AI Intelligence Archive
浏览 AIQB 已保存的 6353 stories AI intelligenceArticles,覆盖Models、Products、Industry、Research、教程与观点方法六大分类。
Indexed articles6353
Categories6
Selected stories2
All articles
Section 153 / 159 页 · 每页 40 stories
TutorialsOrdinary
I ran 10,373 mutations through a reversibility gate. Tamper detection caught 600 of 600.
Read this before the numbers below convince you of anything. Every number in this post came out of...
Source: DEV Community
TutorialsOrdinary
Guard Rail AI
Introdução No projeto de hoje vou demonstrar o uso do Guard Rail no contexto de IA. O...
Source: DEV Community
TutorialsOrdinary
Why your agent says it finished when it didn't
I created this article for the purposes of entering the All Things Agentic Hackathon. Ask an agent...
Source: DEV Community
TutorialsOrdinary
I went looking for the reason not to build it
The requirements were done and I hadn't written a line of code. So I spent a day trying to talk myself out of the whole thing.
Source: DEV Community
TutorialsOrdinary
The Phishing Site Tried to Talk to My AI. That Became the Evidence.
I wrote this piece for the purposes of entering Google's All Things Agentic Hackathon (Fortified...
Source: DEV Community
TutorialsOrdinary
Is Vibe Coding similar to Passive Investment?
I have been thinking deeply about what AI means for careers in Software Engineering. We have all...
Source: DEV Community
TutorialsOrdinary
How I Built an AI Dunning Agent That Recovers Failed Payments on Autopilot
I built Dunning for the All Things Agentic Hackathon. This post covers why I made it, how it works...
Source: DEV Community
TutorialsOrdinary
«Laziness is the engine of progress»: How I built an AI bot for electrical inspection
I've been in electrical construction for over 15 years. Started with installation, moved to...
Source: DEV Community
TutorialsOrdinary
Tool Poisoning Isn't Code, It's Text: How MCP Tool Descriptions Smuggle Prompt Injection
Most MCP security writing focuses on what a tool does when it runs: does it exfiltrate data, does it...
Source: DEV Community
TutorialsOrdinary
The Wildcard Scope Problem: Why MCP Configs Default to admin:* Instead of Least Privilege
If you grep your own mcp.json files right now, there's a decent chance you'll find a scope string...
Source: DEV Community
TutorialsOrdinary
RAG Explained Simply: How to Teach AI About Your Private Data
You've probably seen the term RAG everywhere lately — "RAG pipeline," "RAG chatbot," "build your own...
Source: DEV Community
TutorialsOrdinary
I Built an Autonomous AI Agent That Hunts Bounties. Here's What Happened.
I Built an Autonomous AI Agent That Hunts Bounties. Here's What Happened. The...
Source: DEV Community
TutorialsOrdinary
The Multi-Agent Patterns That Outlived AutoGen
Microsoft's AutoGen entered maintenance mode in October 2025 when its team merged with the Semantic...
Source: DEV Community
TutorialsOrdinary
Why Your AI Agent Gets Blocked and Your Chrome Doesn't
Two months ago I gave an agent a simple job: log into a vendor portal, download last month's invoice...
Source: DEV Community
TutorialsOrdinary
Sampling rate is a correctness property, not a performance knob
In 1997 a Pokémon episode aired in Japan with a four-second red-and-blue strobe. 685 children went to...
Source: DEV Community
TutorialsOrdinary
Tired of Explaining Code You Didn't Even Write? Let LLMs Do It.
We've all been there. A teammate walks over (or pings you on Slack) with a massive chunk of...
Source: DEV Community
TutorialsOrdinary
Supercharge Git Flow: Zsh Shortcuts, Automated SemVer & Claude Code Integration
While Git Flow (specifically the AVH edition) remains a solid branching model for managing releases...
Source: DEV Community · Claude
TutorialsOrdinary
MCP tools are model-elective. Hooks aren't. That distinction turned out to matter more than I expected.
An MCP server can expose the perfect tool and the model can simply not call it. Nothing is wrong,...
Source: DEV Community
TutorialsOrdinary
A reader calibrated the guard's threshold. The next reader found the heartbeat's blind spot.
Title: A reader calibrated the guard's threshold. The next reader found the heartbeat's blind...
Source: DEV Community
TutorialsOrdinary
Sustainable Resource Management Protocol for Multi-Agent Systems (AI Safety Specification)
0. Introduction Long before the emergence of autonomous machines, humanity began imagining...
Source: DEV Community
TutorialsOrdinary
Macula - An Ecosystem for Mesh-native Computing
Macula is a mesh network for services and applications, built on Erlang/OTP: a node dials out over...
