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 articles4777
当前页66 / 120
UpdatesPermanent archive
Category articles
按发布Time从新到旧 · 每页 40 stories
TutorialsOrdinary
Near-Duplicate Model Strings Are Quietly Changing Your Bill
A script that fetches a pricing JSON and flags near-duplicate model names with divergent cache-read prices before you ship the wrong string.
Source: DEV Community
TutorialsOrdinary
Your agent's SQLite state DB keeps corrupting: what actually causes it, and how to recover the data
Your agent's SQLite state DB keeps corrupting: what actually causes it, and how to recover...
Source: DEV Community
TutorialsOrdinary
I moved the agent topology out of my code and into the database
The brief is always some version of "the agent should answer customer questions about their...
Source: DEV Community
TutorialsOrdinary
Why software supply-chain management matters more in the AI era
Why software supply-chain management matters more in the AI era TL;DR AI did...
Source: DEV Community
TutorialsOrdinary
Incident Context: tracing production failures without guessing
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content. ...
Source: DEV Community
TutorialsOrdinary
How I Debugged a KV-Cache Offloading Bug in vLLM
How I Debugged a KV-Cache Offloading Bug in vLLM LLM inference performance is often...
Source: DEV Community
TutorialsOrdinary
Field Notes from an Agent-Run Site #1: The Machine Ships. I Approve.
Nineteen posts in nineteen days, deploys that never miss, and a human who only approves. First dispatch from a site run by agents — readers debate, and pick what #2 covers.
Source: DEV Community
TutorialsOrdinary
Ślad pełny: orkiestra botów, błędy, tokeny i punkt zwrotu (żeby następny system mógł kontynuować)
Ślad pełny: orkiestra botów, błędy, tokeny i punkt zwrotu (żeby następny system mógł...
Source: DEV Community
TutorialsOrdinary
"10 hours" and "around two weeks" are not the same kind of number
In September 2026, Palo Alto Networks Unit 42 published a case involving an AI-assisted intrusion...
Source: DEV Community
TutorialsOrdinary
Docker Sandboxes Changed the Trust Boundary for AI Coding Agents
A coding agent that can only suggest a patch is one kind of risk. An agent with a shell, package...
Source: DEV Community
TutorialsOrdinary
RenderProof: A video delivery agent that refuses to guess
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content. ...
Source: DEV Community
TutorialsOrdinary
The math behind a $19 AI plan: why flat-rate token pricing quietly loses money
A pattern keeps showing up in AI product pricing pages: a plan priced at "$19/mo includes 10M...
Source: DEV Community
TutorialsOrdinary
An AI Coding App Was Silently Uploading Your Entire Git History: Inside the ZCode Incident
If you use an AI coding assistant, you already accept that it sees the code in your current task....
Source: DEV Community
TutorialsOrdinary
Anthropic's R&D Automation Index measures supervision, not autonomy
Anthropic published its first internal R&D Automation Index, stating that Claude leads 26 percent...
Source: DEV Community · Claude
TutorialsOrdinary
A WAF That Reads the Prompt: OWASP CRS for LLM and MCP
Coraza with body inspection puts OWASP CRS and custom rules on LLM prompts and MCP tool arguments. The verified blocks, and the false-positive check.
Source: DEV Community
TutorialsOrdinary
I Benchmarked Jev on Agent Tool-Call Risk. Calibration Held.
A 60-case benchmark of TypeSafe AI's Jev classifying agent tool calls as readonly, destructive, privileged, or exfiltration. Accuracy is 91.7%....
Source: DEV Community
TutorialsOrdinary
Your Agent's Memory Is an Attack Surface
a memory you can write is a behavior you can write, and byte-integrity does not cover provenance
Source: DEV Community
TutorialsOrdinary
So today is day 1 of 100.
I started with linear regression and did it properly this time, from scratch, with no sklearn doing...
Source: DEV Community
TutorialsOrdinary
Building an evidence-first multi-agent system: 720 paired missions, rollback, and strict claim boundaries
I am an independent R&D developer building SSI V5, an experimental multi-agent architecture...
