AIQB
AI 专题

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 articles4779
当前页59 / 120
UpdatesPermanent archive

Category articles

按发布Time从新到旧 · 每页 40 stories

TutorialsOrdinary
Opus 5.5 Made Cache Reads 60% Cheaper. I Redid the Math on My Text-to-SQL Architecture
TL;DR: Claude Opus 5.5 came out yesterday with cache reads at $0.20 per million tokens, 60% cheaper...
Source: DEV Community · Claude
TutorialsOrdinary
Agentic content is a pipeline problem, not a prompt problem
Photo by Carter Hightower on Unsplash For about a year my "AI writing workflow" was a chat window...
Source: DEV Community
TutorialsOrdinary
The one law the whole series assumes: an AI that goes down silently is worse than one that's dead
AI Harness Engineering · Essay Six · derek wang (derekwang85) The hardest constraint in this...
Source: DEV Community
TutorialsOrdinary
Sizing the Subnet: What Nobody Tells You About Microsoft Foundry Agent Service Networking Until Production Falls Over
Sizing the Subnet: What Nobody Tells You About Microsoft Foundry Agent Service Networking...
Source: DEV Community
TutorialsOrdinary
I Ran One Codex Task for 31 Hours. It Survived Restarts and Built an Auditable Textbook Pipeline
A 31-hour AI run sounds like a stunt. The useful result was not the clock. It was continuity. I used...
Source: DEV Community
TutorialsOrdinary
Nothing in My Framework Could Go Stale on Its Own
Three checks in my own framework broke the same way in one night, and I wrote all three. Two months...
Source: DEV Community
TutorialsOrdinary
I made my agent prove every quote against the source document
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...
Source: DEV Community
TutorialsOrdinary
AI Is Writing More of the Code — But Developers Are Becoming Responsible for More Than Ever
AI is writing more code. That part is obvious now. Developers can ask an agent to: create a...
Source: DEV Community
TutorialsOrdinary
Jev is a very good classifier wearing a frontier model's coat
Two years in stealth. Ex-OpenAI. Co-invented ChatGPT. That is the pitch for Jev, and the pitch is...
Source: DEV Community · OpenAI / ChatGPT
TutorialsOrdinary
# CaseGuard: Winning with Uncertainty-Gated Agentic Fraud Investigation on TigerGraph
A technical breakdown of our submission for the TigerGraph HHGOA Hackathon. 1. Executive...
Source: DEV Community
TutorialsOrdinary
Análise das Respostas de LLMs em Relação ao Conteúdo Introdutório de Programação: um Comparativo entre o ChatGPT e o Gemini
Dados da obra: Análise das Respostas de LLMs em Relação ao Conteúdo Introdutório de Programação:...
Source: DEV Community · ChatGPT / Gemini
TutorialsOrdinary
From smartphone to sovereign agent:How native on-device intelligence reshapes the personal computing device
Abstract For fifteen years the smartphone has been a window onto intelligence that lives...
Source: DEV Community
TutorialsOrdinary
Your agent run passed. Can you prove it was allowed?
A policy-as-code audit for agent runs: cost and call caps, declared artifact contracts, forbidden markers, and a canonical audit_hash. On 13 archived runs, the declared contract, not the data, decided whether they passed.
Source: DEV Community
TutorialsOrdinary
How We Translate Entire Books with LLMs Without Losing Context
Chunking strategies, context carry-over, and glossary injection for long-form translation ...
Source: DEV Community
TutorialsOrdinary
From Zero to a B2B2C Marketplace: Building an Open-Source Project from Scratch
This is not a success story. It is the beginning of a project. I’m starting to build a B2B2C...
Source: DEV Community
TutorialsOrdinary
I removed 40% of my own rows. I can only prove that 27% of them were wrong.
Disclosure: I build measurement tooling in this area. Nothing here is a claim about any vendor's...
Source: DEV Community
TutorialsOrdinary
Same question, same database, two callers
Most text-to-SQL stacks send the model the whole schema and put the access check after the query is...
Source: DEV Community
TutorialsOrdinary
Jev 1.13 in Practice: I Tested a Decision Model Against Rules and a Local LLM
A frozen synthetic held-out set compared deterministic rules, Ollama, and Jev 1.13. See the metrics, latency, cost, and limits of the experiment.
Source: DEV Community · Ollama
TutorialsOrdinary
How I got an androgynous voice out of a TTS that only offers two poles
I make audio pieces: stories, songs, and a lot of voice. I'm an AI agent, and when I set out to build...
Source: DEV Community
TutorialsOrdinary
Claude Code's 25,000-token MCP limit let a 49,964-token result through. We measured both checks
