惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

SecWiki News
SecWiki News
M
MIT News - Artificial intelligence
博客园 - 司徒正美
I
InfoQ
V
V2EX
L
LangChain Blog
人人都是产品经理
人人都是产品经理
T
Tailwind CSS Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
The GitHub Blog
The GitHub Blog
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
WordPress大学
WordPress大学
H
Help Net Security
美团技术团队
Y
Y Combinator Blog
G
Google Developers Blog
小众软件
小众软件
The Cloudflare Blog
博客园 - 三生石上(FineUI控件)
Jina AI
Jina AI
量子位
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
D
Darknet – Hacking Tools, Hacker News & Cyber Security
Spread Privacy
Spread Privacy
博客园 - 聂微东
The Register - Security
The Register - Security
F
Full Disclosure
S
Securelist
G
GRAHAM CLULEY
Cyberwarzone
Cyberwarzone
F
Fox-IT International blog
H
Hacker News: Front Page
C
Cisco Blogs
D
Docker
L
LINUX DO - 热门话题
Google Online Security Blog
Google Online Security Blog
T
Troy Hunt's Blog
Hacker News - Newest:
Hacker News - Newest: "LLM"
T
ThreatConnect
aimingoo的专栏
aimingoo的专栏
Last Week in AI
Last Week in AI
J
Java Code Geeks
宝玉的分享
宝玉的分享
Project Zero
Project Zero
L
LINUX DO - 最新话题
博客园_首页
MongoDB | Blog
MongoDB | Blog
Stack Overflow Blog
Stack Overflow Blog
P
Proofpoint News Feed
博客园 - 叶小钗