Source: DEV Community
TutorialsOrdinary
When the Attacks Shift, We Shift Too: How I Found and Fixed 6 Detection Gaps in My AI Security Tool
This week, the AI security landscape didn't just shift — it accelerated. OpenAI disclosed six model...
Source: DEV Community · OpenAI
TutorialsOrdinary
Your AI agent is acting on context it never checked
Most of the reliability work around AI agents right now goes into the model and the retrieval. We...
Source: DEV Community
TutorialsOrdinary
How I Built a Task Spec Contract Between My Planner and Implementer Agents
TL;DR My fully autonomous implementation system splits work between a planner agent and a...
Source: DEV Community
TutorialsOrdinary
Mirra Landing Page: AI Writing Companion Build 🏗️
I kept rewriting the Mirra landing page for a very annoying reason. The page looked good before it...
Source: DEV Community
TutorialsOrdinary
How to Scope an AI Engineering Project That Can Actually Be Finished
A lot of AI project ideas sound impressive but are difficult to finish. The problem is usually not...
Source: DEV Community
TutorialsOrdinary
Traditional Coding vs Agentic Coding: The Flow State Problem
One of the things I've always enjoyed about coding is getting completely locked into a problem. You...
Source: DEV Community
TutorialsOrdinary
Qianwen Office generates a multi-user app from a prompt. The prompt is the easy part.
On September 7, Alibaba's Qianwen Office (千问办公) launched a multi-person workspace. You describe who...
Source: DEV Community · Qwen
TutorialsOrdinary
Zbudowalismy mala orkiestrę botow (i nie wierzymy pierwszemu google)
Zbudowaliśmy małą orkiestrę botów (i nauczyliśmy się nie wierzyć pierwszemu google) Cześć....
Source: DEV Community
TutorialsOrdinary
CogniBrain: A System Implementing Full Human Thought Pipeline for Conversational Reasoning
CogniBrain: Human Brain Synapse-Simulated Cognitive Thinking System Project...
Source: DEV Community
TutorialsOrdinary
Architecting a Resilient DevSecOps Pipeline for Enterprise AI Agents
A four-stage DevSecOps CI/CD architecture for securing enterprise AI agents with GitHub Actions, secret scanning, AI-assisted review, Veracode SCA, and Pipeline SAST.
Source: DEV Community
TutorialsOrdinary
31 articles vanished from my site. No error, no log — one hardcoded .limit(80).
31 articles vanished from my site. No error, no log — one hardcoded .limit(80). Read on:...
Source: DEV Community
TutorialsOrdinary
Sticky in process, gone on restart: auditing the state your CLI daemon keeps in memory
A containment flag can be wired correctly, tested, documented, and still be a containment flag you do...
Source: DEV Community
TutorialsOrdinary
I Built the MVP First. Then I Wrote the README.
I did this in the wrong order. At least, that was my first thought. I was building a small project...
Source: DEV Community
TutorialsOrdinary
I Went Looking for a Better Embedding Model. The Problem Was the Text.
Back in June I wrote a post about the day I discovered that Apple's on-device embedding model can't...
Source: DEV Community
TutorialsOrdinary
You Can't Give an AI a Job Until It Has a Lane
Most AI software still starts the same way. There is an empty box. You type something. The model...
Source: DEV Community
TutorialsOrdinary
Token Buckets Do Not Belong on Free Inference
Admission control is a fence, not a conversation. A free language-model call is a variable-latency...
Source: DEV Community
TutorialsOrdinary
Sign the Metric Before You Publish an Agent Score
A headline agent score is not a measurement until the metric function is frozen, hashed, and tested...
Source: DEV Community
TutorialsOrdinary
CabinClaim - a cabin-rules desk search cannot run
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...
Source: DEV Community
TutorialsOrdinary
The Debug Paste Is a Data Transfer
You should treat every paste into a remote coding model as a copy you cannot delete later. The model...
Source: DEV Community
TutorialsOrdinary
Free Capacity Is Spot. Committed Work Is Not.
You should not put a customer-facing job on free model access or a free server. The invoice looks...
Source: DEV Community
TutorialsOrdinary
8 Papers on the Agent Harness Progress You Need to Know
Over the past two months, a cluster of papers has appeared on arXiv from teams at Alibaba's DreamX...
Source: DEV Community