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.

As a guitarist, I always thought more could be done with floor based controllers. In particular, the expression pedal. Expression pedal examples include effects such as the wah-wah or simple parameter controls.
Some samples of apps by FlatCoder Ltd. circa 2014/15.
Several clients of FlatCoder Ltd, past and present, have required bespoke Customer Relationship Management solutions (CRM) or Enterprise Resource Planning (ERP).
I was approached by a client recently who had developed their own bespoke Customer Relationship Management software (CRM). It wasn’t really a planned system – more a necessity as the business grew.