Claude Code is a bit like a cat

Claude Code is infuriating. It is helpful for sure, but it is also infuriating. Debugging complex issues with Claude Code gives you a false sense of safety. This is known, and I am used to it. The bit I am having difficulties with is the aftermath. Like cats, coding models always fall back on their feet. The model will find a small caveat it had missed, sure it’s not much, and then make another round of fixes. More likely than not, the result is worse.

Claude Code, more than Codex I find, is particularly good at this “recovering”. Even if, really, it is a major blunder that needs a much deeper fix. It’s like a cat that will break all your lovely cupboard deco, ruin your curtains, and fall back on its feet and cuddle with you after being shouted at. And then of course you have to feed it.

The main constraint cats and AI have in common is they have to be quick. They rely on signals they recognise to quickly make a decision, and act. Understanding the full context is never an option. Falling back on your feet and continuing to be fed becomes the critical skill.

Anyways, it’s obviously not a fair comparison. I eventually got my cat to re-arrange all my deco and replace my curtains. It even re-built a new house, with extension, and 4 bathrooms and no kitchen. While accidentally setting my car on fire.