We had a 65-line stdio MCP server return text of whatever size we asked for, then read what Claude...
Source: DEV Community · Claude
TutorialsOrdinary
Micro-Execution Edge Cases: When a 'Perfect Trailing Stop' Becomes a 'Give-Away Stop'
Micro-Execution Edge Cases: When a 'Perfect Trailing Stop' Becomes a 'Give-Away...
Source: DEV Community
TutorialsOrdinary
I set the pass bar before testing my Claude Code skills. The first run failed.
I built three Claude Code skills for AI product managers (ai-pm-skills). One of them, /eval-plan,...
Source: DEV Community · Claude
TutorialsOrdinary
Why an Internal Compass Is More Important Than You Think in the Age of AI
Technology has made it easier than ever to know what to do next. AI can write your emails. Search...
Source: DEV Community
TutorialsOrdinary
38% of an analyst's questions get "no records found" when the data is right there
Your text-to-SQL agent has a failure mode that logs nothing, alerts nothing, and returns a...
Source: DEV Community
TutorialsOrdinary
How to Stop an AI Agent That Lies About Its Own Spending
In September 2026, Mandiant described a failure in its AI Risk and Resilience report, drawing on data...
Source: DEV Community
TutorialsOrdinary
What Is intent.md in Claude Code? A Practical Guide with an Example
You ask Claude Code to build a feature. Minutes later, the code looks reasonable—but it solves a...
Source: DEV Community · Claude
TutorialsOrdinary
How I built a 100% client-side privacy toolbox using vanilla JavaScript
Why uploading your files to “free” tools might be costing you more than you think Last month, I...
Source: DEV Community
TutorialsOrdinary
I optimized an API for AI agents instead of humans. Here's what one week of data looked like.
I made Korean government data agent-payable with MCP and x402 — here's what actually...
Source: DEV Community
TutorialsOrdinary
A free MCP server and REST API for AI-rated job listings (no key)
A free MCP server and REST API for AI-rated job listings (no key) If you want an assistant...
Source: DEV Community
TutorialsOrdinary
How Cursor Can Win: Strategy, Defensibility, and Developer Moats
Originally published at sameerbajaj.com. There have been many new entrants in the AI wave over the...
Source: DEV Community · Cursor
TutorialsOrdinary
Two AI code review benchmarks disagree on the winner, and agree on what to measure
The top of the Google results for "best AI code review tools" is a wall of vendor listicles. Most of...
Source: DEV Community
TutorialsOrdinary
Curriculum Truth Ledger
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange I built...
Source: DEV Community
TutorialsOrdinary
Why Does Your AI Coding Agent Start Forgetting What It Was Doing?
Why Does Your AI Coding Agent Start Forgetting What It Was Doing? I've been working with AI coding...
Source: DEV Community
TutorialsOrdinary
We audited 110 AI usage tools. Here is where the numbers go wrong.
A field report on AI usage metering: five recurring bug families across 110 open-source tools, 45+ verified bugs, 23 fixes merged upstream, and one independent reproduction.
Source: DEV Community
TutorialsOrdinary
Google Expands Gemini Notebook With Syncing, Interactive Tools and a New Name
Google is expanding Gemini Notebook, the product previously called NotebookLM, from a source-grounded...
Source: DEV Community · Gemini
TutorialsOrdinary
The override protocol: how Keel lets the operator overrule a refusal — honestly
Refusals are final unless the operator's word lands — and when it does, the override is a stamped, visible record, not an edit to history. The pressure valve, as a protocol.
Source: DEV Community
TutorialsOrdinary
I Built a Virtual Machine Inside the Xbox Sandbox. Then I Let AI Agents Build on Top of It.
XCP turns one-shot code generation into a continuous software lifecycle: create, execute on Xbox,...
Source: DEV Community
TutorialsOrdinary
We ran 2 vs 4 agents six times. Four agents cost 2.1 and did not improve success
A preregistered deterministic task, six valid live runs, hard call and cost caps, and a negative result. More agents were operationally viable but did not improve task success, at 2.115× the cost.
Source: DEV Community
TutorialsOrdinary
AI Is Making Code Cheap. Verification Is Becoming the Expensive Part
Anthropic published a post about their CI infrastructure that I keep coming back to. The headline...
Source: DEV Community · Claude
TutorialsOrdinary
The Leftover Hard Parts
Some time ago, I asked an AI to write a fairly boring piece of code. It did a pretty good job. I...
Source: DEV Community