When to Train an AI Model and When to Write Code
There's a rush to use AI for almost every problem at the moment. That enthusiasm can make it easy to reach for a model before asking whether a straightforward rule would solve the problem more reliabl

There's a rush to use AI for almost every problem at the moment. That enthusiasm can make it easy to reach for a model before asking whether a straightforward rule would solve the problem more reliabl

Spend enough time following Python tooling and AI infrastructure, and you start noticing the same implementation detail - "written in Rust". The validator is Rust. The tokenizer is Rust. The DataFrame

We've become very comfortable putting instructions for AI into Markdown. It makes instructions easy to write. It does much less to help us establish whether those instructions are complete, whether th

Usually with An LLM integration the application might create a provider client, assemble a prompt, send a request and deserialise the response. The first feature works, the code is easy to follow and

Circuit breakers in .NET are good at recognising technical failure. They can stop calls when a service begins returning HTTP 500 responses, timing out or refusing connections. This works because conve

Most .NET developers recognise an N+1 database query when they see one. AI features can recreate the same failure at a more expensive boundary. An application loads 300 support tickets, documents or p