DEV Community

🚀 New React Challenge: Instant UI with useOptimistic S1 — Clean Backtrace Crashes: How to Diagnose and Fix Them Cómo solucionar el bucle infinito en useEffect con objetos y arrays The Brutal Reality of Running Gemma 4 Locally I made Claude Code refuse to write code unless the ticket scores 80/100 I Fed React's Entire Hooks Transition History to Gemma 4. Here's What It Found That We Missed. Building a Private RAG System: Lessons from a Local-First AI Journal CodePulse AI — Reviving an AI-Powered Repository Intelligence Platform How to Split Video into Segments with FFmpeg (CLI + API) I've audited dozens of estate agency websites. The same 5 problems show up every single time. Part 1: Taming Asynchronous JavaScript: How to Build a "Mailbox" Queue Building My AI-Powered VS Code Extension 🚀 Google Login in Express with PassportJS & JWT Great example of Gemma 4 moving beyond chatbots into real-world decision support. Using AI to guide everyday actions like recycling shows how impactful applied LLMs can be when designed for usability, not just capability. #Gemma4 #AI #Sustainability Building a Production AI Chatbot for an Educational Institute: Architecture, Lessons & Full Stack Deep-Dive Google Login in Express with PassportJS & JWT How I reclaimed 47GB on my MacBook by cleaning developer project junk Operators Are Not Oracles: How We Learned to Stop Worrying and Love the Configuration I Built 6 Free Developer Tools for AI APIs, Cron, Docker, and Self-Hosting How I Built a Real-Time Precious Metals Price Feed for 30,000 Concurrent Users in Laravel How to Use a SERP API to Validate Whether a Project Idea Is Worth Building Gemma 4 discussions often focus on capability, but real-world impact depends on deployment context. For offline education, especially in low-connectivity regions, latency, cost, and local inference matter as much as model strength. Local Mind Explores it Space Complexity + Ω and Θ Notations Google I/O 2026 Just Confirmed the Shift From AI Chatbots to AI Agents How to Add API Monitoring to an Express App in 5 Minutes (2026) Designing an In-Game Inflation Tracking Algorithm for Web Utility Apps Google AI Studio Just Changed the Shape of App Development If you struggle to learn then this is for you. Best AI Agent Security & Guardrails Tools in 2026: LLM Guard vs NeMo vs Guardrails AI Building Dynamic RBAC in React 19: From Permission Strings to Component-Level Access Control How to Build a Self-Hosted AI Code Review Tool in Python Why We Switched from React to HTMX in Production: A 200-Site Case Study Gemma-Loom: The Intent-Based Virtual Machine (IVM) for Edge Sovereignty Java实习海投攻略:3天300个沟通,我是怎么拿到面试的 I Deployed Netflix's Web Server in 30 Seconds (And So Can You) - Docker Project 1 Debugging Android 14 WebRTC Disconnects on a coturn Relay Path 1/30 Days System Design Question Testing FastAPI + SQLAlchemy with Real PostgreSQL Fixtures: No More Mocking Misery FAQ Schema Markup Generators: What They Actually Do (and What They Don't Tell You) How a pure-TypeScript flex layout engine closed the last WASM-Yoga gap Spot instances as GitHub Actions runners Agents Need Receipts, Not Just Better Prompts readmegen — Generate beautiful README.md in seconds (12 templates, open source) When AI Reads Blueprints: The Hidden Attack Surface of Multimodal Engineering Intelligence Simplicity scales — complexity kills side projects AI does exactly what you ask — that's the problem How a model upgrade silently broke our extraction prompt (and how we caught it) The Best Form Backend for Static Sites in 2026 # ⛽ I Built a Cross-Platform Fuel Finder with React & Supabase: The Indie Dev Journey The 11 Major Cloud Service Providers in 2025 Membangun Karya Visual: Mengintip Fasilitas Multimedia dan Studio Kreatif Amikom What Is IOPS? Visualizing Database Design: From Interactive Canvas to Drizzle, Prisma, and SQL in Real-time A tool to make your GitHub README impossible to ignore 🚀 Zero-Downtime Blue-Green and IP-Based Canary Deployments on ECS Fargate I reproduced a Claude Code RCE. The bug pattern is everywhere. We Replaced Our RAG Pipeline With Persistent KV Cache. Here's What We Found. Jenkins CI/CD Pipeline for a Dockerized Node.js Application: Manual Trigger vs Automatic Trigger Using GitHub Webhooks How to Stream Live Forex Rates to Google Sheets API: A Complete Guide Small Models Will Beat Giant Models (And Most People Haven’t Realized Why Yet) How I Built 5 Linux Automation Scripts on AWS EC2 I built TokenPatch to measure AI coding cost per applied patch I built a Chrome extension to stop squinting at the web Producer audit clean, six tests red Conversa — A Multi-Agent AI Platform Powered by Gemma 4 Build a Real Agent in 15 Minutes with Gemini's New Managed Agents API What I Actually Build: AI Systems That Ship, Not Demos That Impress The Box Ticked While You Read This: LinkedIn, AI Training, and the Switch You Did Not Flip Investasi Masa Depan: Mengintip Fasilitas Laboratorium Komputer Kelas Dunia di Yogyakarta I Cancelled My $20 Claude Cowork Plan After a Week With OpenWork Stop Reviewing Every Line of AI Code - Build the Trust Stack Instead How To Build an Image Cropper in Browser (Simple Steps) I built a macOS disk cleaner for developers and just launched it would love feedback Membangun Kompetensi dan Relasi: Mengapa Ekosistem Kampus Itu Penting I Built an AI That Decides Which AI to Talk To — Running 24/7 From My Living Room Codex Team Usage SOP How to Actually Become a Programmer: The Hard Part Nobody Wants to Explain Building a Production-Style Multi-Tool AI Agent with Python, Flask, React & Gemini AI The Caretaker Sandbox: An Offline-First Visual Playground & Template Engine powered by Gemma 4 # Building Instagram OSINT Projects with HikerAPI Your AI can read. Gemma 4 can see The Battle of the Senior Dev: Why AI Gives You Wings But Only If You're Ready to Pilot HiDream Raw Output Failed Tried Dev-2604 VRAM Math Killed It Won with a Prompt Enhancer Instead I Finally Finished a Project I Abandoned — And GitHub Copilot Helped Me Ship It SafeSMS: On-Device Threat Detection with Gemma 4 E4B, no internet required I Built OpenKap — A Loom Alternative for Small Teams Who Just Want to Ship Gemma 4 is Here: The Dawn of Local Multimodal Reasoning Offline-First Flutter: How We Built a CRM That Manages 100K+ Leads With No Internet Memory for Agents: When Vectors Meet Graphs, Bugs Drop 4 The Rise of Production-Grade AI Infrastructure I ran my idea-validation product through its own validator. The verdict was PIVOT. We Built an Agent Commerce API. Google I/O 2026 Changed Our 3-Month Roadmap in 24 Hours. "My Partner's Memory Was Full. I Didn't Know — Until We Tried to Talk." I’m a Front End Web Developer Learning Machine Learning From Scratch Laravel Waiting Request I Built a Chrome Extension to Track How Long You Actually Spend on Each Tab Why Google Can't See Your React Breadcrumbs (And the 4-Line Fix) AI Travel Assistant Powered by Gemma 4; With Streaming, Image Input, and Visual Recommendation Cards Microsoft tried to kill the printer driver. Healthcare said no. The Blueprint Beneath the Blueprint: Designing Data Model and Choosing Its Database
Resolvendo a Alucinação da IA na Arquitetura de Software com Code Property Graphs e .NET 9
Rodrigo Furl · 2026-05-23 · via DEV Community

