AI Development

I Made It Write the Rule. Three Minutes Later, Claude Code Broke It.

I spent about thirty hours with Claude Code, putting a small home-made app onto a home server. The model behind it is Claude Sonnet 5. Below, “Claude Code” means the tool; “Sonnet 5” means the habits in its output. For those thirty hours I checked every line it produced. Here are the patterns that kept coming back. This is about technical mistakes, not about how smart it is. This is a record of Sonnet 5. I haven’t used Opus or Fable, so I can’t speak to those. ...

From Babysitting Claude to Trusting It — Verification Loops, Multi-Clauding, and Background Loops

Source Post: X (formerly Twitter) Content: A conference talk (in English) by the Claude Code engineering team, roughly 37 minutes long. Transcription: Auto-generated with faster-whisper (small model, CPU, int8). This article is a summary written from that transcript, not a verbatim translation. If you use Claude Code for a while, it’s easy to end up in a routine where a human still has to watch everything Claude writes and correct it when it’s wrong. This talk lays out three techniques, built on top of each other, for reducing that supervision: verification loops, multi-clauding, and background loops. ...