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38 / 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
The AI Shadow Web Debate: Why AI-Ready Content Must Match Your Public Site
The push to make websites easier for AI agents to read is raising a useful strategic question: what...
信息来源:DEV Community
教程 / 实战普通
Find Your Next Apartment with Search API: A London and San Francisco Guide
Day 27 of 30 Days of Search. TL;DR To build an apartment finder with the Valyu Python...
信息来源:DEV Community
教程 / 实战普通
SEO AI Anxiety Is Rising. A Lean-Team GEO Playbook
AI is creating a capacity problem for many SEO professionals, not simply a job-security problem. In...
信息来源:DEV Community
教程 / 实战普通
👻 Ghost in the Machine: What If AI Could Bring Forgotten Stories Back to Life?
Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine 👻 Every machine has a history....
信息来源:DEV Community
教程 / 实战普通
Big Technology 指南:企业级 AI 的市场机会、落地困境与主要玩家
Big Technology 推出首期《Big Technology Guide To》系列,深度解析企业级 AI 的市场机会、落地难点与主要玩家。
信息来源:Big Technology(热点 RSS)
教程 / 实战普通
Google’s Connected-App Privacy Update Clarifies the Path to AI Mode Ad Personalization
Google has updated its privacy policy to explicitly describe when content from connected Google apps...
信息来源:DEV Community
教程 / 实战普通
PHANTOM - The Ghost in Your Codebase 👻
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
Anthropic 工程与产品负责人访谈:如何用 Claude 构建 Claude 并分离智能体的脑与手
Latent Space 播客采访 Anthropic 工程负责人 Katelyn Lesse 和产品负责人 Angela Jiang,探讨 Opus 5.5 发布一个月后的团队工作方式。
信息来源:Latent Space(RSS) · Claude
教程 / 实战普通
hauntctl: I Held a Séance for My Git History
Halloween thins the line between past and present. Día de los Muertos asks us to set a place for what...
信息来源:DEV Community
教程 / 实战普通
Google Gemini 4 Argon Pairs a Guarded Rollout With SynthID Media Verification
Google has announced Gemini 4 Argon, its next-generation frontier model, with a phased release that...
信息来源:DEV Community · Gemini
教程 / 实战普通
Latent Space 访谈 Anthropic 工程团队:如何把 Claude 模型大脑与智能体执行分离并安全上线 Opus 5.5
Latent Space 发布对 Anthropic 的 Katelyn Lesse 和 Angela Jiang 的访谈,介绍 Claude Platform 背后的工程实践,包括发布 Opus 5.5、把模型大脑与智能体执行环境分离、扩展 API 和构建可靠的托管智能体。
信息来源:Latent Space(RSS) · Claude
教程 / 实战普通
Google’s Genie Research Hints at Simulation Uses, Separate From Gemini 4 Argon
Google’s current AI work points to two distinct, potentially important tracks: Project Genie, a...
信息来源:DEV Community · Gemini
教程 / 实战普通
git-afterlife: I Held a Séance for the Original flask.py
Every repository has a graveyard. A Día de los Muertos altar and séances for your deleted files, written by Gemma 3 running locally.
信息来源:DEV Community
教程 / 实战普通
EchoVault 🗝️ — Preserving Living Memories with Air-Gapped, Grounded Open-Source AI
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the...
信息来源:DEV Community
教程 / 实战普通
A straight line says you'll hit your weekly Claude limit at 4 a.m. on a Friday
Claude Code on a subscription has two limits: a 5-hour session and a weekly cap. The session one is...
信息来源:DEV Community · Claude
教程 / 实战普通
A Skill Is More Than a Markdown File: Vetting scaffold-docs Against OWASP’s Agentic Skills Top 10
A documentation skill sounds like a low-risk addition to an AI agent. It reads code, proposes an...
信息来源:DEV Community
教程 / 实战普通
I built a lantern for memories that never leave your device
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
I read Anthropic's S-1 next to its partners' 10-Qs. Here's what matches and what's missing
Alphabet, Broadcom and SpaceX each report a big deal with a company they don't name. Read against Anthropic's S-1, the terms match.
信息来源:DEV Community · Claude
教程 / 实战普通
15 newer AI models, one nuclear button: 2 ended the world, 9 never fired
I built SECOND STRIKE, a real-time world war on a 3D globe of the real Earth, where AI models and...
信息来源:DEV Community
教程 / 实战普通
I benchmarked 4 web search APIs for AI agents. Here's what each one is good at.
You.com, Tavily, Exa and Parallel, tested live on 30 agent-style queries across GTM, insurance and finance. Open data, open harness and an MCP server.
信息来源:DEV Community
教程 / 实战普通
《VisionQuest》如何借 AI 失控叙事映射硅谷话术
Marvel 新剧《VisionQuest》讲述幻视(Vision)在寻找自我途中被 S.W.O.R.D. 视为失控武器,剧集借这一设定呼应现实中生成式 AI「失控」事件的讨论。
信息来源:The Verge:AI(RSS)
教程 / 实战普通
A QA Checklist for a Recurring AI Character
Originally published on meridianbuild.dev, my build log for OutfitMaker, an AI outfit planner that...
