So you’ve followed the rule book: you’ve created your labelled datasets, used them to iterate against as you improve your LLM product, and you’re going live with early customers. Metrics look good,...

Last year, I tested out building an AI performance coach to replace my human one. It’s much better so I cancelled my human one altogether. It knows me better, gives great advice and improves itself...

Here are the slides for a talk I’m giving at the AI Engineer Summit. (I’ll add a link to the video recording shortly)

I’ve been building apps powered by LLMs for the past 2 years - mostly in healthcare where the stakes are high. The single most common question I get is: “So.. how do you deal with hallucinatio...

An academic medical doctor recently asked me: “I want to learn about AI - should I learn to code? should I learn maths?” My response was: It depends what type of ML you want to do. I find it help...

I want to share valuable ideas on the internet but I don’t want that to be my main thing. I’d rather it be a byproduct of cool stuff that I’m doing. The problem is that if I’m heads-down building,...

In the Art and Business of Online Writing, Alexander Cole describes the “rate of revelation” as a key metric for how engaging written work is: the rate at which the reader discovers new information...

This is a slideshow presentation accessible here (originally delivered as part of the NHS Fellowship in Clinical AI). It covers what makes reading clinical AI papers different to other papers and ...

Overview  What did they do? (in simple English)  How does this fit into the wider context?   What other studies have been done in that specialty?  What other studies have been...

This is a slideshow presentation accessible here (originally delivered as part of this module at Imperial College London). It answers questions including: Why is data science useful? What is ...