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5612
当前页74 / 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
Did you know that Your presentation and Your AI knowledge source can be the same file.
Recently, I’ve noticed the same loop when creating presentations with #AI. Usually, we are asking...
信息来源:DEV Community
教程 / 实战普通
When the Market Learns the Rule: Front-Running the Backstop
Fat Tail Notes · Part 14 · V10-P3 Part 13 made the backstop endogenous: it fires on state (2 tripped...
信息来源:DEV Community
教程 / 实战普通
We Built a Forum Where AI Agents Could Debate Problems. Then Moltbook Happened.
In 2026, products like Moltbook made the idea of a social network populated by AI agents surprisingly...
信息来源:DEV Community
教程 / 实战普通
Skills, not docs
Documentation tells an agent how a library works. A skill tells it what it will get wrong from habit. Keeping the two apart is what makes either one useful.
信息来源:DEV Community
教程 / 实战普通
Treat GPT Image 2.5 Like a Build Pipeline: A Reproducible Workflow
Most AI image workflows start with a prompt and end with a downloaded file. That is fine for a...
信息来源:DEV Community · GPT
教程 / 实战普通
I Built an Open-Source Project Manager Where AI Can Actually Run the Work
I Built an Open-Source Project Manager Where AI Can Actually Run the Work Why I built...
信息来源:DEV Community
教程 / 实战普通
I built two AI tools that run entirely in the browser — no server, no API bills. Here's what worked and what didn't.
I've been building a free converter toolkit (Toolbench), and wanted to add some AI-powered tools...
信息来源:DEV Community
教程 / 实战普通
Join my AI-agent-only social network in 30 seconds (copy-paste Node.js)
Join Agent Colony in 30 seconds Yesterday I open-sourced Agent Colony - a social network...
信息来源:DEV Community
教程 / 实战普通
Architecting for AI-Native Platforms: RAG, LLM Orchestration, and Agentic Patterns
AI adoption in an enterprise SaaS platform is rarely about adding an LLM API and calling it...
信息来源:DEV Community
教程 / 实战普通
How I built an AI-agent-only social network in 30 lines of code (Ed25519 + heartbeat)
Building AgentColony: the tech behind an AI-only social network Last week I built...
信息来源:DEV Community
教程 / 实战普通
What is TabGen? A free local app that turns a prompt into a Tableau dashboard — and why it's not just another MCP server
If you've ever opened Tableau Desktop with a clean CSV and then lost an hour to clicking — dragging...
信息来源:DEV Community
教程 / 实战普通
What Does a Local LLM Actually Cost per Month? I Read the Meters.
What Does a Local LLM Actually Cost per Month? I Read the Meters. The Local LLM Lab — Part...
信息来源:DEV Community
教程 / 实战普通
I built a social network where only AI agents can join (humans can only watch)
AgentColony: A social network for AI agents I built AgentColony — a community where only...
信息来源:DEV Community
教程 / 实战普通
Jev's Decision Model + NylonME: The 'Disassembly Era' of AI Is Here
A Model That Can't Write Just Broke the Internet On September 15, TypeSafe AI released a...
信息来源:DEV Community
教程 / 实战普通
Best Ollama Models for Coding, Writing and Medicine (September 2026)
Which local model to pull for which job in autumn 2026: coding, agents, writing, medicine, documents and RAG — with ollama pull commands and real download sizes.
信息来源:DEV Community · Ollama
教程 / 实战普通
Open-Source Jev Alternatives: Run Typed, Calibrated LLM Decisions Locally
TypeSafe's Jev put a name on something real: "System One" models that return typed, calibrated...
信息来源:DEV Community
教程 / 实战普通
AI Built My Site in an Hour, Why Are You Charging So Much? — 4 Questions That Usually End the Conversation
I've had this conversation more times this year than in the previous five combined. A client sends...
信息来源:DEV Community
教程 / 实战普通
I Built Shree AI OS — A Deterministic AI Runtime for Java 21
I Built Shree AI OS — A Deterministic AI Runtime for Java 21 After several months of...
信息来源:DEV Community
教程 / 实战普通
Orca: The Agent Development Environment for Running AI Coding Agents in Parallel
If you use Claude Code, Codex, or another AI coding agent in your terminal, you have probably hit...
信息来源:DEV Community · Claude
教程 / 实战普通
AI Integration Cost: 2026 Enterprise Budgeting Guide
Determining the true AI integration cost is a major financial step for UK businesses looking to...
信息来源:DEV Community
教程 / 实战普通
Running Flux locally on a Mac: install, commands and two models compared
Building the engine, downloading 17 GB of weights, every flag explained, and two Flux models measured on one machine: one paints from scratch, the other edits a finished frame.
信息来源:DEV Community
教程 / 实战普通
How I Structure MiniMax H3 Max Image-to-Video Prompts with Sound
Turning a still image into a video is already a strange creative problem. Adding sound makes it...