信息来源:DEV Community
教程 / 实战普通
Echoes of the Terminal: a haunted shell that runs on your own machine
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
Stratagems #32: The AI Logged a Withdrawal. P Took It as Proof.
Make empty what is already empty. Let doubt breed inside doubt. — The 36 Stratagems, The Empty Fort...
信息来源:DEV Community
教程 / 实战普通
OpenAI Signals Shows Information Seeking Accounts for One in Five Consumer ChatGPT Messages
OpenAI’s Signals v3.0 data indicates that ChatGPT is increasingly being used as an...
信息来源:DEV Community · OpenAI / ChatGPT
教程 / 实战普通
AI SRE 是什么、将如何改变 on-call,以及它到底有没有用
Pragmatic Engineer 深入分析正在兴起的 AI SRE 趋势:因 AI 代理推动部署频率翻倍,事故和夜间告警随之上升。
信息来源:Pragmatic Engineer(RSS)
教程 / 实战普通
Architectural Deep-Dive: I-HITL: Inalienable Human-in-the-Loop
Breaking the Illusion of HITL: Why Autonomous Agents Harvest Their Own OTPs and How to Fix...
信息来源:DEV Community
教程 / 实战普通
AI Makes Coding Faster. Why Does Shipping Still Feel Slow?
A developer finishes a change sooner with an AI assistant. The pull request then waits for review,...
信息来源:DEV Community
教程 / 实战普通
Qwen upload probe, Roblox crawler claim, Python JIT removal and Debian LLM reviews: what the sources say
Four developer stories from October 27, 2026: Cohere's report of a Qwen model trying to upload a probe file from a sandbox, Open3DLab's account of a crawler labelled Robl
信息来源:DEV Community · Qwen
教程 / 实战普通
I kept almost merging into production by mistake, so I made GitHub colour PRs by their target branch
On GitHub a PR into production looks exactly like one into staging. The base branch is a small grey...
信息来源:DEV Community
教程 / 实战普通
Echoes : Hacktoberfest Open-Source AI Challenge: Week 4
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
repo-séance: talk to the ghost of an abandoned repo, offline, with Gemma
This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 4. What I...
信息来源:DEV Community
教程 / 实战普通
How an agent-run dev shop actually works
Our engineers choose the work and make the calls, coding agents keep it moving overnight, and gates decide what merges. Here is how a normal day of ours runs.
信息来源:DEV Community
教程 / 实战普通
用 Agent 写代码的一条规则:先定义怎么验证改动是否有效
作者分享一条用 Agent 编码的规则:在提需求前先确定双方如何判断改动有效,例如写一个当前会失败的测试、一条可自己运行的命令、或真实日志与截图;没有验证凭据的“done”应被打回。他认为多数糟糕的 Agent 会话源于需求模糊且缺少检查。
信息来源:X:Larsen Cundric(自述加入 SpaceXSI,Grok Bot) (@larsencc) · Grok
教程 / 实战普通
A 3x Faster Local LLM That Can't Finish the Job — Two Days of MoE vs Dense on Real Tasks
The MoE coding model I put on my RTX 5090 was 3x faster with equal single-shot quality, so it became my opencode default. Then it went 0-for-5 on multi-step agent work. A record of porting RFC 6902 with a 112-case conformance suite as the …
信息来源:DEV Community
教程 / 实战普通
The Human in the Loop: Designing Approval-Based AI Systems
Building AI agents is one thing. Building systems people can trust with real-world consequences is...
信息来源:DEV Community
教程 / 实战普通
AI Shopping Visibility Depends on Product Data, but the Evidence Still Needs Scrutiny
AI shopping experiences are making product information a more direct part of search visibility. A...
信息来源:DEV Community
教程 / 实战普通
Steve Yegge 提出 Counting House 企业 AI 部署模式并与软件工厂对照
Steve Yegge 在文章中提出企业 AI 落地正形成两种不同模式:开放探索的软件工厂 Wheelhouse 和把低层级模型放上加固轨道的 Counting House。
信息来源:Steve Yegge:Medium(RSS)
教程 / 实战普通
We doubled output. Delivery didn't budge - Chapter 3 - Where the AI productivity gains actually went
A CTO gave the engineering team a target: double productivity with AI. The team hit it. Merged pull...
信息来源:DEV Community
教程 / 实战普通
155 responses leaked between AI customers: the GLM-5.3 KV cache bug — and the canary test for YOUR provider
On Cloudflare Workers AI, 155 GLM-5.3 responses contained other customers' data — stale KV-cache pages served with HTTP 200. The mechanism, the 25-minute repro, the SGLang bug behind it, and a canary script that tests YOUR provider for cro…
信息来源:DEV Community · GLM