3 articles
11 min
I let an AI agent break my database on purpose
I have tested Docker Sandboxes and it is genius. Imagine you run Claude Code to debug some issue, and suddenly it asks you for permission to run this: Scary, huh? But what if…
5 min
How I Save Tokens While Developing — You and the Planet Have Reached Their Limit
Do you know the moment when you're working on something, or maybe interacting in some other way with an LLM agent, and suddenly you get the message "You've reached your usage…
2 min
How I Run My Blog Through an MCP Server
Over the past few weeks I built my own MCP server for this blog, blog-mcp, and in the process really understood why people are talking so much about the Model Context Protocol…