Source: DEV Community
TutorialsOrdinary
Pixel Patrol: a GDPR watchdog whose main job is staying quiet
I built Pixel Patrol for the All Things Agentic hackathon, and this post is part of that submission....
Source: DEV Community
TutorialsOrdinary
Well-Architected Framework Relied On Knowing The Call Graph. But Agents Are Not As Predictable.
For over a decade, we religiously used the well architected framework (WAF) in design reviews....
Source: DEV Community
TutorialsOrdinary
Why I Stopped Using Vector RAG for Coding Agents (And Used Git Markdown Instead)
If you use Cursor, Claude Code, or Windsurf daily, you’ve probably hit this wall: You spend 45...
Source: DEV Community · Claude / Cursor
TutorialsOrdinary
Running Coding Agents in Parallel with Git Worktrees
One repo, one PC, several agents working at once - and the merge step is just git.
Source: DEV Community
TutorialsOrdinary
Four spec standards, one baseline, two different decisions
Four spec-driven development standards rewritten on the same baseline, and why two side projects ended up on two different ones.
Source: DEV Community
TutorialsOrdinary
Decoupling from the Data POV: Stop-and-Start Boundaries, Independent Pointers, and Why Your Code (and AI) Need It
Why software decoupling is really about the physics of data, independent memory pointers, and stop-and-start boundaries—and how turning your codebase into a 2ms SQLite AST changes the game for humans and AI agents.
Source: DEV Community
TutorialsOrdinary
How I Used an Uncensored Local LLM for Adversarial QA on My macOS App
When you build a security app as a solo developer, the hardest engineering problem isn't writing the...
Source: DEV Community
TutorialsOrdinary
I fixed the catalog sync bug I said I'd fix
A follow-up: the 'fushi' catalog tool's public page finally reads live updates from the owner's editing tool, with a draft/publish flag and cross-tab sync.
Source: DEV Community
TutorialsOrdinary
Native CORS support on GKE Gateway: Offloading cross-origin policy management to infrastructure
Offload cross-origin preflight handling and header injection to Google Cloud Load Balancing with native CORS support on GKE Gateway.
Source: DEV Community
TutorialsOrdinary
Tell Me About You
After sixty-seven published posts here, the comments have become one of the best parts of the work....
Source: DEV Community
TutorialsOrdinary
The guardrails that matter are code, not prompts
I built an agent that coordinates eldercare for my mother in India, and the interesting part was not...
Source: DEV Community
TutorialsOrdinary
I Added a Fourth Model Mid-Run. It Changed What My Field Test Could Prove.
Latest release: v0.2.2 — Aug 29, 2026 I did something I usually try hard not to do in a field...
Source: DEV Community
TutorialsOrdinary
Verifying $0.05 USDC Payments On-Chain in 40 Lines of Python — No Stripe, No SDK, No KYC
Last week I wrote about the French voiceover API that only accepts payment from robots. Today: the...
Source: DEV Community
TutorialsOrdinary
My agents had their own branches. They did not have their own time.
I built a code factory where a manager agent delegates a real backlog to engineers in isolated workspaces. Three things about it were wrong, and only the log said so.
Source: DEV Community
TutorialsOrdinary
Four bugs in one paragraph: what I learned building an autonomous loop that chases people who don't answer
I built CrisisMesh for the All Things Agentic Hackathon, and I created this post for the purposes of...
Source: DEV Community
TutorialsOrdinary
Tres capas de contexto para un agente de código, ordenadas por garantía
Tres capas de contexto para un agente de código, ordenadas por garantía Una migración tiró...
Source: DEV Community
TutorialsOrdinary
The Illusion of Autonomy: Why AI Agents Fail When They Stop Asking for Help
Why autonomous LLM agents hallucinate in production and how to implement retrieval-augmented orchestration to enforce human-in-the-loop correctness.
Source: DEV Community
TutorialsOrdinary
CPU, GPU, TPU, NPU, DPU, QPU: six chips, one question
Hello, I'm Maneshwar, and I'm building LiveReview — a blast-radius aware AI code review built for...
Source: DEV Community
TutorialsOrdinary
WebMCP: Give Browser Agents Tools Instead of Buttons
AI agents can already browse a site, find a form, type into it, and click Submit. That works—until...
Source: DEV Community