Why We Accept Bad Code From Humans But Reject Good Code From AI
I've been noticing something about how developers talk about AI coding agents. They review agent-generated code with a magnifying glass. They point at a variable name they don't like, a…
Vibecoding vs Agentic Engineering: One Ships, the Other Prays
I've been preparing a talk about AI-assisted development and spent a lot of time reading what developers are saying online, in meetups, in conference hallways. A pattern keeps showing up:…
How To Sandbox Your AI Agent Using Docker
Docker just released a really exciting update to Docker Sandboxes, a feature that allows running AI agents, like Claude Code, in isolated environments. This change was released with the Docker…
Claude Code + Ollama: Stress Testing Opus 4.5 vs GLM 4.7
Ollama just made it possible for you to use their models inside of Claude Code. To test Claude Code capabilities and compare top open models with closed ones, I compared…
How AI Wiped Out 80% of Tailwind’s Revenue
Tailwind CSS, you probably know what it is. A utility-first CSS framework that has taken the web development world by storm. It's the default of many frameworks and tools, like…
