E aí, gurizada! De uns tempos pra cá, tenho percebido uma mudança significativa na forma como a gente interage com a Inteligência Artificial. Não é mais só uma ferramenta que responde perguntas ou gera imagens; a parada tá ficando séria, com a IA assumindo um papel mais ativo, quase como um colega de trabalho. Foi pensando nisso que gravei um vídeo recentemente, e a repercussão me fez pensar: "Car
Comments
For years I thought my only options were dual booting or using a clunky virtual machine. Dual boot meant constant reboots, and VirtualBox ate my RAM. Then I discovered Windows Subsystem for Linux 2, and honestly it changed how I work. Now I run a complete Ubuntu desktop right next to my Windows applications. I can code in a native Linux environment, test web servers, and even fire up Linux-only GU
A step-by-step guide for beginners who want a gaming PC and a real enterprise Linux environment on the same machine — with every decision explained in plain English. What Is Dual-Booting and Why Rocky Linux? UEFI, BIOS, and Secure Boot Partitions, File Systems, and GPT The GRUB Bootloader Before You Begin — Checklist Phase 1 — Shrink Your Windows Partition Phase 2 — Download & Flash Rocky Linux Ph
Claude + Mobile via MCP: Giving the Model Hands on a Real Phone I plugged in a Pixel two months ago, ran one command in Claude Desktop, and watched it open Maps and start navigation to my home address from a single sentence prompt. It was the first time I'd ever seen a language model physically operate a phone. Latency was about two seconds per action; the part that surprised me was the third st
AI-Native Mobile Testing: What It Actually Means in 2026 The phrase "AI-native" has been thrown around in the testing space since 2019. Almost every tool calling itself that just bolts a language model on top of Appium and ships the same brittle XPath selectors with a new label. That's not AI-native testing. That's Appium with a chatbot. This post is about what AI-native actually has to mean to
The Missing Control Plane for Local AI Agents I sat with my Pixel for 20 minutes trying to get Claude Desktop to dictate a Slack message via accessibility. It was miserable. The model was capable. The transport wasn't. That gap — between an AI that can reason and an AI that can actually do — is what I've been working on with Drengr. This post is the version of the argument I'd give to anyone bui