How generative AI really works

A chatbot is a large language model: a program trained on a huge amount of text from books, websites and conversations. From that text it learned which words tend to follow which.

When you ask it something, it writes its answer one small piece at a time, each time choosing a likely next word. It is very good at sounding fluent. But likely is not the same as true: it has no built-in way of checking facts.

That is why a chatbot can invent a book that does not exist, a quote nobody said, or a wrong date, in perfect, confident sentences. This is often called a hallucination.

Its knowledge also stops at the date its training text was collected, and it reflects whatever that text contained, including mistakes and unfair ideas. Use it as a starting point, never as the final word.