AI Tutorials & Practice
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。
Category articles4769
当前页17 / 120
UpdatesPermanent archive
Category articles
按发布Time从新到旧 · 每页 40 stories
TutorialsOrdinary
Tiny model. Big decisions. — How I built a 144M-parameter typed decision model that routes 82% of agent decisions off LLMs
Tiny model. Big decisions. — How I built a 144M-parameter typed decision model that routes...
Source: DEV Community
TutorialsOrdinary
Your CEO Sees 5x. Your Engineers See a Longer Review Queue.
Two surveys, one season, and two very different companies. Between December 2025 and January 2026,...
Source: DEV Community
TutorialsOrdinary
Are Frontend Developers Wasting Tokens? 5 Ways to Cut AI Coding Costs
When you have an AI agent open all day, it's really easy to burn through a lot of tokens quickly. And...
Source: DEV Community
TutorialsOrdinary
My coding agent now tells me to go outside, and a 4 GB Gemma writes the message
This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 1. You send one more...
Source: DEV Community
TutorialsOrdinary
Your Is Invisible to AI Agents
I Found Out What an AI Agent Actually Sees When It Looks at My Buttons Imagine describing...
Source: DEV Community
TutorialsOrdinary
People Loved My Software Until I Admitted I Used AI
To the casual observer, the current artificial intelligence boom looks like a wave of digital...
Source: DEV Community
TutorialsOrdinary
MCP vs API: When to Build an MCP Server, and When the API Is Enough
MCP vs API is rarely an either-or choice: MCP is a protocol that lets an AI agent discover and call...
Source: DEV Community
TutorialsOrdinary
We checked 46 popular MCP servers on Smithery: 7 in 10 tools never say when to use them
We took 46 of the most-used MCP servers on Smithery and checked the descriptions of all 1,118 of...
Source: DEV Community
TutorialsOrdinary
Cents Matter: Does a Model Notice When One Financial Fact Changes?
This is a submission for the Kaggle Benchmarking Challenge. What I Benchmarked A...
Source: DEV Community
TutorialsOrdinary
Frostwise — know your frost dates, plant with confidence
Frostwise — know your frost dates, plant with confidence DEV Hacktoberfest AI Challenge —...
Source: DEV Community
TutorialsOrdinary
Fine-tuning Qwen2.5-1.5B on a Mac to fix a parroting chatbot (and halve the prompt)
By Georgii Kharlampiiev, Mindscend Our company website is a single chat page backed by a model we...
Source: DEV Community · Qwen
TutorialsOrdinary
Don't Baptize the GPUs
Why AI systems should be measured by running them, trained to seek truth and owned by the organizations that depend on them, rather than blessed into a theological category.
Source: DEV Community
TutorialsOrdinary
Mental Model AI & Cara Menghindari Zombie UI: Rangkuman Insight Katie Dill (Stripe)
Mental Model AI & Cara Menghindari Zombie UI Di era kecerdasan buatan (Artificial...
Source: DEV Community
TutorialsOrdinary
I let an AI agent drive my remote desktop. It can't touch my passwords.
It's 11 PM. Three servers need the same patch, and I'm alt-tabbing between four remote windows. Two...
Source: DEV Community
TutorialsOrdinary
5 MCP Security Tests to Run Before Your AI Agent Gets Tool Access
Your LLM passed every prompt-injection test. Your agent can still be hijacked. The difference is...
Source: DEV Community
TutorialsOrdinary
Frost Window: 30 years of weather and a laptop-sized Gemma tell you what to do outside this week
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...
Source: DEV Community
TutorialsOrdinary
Google Preferred Sources Adds Publisher Selection Counts and an On-Site CTA Button
Google Preferred Sources is becoming more measurable for publishers. Google says readers who choose a...
Source: DEV Community
TutorialsOrdinary
My agent guardrail was fine. Its kubectl parser wasn't.
I maintain Aegis-DevOps, an open-source check that sits between an AI coding agent and the shell....
Source: DEV Community
TutorialsOrdinary
Can Two Small Nets Invent a Language?
Before testing any grand claim about emergent communication, I ran the only question that mattered first: does a substrate even exist?
