When a chatbot gets something wrong, it’s not because it made an error. It’s because on that roll of the dice, it happened to string together a group of words that, when read by a human, represents something false. But it was working entirely as designed. It was supposed to make a sentence & it did.

Chatbots — LLMs — do not know facts and are not designed to be able to accurately answer factual questions. They are designed to find and mimic patterns of words, probabilistically. When they’re “right” it’s because correct things are often written down, so those patterns are frequent. That’s all.

A little while ago, my parents' cat Bridget went missing. As the weeks dragged on, they became extremely worried. My dad devised a way to distract himself: he began to paint Bridget's adventures, imagining her travelling through time and popping up in some of art and music's most iconic scenes.