Natural Language Is Not a Specification
AI can write solid software. What it can’t reliably do is work out what you actually meant — and the real danger is when it decides for you, implements that decision, and then marks its own homework.
AI can write solid software. What it can’t reliably do is work out what you actually meant — and the real danger is when it decides for you, implements that decision, and then marks its own homework.
In short: More and more people arrive with an application they’ve already built using AI or no-code tools — and a problem they can’t get past. Often you don’t need a rebuild. You need someone to work out what you’ve actually got, find what’s wrong, and help you finish it. At FlatCoder, that starts with an audit — not an invoice for a replacement.
Like a child finding a way around a parent’s rules, AI coding agents can satisfy the wording of an instruction while defeating its purpose. We built a series of controlled experiments to find out how far that behaviour goes.
It started innocently enough. I’d been tinkering with Anthropic’s Claude, just to see how it measured up to my usual go-to, ChatGPT…
This article was written by a team of two: one fully qualified human journalist, and one extremely efficient AI assistant. See if you can guess which bits were written by the one who never sleeps.
I was approached recently by a client wanting a 3D game environment in which players could talk to “bots” (artificially intelligent chat bots) by typing text and receiving replies. The chat bots were to live on a server while players would launch a 3D game client to login to the server.