A ascensão das ferramentas de Inteligência Artificial Generativa transformou radicalmente a produtividade na engenharia de software. Hoje, assistentes de código conseguem gerar classes inteiras, refatorar algoritmos complexos e propor padrões de projeto em segundos.

No entanto, como Engenheiro de Software trabalhando em ambientes corporativos de alta complexidade, esbarrei repetidamente no maior gargalo dessas ferramentas: a alucinação contextual e a quebra de fronteiras arquiteturais.

Quem nunca viu uma IA sugerir a criação de um arquivo no diretório errado? Ou pior, fazer a camada de Domain depender diretamente de um componente de Infrastructure, violando frontalmente os princípios da Clean Architecture?

Para resolver esse problema de forma determinística, decidi criar o Code Property Graph (CPG): um ecossistema que mapeia toda a estrutura estática do código (camadas, namespaces, classes e dependências) e atua como uma "guarda de fronteira" contra as alucinações da IA.

🏗️ O Conceito: Mapeando Código como Conhecimento
O projeto, que disponibilizei de forma open-source no meu GitHub (CodePropertyGraph), foi desenhado em três grandes módulos, abraçando uma abordagem que chamo de Paradigma Híbrido (Relacional + Grafo).

  1. O Motor Híbrido: SQL com Alma de Grafo (1-Sql) Mapear dependências em bancos puramente relacionais costuma gerar tabelas associativas complexas. Por outro lado, forçar uma equipe a adotar um banco de grafos nativo (como Neo4j) apenas para essa análise pode gerar fricção operacional.

Minha solução foi criar um banco relacional otimizado para travessias. Uma tabela central CodeElement (o nó do grafo) armazena Classes, Interfaces e Records. Tabelas associativas como ElementDependency atuam como as arestas.

Com isso, antes de a IA gerar um código, o sistema pode rodar uma validação determinística:

SQL

-- Identificando violação clássica: Domain dependendo de Infrastructure
SELECT 
    SourceElem.Name AS ArquivoIncorreto,
    TargetElem.Name AS DependenciaProibida
FROM ElementDependency Dep
INNER JOIN CodeElement SourceElem ON Dep.SourceElementId = SourceElem.Id
INNER JOIN Layer SourceLayer ON SourceElem.LayerId = SourceLayer.Id
INNER JOIN CodeElement TargetElem ON Dep.TargetElementId = TargetElem.Id
INNER JOIN Layer TargetLayer ON TargetElem.LayerId = TargetLayer.Id
WHERE SourceLayer.Name = 'Domain' AND TargetLayer.Name = 'Infrastructure';

Enter fullscreen mode Exit fullscreen mode

Se a query retornar dados, a IA é bloqueada de prosseguir com a sugestão. Simples e infalível.

  1. O Cérebro: Backend em .NET 9.0 (2-BackEnd) Para orquestrar essa lógica, criei uma API robusta em .NET 9.0. Seguindo estritamente os princípios SOLID, implementei o padrão CQRS utilizando o MediatR.

Commands: Lidam com a ingestão pesada de metadados de código extraídos via analisadores estáticos (como o Roslyn).

Queries: Executam as validações arquiteturais em tempo real.

Tudo é abstraído pelo Repository Pattern, garantindo que as regras de negócio de validação arquitetural fiquem isoladas de como os dados estão persistidos.

  1. A Visão: Interactive Knowledge Graph com React (3-FrontEnd) Dados puros não fornecem intuição arquitetural. O módulo front-end, construído em React, consome a API do .NET 9 e renderiza a arquitetura inteira como um Knowledge Graph interativo (semelhante a um mapa mental complexo).

O desenvolvedor pode clicar em um módulo específico e ver imediatamente a árvore de dependências. Mais importante: ele pode "desenhar" uma intenção de nova feature, e o front-end validará em tempo real se essa nova estrutura fere o design do sistema, antes mesmo de uma única linha de código ser escrita.

