Guide: learn to talk with AI

A modern guide to better results — model-independent advice and a simple method that works regardless of which AI service you use.

Into the engine room: bagging, boosting, attention and why it all happened at once

Part two of the AI alphabet series. How ML and DL actually make decisions, what attention does when an LLM reads a sentence, and the three things that fell into place at the same time.

The AI alphabet: from ANI to RAG, explained without the jargon

ML, DL, NLP, RPA, LLM. The acronym soup that loses most people within a sentence. Here's the untangled version, with a movie example and an inspection report along the way.

Directing AI instead of just prompting it

A new article from MIT Sloan Management Review separates having a conversation with AI from directing it. It turns out to be the next step in exactly the journey we've followed through this series – from words, to maps, to context.

Context – and is "context engineering" the new black?

A perfect map won't help you if you don't know where you're standing on it. The fourth and final part of the series is about context, why "context engineering" became a buzzword, and why the best route there often starts with the right question.

Ontology – the word that sounds harder than it needs to be

Ontology is about which things exist, what they're called, and how they relate to each other. An ancient philosophical concept that can become the invisible blueprint behind AI systems that need to understand a business domain.

What is semantics – and why was the philosopher arguing with his quill pen about it?

Semantics is the study of meaning – how words and sentences convey what we actually mean. It sounds academic, but it has become highly practical knowledge in a world where we increasingly talk to AI.

The Future Belongs to Philosophers (and Others Who Know Their Grammar)

There's been a lot of talk about AI taking our jobs. Programmers, lawyers, copywriters – everyone's gotten their own little scare. But it's time to give credit to a profession that's long wandered around the coffee break table a bit forgotten: the people who can actually express themselves. Because here's the small irony of the AI revolution: the smarter the machines get, the more it matters that we get better at talking to them. We're heading toward an increasingly language-driven interface to the world – where the command line is replaced by conversation (think Siri and Alexa) – and where the difference between a mediocre and a brilliant result is no longer about which code you can write, but about which words you choose.