Source: DEV Community
TutorialsOrdinary
Claude Haiku 5.5 pricing jumps fivefold at 100,001 prompt tokens
A request to Claude Haiku 5.5 with a 100,000-token prompt and 2,000 tokens of output costs $0.011....
Source: DEV Community · Claude
TutorialsOrdinary
Making cross-platform local AI easier with llamadart
My writing assistant could talk to Gemini. The missing piece was using it without a connection. That...
Source: DEV Community · Gemini
TutorialsOrdinary
Obsidian + Claude Code: The Shared Memory Stack I Actually Use
My notes used to be where ideas went to die. Obsidian was my beautiful, over-organized graveyard....
Source: DEV Community · Claude
TutorialsOrdinary
Your coding agent is only trustworthy where you can inspect its work. Draw that line.
Stack Overflow's 2026 survey: 67% of developers use AI to generate code in areas they know, but only 20% use it in production. The line between them is verifiability. Here is how to draw it as a workflow rule instead of a feeling.
Source: DEV Community
TutorialsOrdinary
Tendril: a garden assistant you barely have to open
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass. ...
Source: DEV Community
TutorialsOrdinary
My Eval Said RAG Made Things Up. My Eval Was Wrong.
I maintain django-explain-errors, a Django middleware that catches unhandled exceptions in...
Source: DEV Community
TutorialsOrdinary
Honest struggles of bringing AI into everyday work – what I’m seeing and what I’d love to hear from developers
I’m Seohyun, an AX Researcher at Knowverse. My job isn’t to build models or maintain infrastructure;...
Source: DEV Community
TutorialsOrdinary
Microsoft Brings MAI Code 1.1 Flash Local Inference to GitHub Copilot
Microsoft plans to bring MAI Code 1.1 Flash to local coding workflows in GitHub Copilot, allowing...
Source: DEV Community
TutorialsOrdinary
Janela — a local Gemma tells you when to go outside (and why)
This is a submission for the Hacktoberfest 2026 Open-Source AI Challenge, Week 1: "Touch Grass". ...
Source: DEV Community
TutorialsOrdinary
"My Mergetober story: building a BambooHR connector for cognee"
This Mergetober I wanted to do more than fix a typo. I wanted to build something real, get it...
Source: DEV Community
TutorialsOrdinary
The AI That Never Leaves My Laptop
Show almost any enterprise a useful AI workflow and the demo goes well right up until someone from...
Source: DEV Community
TutorialsOrdinary
fieldmemo: keep the phone in your pocket, talk to it, get a field journal at home
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass AI...
Source: DEV Community
TutorialsOrdinary
What happens to the Developer?
Recently, I've been struggling more and more with the way we're using AI to automate nearly every...
Source: DEV Community
TutorialsOrdinary
I built a blogging platform where you have to type every word by hand
I got tired of wondering whether anything I read online was written by a person. So I built...
Source: DEV Community
TutorialsOrdinary
Timeless Stopwatch: An Open-Source AI Companion Built for a Friend
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend. ⏱️...
Source: DEV Community
TutorialsOrdinary
WildPulse: The Zero-Signal Trail Naturalist That Tells You to Put Your Phone Away
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...
Source: DEV Community
TutorialsOrdinary
Slopsquatting: The Supply Chain Attack Your AI Coding Assistant Might Be Setting Up For You
You ask your AI assistant for a quick script. It writes clean code, imports a package you've never...
Source: DEV Community
TutorialsOrdinary
Why your planner-executor split is creating more problems than it solves?
I spent three weeks trying to fix a planner-executor pipeline that was failing in a way I couldn't...
Source: DEV Community
TutorialsOrdinary
Five agent episodes, and the build decision to take from each
Pull one concrete build decision from each Chain of Thought episode in the agents collection, from context to memory, stacks, and coordination.
Source: DEV Community
TutorialsOrdinary
OpenAI Launches Interactive Learning Visuals in ChatGPT for Hands-On Answers
OpenAI has launched interactive learning visuals in ChatGPT, adding hands-on modules that let users...
Source: DEV Community · OpenAI / ChatGPT
TutorialsOrdinary
Does a design system change what a coding agent writes?
A while ago I finished a piece of work I was proud of: a design system built the way I'd argue a...
Source: DEV Community