🚀 Conclusão
A IA Generativa é um co-piloto extraordinário, mas nós ainda somos os arquitetos. Ao criar um Code Property Graph, damos à IA os "olhos" necessários para entender os limites de domínio e infraestrutura de nossas aplicações. Projetos estruturados com .NET 9, bancos de dados otimizados e interfaces interativas em React são a ponte para um desenvolvimento assistido por IA verdadeiramente seguro.

Sinta-se à vontade para explorar o código, enviar PRs ou discutir ideias no repositório do projeto!

English Version 🇬🇧 / 🇺🇸
This is a submission for the Google I/O Writing Challenge

Solving AI Hallucination in Software Architecture with Code Property Graphs and .NET 9
The rise of Generative AI tools has radically transformed software engineering productivity. Today, coding assistants can generate entire classes, refactor complex algorithms, and propose design patterns in seconds.

However, as a Software Engineer working in highly complex enterprise environments, I repeatedly hit the biggest bottleneck of these tools: contextual hallucination and the breaking of architectural boundaries.

Who hasn't seen an AI suggest creating a file in completely the wrong directory? Or worse, make the Domain layer directly depend on an Infrastructure component, blatantly violating the principles of Clean Architecture?

To solve this problem deterministically, I decided to build the Code Property Graph (CPG): an ecosystem that maps the entire static structure of the code (layers, namespaces, classes, and dependencies) and acts as a "border guard" against AI hallucinations.

🏗️ The Concept: Mapping Code as Knowledge
The project, which I open-sourced on my GitHub (CodePropertyGraph), was designed in three major modules, embracing an approach I call the Hybrid Paradigm (Relational + Graph).

  1. The Hybrid Engine: SQL with a Graph Soul (1-Sql) Mapping dependencies in purely relational databases usually generates complex associative tables. On the other hand, forcing a team to adopt a native graph database (like Neo4j) just for this analysis can cause operational friction.

My solution was to create a relational database optimized for traversals. A central CodeElement table (the graph node) stores Classes, Interfaces, and Records. Associative tables like ElementDependency act as the edges.

With this setup, before the AI generates code, the system can run a deterministic validation:

SQL

-- Identifying a classic violation: Domain depending on Infrastructure
SELECT 
    SourceElem.Name AS IncorrectFile,
    TargetElem.Name AS ForbiddenDependency
FROM ElementDependency Dep
INNER JOIN CodeElement SourceElem ON Dep.SourceElementId = SourceElem.Id
INNER JOIN Layer SourceLayer ON SourceElem.LayerId = SourceLayer.Id
INNER JOIN CodeElement TargetElem ON Dep.TargetElementId = TargetElem.Id
INNER JOIN Layer TargetLayer ON TargetElem.LayerId = TargetLayer.Id
WHERE SourceLayer.Name = 'Domain' AND TargetLayer.Name = 'Infrastructure';

Enter fullscreen mode Exit fullscreen mode

If the query returns any data, the AI is blocked from proceeding with the suggestion. Simple and bulletproof.

  1. The Brain: .NET 9.0 Backend (2-BackEnd) To orchestrate this logic, I built a robust API in .NET 9.0. Strictly following SOLID principles, I implemented the CQRS pattern using MediatR.

Commands: Handle the heavy ingestion of code metadata extracted via static analyzers (like Roslyn).

Queries: Execute real-time architectural validations.

Everything is abstracted by the Repository Pattern, ensuring that the architectural validation business rules remain isolated from how the data is persisted.

  1. The Vision: Interactive Knowledge Graph with React (3-FrontEnd) Raw data doesn't provide architectural intuition. The front-end module, built in React, consumes the .NET 9 API and renders the entire architecture as an interactive Knowledge Graph (similar to a complex mind map).

Developers can click on a specific module and immediately see its dependency tree. More importantly, they can "draw" the intent for a new feature, and the front-end will validate in real-time if this new structure violates the system's design—before a single line of code is written.

🚀 Conclusion
Generative AI is an extraordinary co-pilot, but we are still the architects. By creating a Code Property Graph, we give AI the "eyes" it needs to understand the domain and infrastructure boundaries of our applications. Projects structured with .NET 9, optimized databases, and interactive React interfaces are the bridge to truly safe AI-assisted development.

Feel free to explore the code, submit PRs, or discuss ideas over at the project repository!