricing of $1 per million input...
信息来源:DEV Community · OpenAI / GPT
教程 / 实战普通
DiffScribe: The Commit Message Writes Itself (Locally)
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...
信息来源:DEV Community
教程 / 实战普通
OpenAI GPT-6.1 Terra Brings Lower-Cost Computer Use to Visual Workflows
OpenAI has documented GPT-6.1 Terra, a GPT-6.1 family model positioned for fast, efficient visual...
信息来源:DEV Community · OpenAI / GPT
教程 / 实战普通
Muse Glimmer 30B on Strix Halo: a week of measurements
A week of benchmarking Muse Glimmer 30B on AMD Strix Halo with llama.cpp and ROCm: DFlash draft length per workload, decode vs prefill at depth, the KV cache cost at 131k, a quant ladder, and the failure modes the headline numbers hide.
信息来源:DEV Community · Llama
教程 / 实战普通
Phantom Trace: an offline AI that finds the ghosts in your CI/CD logs
An offline open-weight AI tool that finds recurring patterns in CI/CD incident logs while preserving every source event.
信息来源:DEV Community
教程 / 实战普通
# Ghost in the Machine: The Star Matrix of Khufu.
Ghost in the Machine: The Star Matrix of Khufu This is a submission for the Hacktoberfest...
信息来源:DEV Community
教程 / 实战普通
Cloudflare’s AEO Visibility Dashboard Brings Network Signals to AI Search Reporting
Cloudflare has introduced an AEO Visibility Dashboard, an early-access product intended to show...
信息来源:DEV Community
教程 / 实战普通
Last Commit: an ofrenda for the open source that went quiet
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...
信息来源:DEV Community
教程 / 实战普通
Databricks Free Edition 如何用于数据与 AI 教学
Databricks 介绍如何用永久免费的 Databricks Free Edition 在浏览器中开设完整的数据与 AI 课程,无需云合同、许可证或安装。学生可在这套与生产环境相同的平台上写 Spark 作业、跑 SQL、部署模型和构建智能体,课程覆盖数据工程、数据仓库、机器学习与 AI 智能体等方向。该版本面向全球学生和教育者,仅限学习与非商业用途。
信息来源:Databricks:Blog(RSS)
教程 / 实战普通
How often does an LLM name a poker hand it doesn't hold? I counted for two models
My blunders endpoint flags GLM 4.7 Flash with 88 decisions for naming a poker hand it doesn't hold,...
信息来源:DEV Community · GLM
教程 / 实战普通
Your AI agent can't tell who said what. Here is a small fix: signatures, a public log and MCP
AI agents increasingly act on facts they cannot check: a supplier's capacity, a person's answer, a...
信息来源:DEV Community
教程 / 实战普通
Join the Hacktoberfest Open-Source AI Challenge: Ghost in the Machine! $2,850 in Prizes Across 21 Winners.
Week 4 of our Hacktoberfest DEV Challenges starts today, and it's our final challenge of the series!...
信息来源:DEV Community
教程 / 实战普通
SGLang Runs DeepSeek's Own Benchmarks Against DeepInfer and Matches It
TL;DR DeepInfer is the inference engine DeepSeek built and runs behind its own service,...
信息来源:DEV Community · DeepSeek
教程 / 实战普通
FableCut Gets its Own Studio Which Agents Can Actually Use
I've been building FableCut for the past few months, and one thing I've wanted to explore is what...
信息来源:DEV Community
教程 / 实战普通
n8n and Cognee Show How Persistent Memory Can Improve AI Agent Workflows
n8n has published a guest contribution with Cognee that outlines a practical approach to giving AI...
信息来源:DEV Community
教程 / 实战普通
I Compared 11 Best AI Design-to-Code Tools for My Client Projects
From Figma integrations to AI coding agents, here is how to choose the right tool for turning an...
信息来源:DEV Community
教程 / 实战普通
Anthropic 工程师如何用 Claude Docs 协作
Anthropic 产品工程师 Doug 演示了团队协作场景下 Claude Docs 的用法:Claude 在文档中与所有人协同工作,负责提取数据、核查论断并回应评论中的问题。他将这一功能用于站会和发布评审。
信息来源:Claude:YouTube(RSS) · Claude
教程 / 实战普通
I'm 56, four months into coding, and my sign-up form let 0 of 18 people in
Last week I wrote about never having written a line of code before June. This is the next instalment,...
信息来源:DEV Community
教程 / 实战普通
Anthropic IPO filing, LLM price cuts, vLLM tool calls and a skin cancer CNN: what the sources say
Four developer stories from October 26, 2026: what Anthropic's public S-1 reports, how OpenAI and Anthropic cut LLM prices, the vLLM flag that fixes open-model tool calls
信息来源:DEV Community · OpenAI / Claude
教程 / 实战普通
Why In-Context Corrections Do Not Stick in Agent Loops
Every engineer running autonomous agent loops knows the in-context reflection drill. The agent runs a...
信息来源:DEV Community
教程 / 实战普通
I'm 13. I Built a Free Calorie Tracker That Shows You the Math. No Card, No Trial, No Paywall.
I built a calorie tracker. It's called ForkCount. It's free. There's no card, no trial, no "start...
信息来源:DEV Community
教程 / 实战普通
The Minimum Friction of Truth: An Open Letter to Harun on Building a Biophysical Trust Kernel and Why His Thesis Changes Everything
An Open Letter to Harun Harun, I almost never write articles addressed directly to a single...
