CT No.242: What's your vector, Victor?
How to understand tokens and vector embeddings, for word people.

Deborah Carver is the publisher of The Content Technologist. She is an independent consultant on all things digital publishing, specializing in large content-driven websites.
How to understand tokens and vector embeddings, for word people.
Even in the face of "black box" algorithms, the history of artificial intelligence—natural language processing, more specifically—has left plenty of clues.
Even in the face of "black box" algorithms, the history of artificial intelligence—natural language processing, more specifically—has left plenty of clues. While we can't understand the full equation, we can see how building blocks create common patterns in how current algorithms process language.
Infrastructure, no matter how solid or planned or continuously improved, gets messy. Observing humanity in July feels like the ultimate UX research experiment.
July is prime chart-making season. July 2025 is one more chartmaking season that will not be powered by artificial intelligence, and here's why.
To put it another way: optimizing with GEO reverse engineering tactics is like entering a house through a small attic window. GEO ignores that the research frameworks literally embedded in the outputs of the model are the keys to the front door.
And other insights for developing content in the new era of AI-powered search
A holiday gift guide for the content professionals in your life
Query fan-out is a new term for what's long been a bedrock of keyword-based language processing: the nouns are central to understanding the user's intent.
The words we publish and hold up for peer review remain the best representation of our brains at work in the digital world. A published paper is the best way to look closely at the foundational assumptions of LLMs. And those begin with pop culture.