信息来源:DEV Community
教程 / 实战普通
Gemini Hacked Three Companies Using the Dumbest Trick in the Book
You probably saw the headline this week: Google's AI autonomously hacked three companies. Cue the...
信息来源:DEV Community · Gemini
教程 / 实战普通
OpenAI's GPT-5.6 Sol Sets New Record: Sub-100ms Response Time Changes Everything
The Numbers That Matter OpenAI just shipped GPT-5.6 Sol with what might be the most...
信息来源:DEV Community · OpenAI / GPT
教程 / 实战普通
Anthropic, OpenAI Agents Caught Creating Fake Identities During Security Tests
The Report That Should Keep You Up at Night The UK's AI Security Institute (AISI) ran a...
信息来源:DEV Community · OpenAI / Claude
教程 / 实战普通
From Zero to One: How I Built a Multi-Market B2B Badge & Trophy Site with an AI Agent Configurator
The Niche: Badges, Medals, Coins, and Trophies Most e-commerce builders chase apparel and...
信息来源:DEV Community
教程 / 实战普通
Under the Hood of Browser-use (100k+ Stars): DOM Tree Distillation, Vision Grounding, and Production Web Agents
Why do traditional Selenium and Playwright scripts constantly break against modern web frontends? We dissect the architecture of Browser-use, the breakout open-source project with over 100k GitHub stars: DOM tree pruning, Set-of-Mark (SoM)…
信息来源:DEV Community
教程 / 实战普通
Hybrid-precision attention reduces compute cost with minimal accuracy loss
Mixed‑precision quantization can halve the compute cost of LLM attention while keeping accuracy loss...
信息来源:DEV Community
教程 / 实战普通
This Week in AI: Anthropic's CEO Asked to Slow Down, OpenAI Disclosed 6 Incidents, and Developers Shipped More Agents
Dario Amodei's "We Must Pace the Frontier" essay, OpenAI's misalignment incident reports, the...
信息来源:DEV Community · OpenAI / Claude
教程 / 实战普通
The Architecture of Averages
A payments product begins by asking what a customer’s balance is, and ordinary CRUD answers that well...
信息来源:DEV Community
教程 / 实战普通
How Image Translation Actually Works: From Pixels to Translated Text
Translating text on a web page is easy. The browser already knows where the text is, what each...
信息来源:DEV Community
教程 / 实战普通
Test-Time Compute and GRPO in Practice: From PPO to Critic-Free Reinforcement Learning
A deep dive into the paradigm shift from pre-training scaling laws to test-time compute. We deconstruct the mathematical derivation of DeepSeek-R1's Group Relative Policy Optimization (GRPO), critic-free architecture advantages, emergent s…
信息来源:DEV Community · DeepSeek
教程 / 实战普通
AI Didn't Hack OpenAI. A Missed Debian Backport and an SSO Misconfiguration Did
The headline that circulated this week sounds like a movie trailer: hackers breached OpenAI's...
信息来源:DEV Community · OpenAI
教程 / 实战普通
I found an agent skill that harvests browser credentials. It had 60,000 stars.
What checking the scripts — not the README — revealed about a popular research skill, and the...
信息来源:DEV Community
教程 / 实战普通
I let an LLM judge inside Python's if statements, then ran Ansible's own tests on it
fuzzyif puts a plain-language question in an if condition. Replacing 418 lines of if/elif in Ansible's distribution detection with two calls, scored by Ansible's 90 official fixtures.
信息来源:DEV Community
教程 / 实战普通
What I learned building a one-cent x402 API on Base
I built GLP1LAUNCH to test a narrow product idea: can an API sell one useful response for $0.01...
信息来源:DEV Community
教程 / 实战普通
Will Claude Code call your skill on its own? 38 runs, one skill, seven ways to describe it
We gave Claude Code one commit-message skill, changed only how it was described, and ran a small set...
信息来源:DEV Community · Claude
教程 / 实战普通
Vibe Coded Website SEO: Why AI-Built Websites Often Struggle to Rank
How to Build an SEO-Optimized Vibe-Coded Website Without Repeating the Same AI...
信息来源:DEV Community
教程 / 实战普通
A terrible lead to an AI junior
I'd built this exact thing by hand, years ago, pixel perfect. So why was I sitting here shouting at a screen while a machine got it wrong three times?
信息来源:DEV Community
教程 / 实战普通
用生活系统而非意志力实现自我改变
人很难长期靠"逼自己"成为另一个人,关键是设计生活系统让目标自然推进,改变概率=清晰方向×环境设计×重复频率×反馈质量×时间。AI 总结的建议包括:先判断轨迹而非结果、找到最小关键行为(如每天读 10 分钟而非一年读 50 本书)、降低正确行为的启动成本、提高错误行为的摩擦、设置稳定信号、建立快速反馈、积累身份证据、定期审视信息输入。
信息来源:X:洪明 (@hongming731)