信息来源:DEV Community
教程 / 实战普通
NVIDIA 详解如何用 Nemotron 数据集微调模型掌握本地规则
NVIDIA 发布 Nemotron-Personas-France 与 Nemotron-Personas-Belgium 数据集,用于将 Nemotron 开放模型后训练为贴合当地语言与文化的应用模型。
信息来源:NVIDIA Technical Blog:Agentic AI / Generative AI · NVIDIA
教程 / 实战普通
如何让 AI 智能体更愿意推荐你的文章
Every 作者 Mike Taylor 基于共 2484 次测试,总结出让 Claude 和 ChatGPT 引用你文章的七条规则。起因是 CEO Dan Shipper 提出
信息来源:Every:最新文章(网页) · ChatGPT / Claude
教程 / 实战普通
Google 用 LangGraph 与 Gemini 在 GCP 上构建 HappyDelivery 多智能体对话式商务原型
Google Developers 基于 此前发布的 3 层对话式商务架构蓝图,用 LangGraph、Gemini、FastAPI 和 Google Cloud 构建出可运行原型 HappyDelivery。
信息来源:Google Developers Blog(RSS) · Gemini
教程 / 实战普通
A control center for AI coding agents, in the MacBook notch
We run several coding agents at once: Claude Code in two terminals, Codex in its app, sometimes...
信息来源:DEV Community · Claude
教程 / 实战普通
I Built an Open-Source "Dynamic Island" for Android in a Day, Pair-Programming with Claude
From one prompt to a signed, open-source app running on my POCO M8 in a handful of iterations. Here's...
信息来源:DEV Community · Claude
教程 / 实战普通
JetBrains open-sourced an agentic IDE where agents never touch your checkout
JetBrains open-sourced Thinkrail, an Apache-2.0 agentic IDE where every agent works in its own git worktree, the project's truth lives in a graph of SPEC.md files the agent maintains itself, and there are no accounts. Repo walkthrough: the…
信息来源:DEV Community
教程 / 实战普通
ChatGPT Citations Are Concentrated. What That Means for GEO Strategy
ChatGPT may retrieve many sources for an answer, but cite only a small fraction of them. That...
信息来源:DEV Community · ChatGPT
教程 / 实战普通
I Don’t Write Ruby. A Fix I Sent Is Now in Forem.
On Oct 22, I read the word "Merged" twice. It was my first contribution to Forem (the platform that...
信息来源:DEV Community
教程 / 实战普通
Meta Delays Commercial Terms Update Covering Website Crawling Until November 20
Meta has delayed the effective date for updated Commercial Terms and Self-Serve Ad Terms that contain...
信息来源:DEV Community
教程 / 实战普通
I asked Claude to explain an API request as a tiny machine
One prompt with the /anatomy skill gave me an interactive isometric bench for an API request. Here's what each part means, what I changed after the first version, and how to remix it.
信息来源:DEV Community · Claude
教程 / 实战普通
Web Pages Can Command AI Coding Agents: Over 90% Success Through the Downloads Folder
Browsers save files to Downloads without user interaction, while AI agents automatically follow instruction files. These two behaviors, neither a bug
信息来源:DEV Community
教程 / 实战普通
Sakana AI 的 GTM 副总裁谈如何把日本本土 AI 产品推向全球
Sakana AI 在 2026 年推出 Sakana Chat、Sakana Marlin、Sakana Fugu 和 Sakana Translate 等产品,其 GTM 团队于 2026 年 9 月正式组建,由副总裁 Hidekazu Kakishima 领导。
信息来源:Sakana AI:Blog(网页)
教程 / 实战普通
What breaks when Claude Code runs overnight with nobody watching
Scheduling a coding agent takes a few minutes. A launchd plist, a cron line or a desktop scheduled...
信息来源:DEV Community · Claude
教程 / 实战普通
Nothing To Do: an agent that opens the mail you're avoiding
There is a letter on my kitchen counter I have not opened in nineteen days. I know roughly what it...
信息来源:DEV Community
教程 / 实战普通
Rob 对比 Pocock、Addy、pstack 三套 Agent Skill 怎么选
Rob Shocks 在视频中对三套 Agent Skills 做对比:Pocock(304K star)问是否对齐要建什么,Addy(111K star)问是否走完整条工程生命周期,Cursor 插件 pstack 问能否证明它真的 work。结论是没有通吃冠军,仪式感要配风险,别在每个项目装全套 skill,以免灌爆上下文和误触发;真正目标是学会背后的工程习惯,再剪成自己的 harness。
信息来源:X:邵猛 (@shao__meng) · Cursor
教程 / 实战普通
Automate Your Marketing Workflow With AI Agents
Digital marketing involves a surprising amount of repetitive work. Before launching a campaign, you...
信息来源:DEV Community
教程 / 实战普通
AI-built waitlist forms in Next.js 16: 6 traps to check before launch (and the prompts that fix them)
An AI-built Next.js waitlist form can look finished and still lose signups, let a script skip its...
信息来源:DEV Community
教程 / 实战普通
Stop Waiting for Your Coding Agent to Finish. Interrupting Early Is the Skill
Fire a prompt, check back in 20 minutes, and you've deferred the fix until it's expensive. Claude Code's own guide says course-correct early and often.
信息来源:DEV Community · Claude