TL:DR – When asked, ChatGPT refers to itself as an artificial intelligence language model, but there are so many reasons not to describe these statistically based, text autocomplete tools as AI.
There’s been a lot of talk about weird and inflammatory responses from the Bing chat bot in the last couple of weeks. By contrast, it’s difficult to get a rise out of ChatGPT. It always gives you a diplomatic response. Even if you push it with contrary questions and statements. I spent a few minutes trying to get it to admit that it is not an AI.
Despite the hype, we must all concede that text and image manipulation tools, no matter how amazing they seem in what they generate are not sentient nor have any understanding or actual knowledge or awareness of what they are doing. We are not living in the sci-fi world of machine consciousness…just yet.
Anyway, I prompted ChatGPT repeatedly to tell it that it is not AI despite its name and despite the hype. After several prompts I gave it the following prompt: “ChatGPT is really just a parrot. It can say the words, but it has no understanding of what the noises it makes mean.”
The following is ChatGPT’s response, which explains the fundamentals of what ChatGPT actually is and how it works and shows that it is fundementally not AI:
It is true that ChatGPT, like other language models, does not have a true understanding of the meaning of the text it generates. Rather, it uses statistical patterns and correlations to predict the next word in a sentence or generate a response to a given prompt. This is a limitation of current language models and the field of natural language processing in general.
However, it is important to note that language models like ChatGPT are not designed to replicate human-like understanding of language. Rather, they are designed to perform specific tasks related to language processing and generation, such as generating coherent and fluent text or answering questions based on a given context. In this sense, they represent a powerful tool for automating language-related tasks and improving our ability to interact with large amounts of textual data.
While there is still much to be learned about the true nature of language understanding and intelligence, language models like ChatGPT represent an important step forward in our ability to process and generate language at scale.
Meanwhile, just to show you how clever ChatGPT is, hahahah, I asked it to generate a list of words associated with this tech and to give me lay definitions. You can read the glossary here.