[..] most critical bugs actually result from misunderstanding the problem rather that implementation errors.

While these (MCP Servers) were heavily promoted a couple of months ago, these bloat the context window of the agents, resulting in lower quality output. There are many skills and/or CLI tools that can replace tasks for an MCP server.

Supervised software engineering agents are increasingly capable of identifying necessary updates and making larger changes to a codebase. At the same time, we’re seeing growing complacency with AI-generated code, and developers becoming reluctant to review large AI-made change sets. A common justification for this is that human-oriented code quality matters less since AI can handle future modifications; however, AI coding assistants also perform better with well-factored codebases, making AI-friendly code design crucial for maintainability.

“[..]. Working on a project of your own is as different from ordinary work as skating is from working. It’s more fun, but also much more productive.”