ChatGPT was created using a state-of-the-art machine learning technique called transformers, which allows the model to process and understand large amounts of text data. The model was trained on a dataset of billions of words, which includes a wide variety of texts such as books, articles, and websites. The training process involved feeding this dataset into the model and using machine learning algorithms to adjust the model's parameters. This process allows the model to learn about language and to generate human-like text when given a prompt.