Chatting with ChatGPT

And learning about the history of chatbots in the process...
24 January 2023


A picture of someone talking, drawn on a blackboard


To demonstrate its potential, and to find out a bit more about how chatbots got to the level they are at today, I thought I’d give ChatGPT a test drive before running its responses through some free online text to speech software to give it a voice…

James - ChatGPT, what was the first chatbot?

ChatGPT - The first chatbot, known as ELIZA, was created in the 1960s by Joseph Weizenbaum at MIT. ELIZA simulated a Rogerian psychotherapist and used pattern matching and substitution to respond to user inputs. It was designed to demonstrate the superficiality of communication between humans and computers.

James - what do you mean, "the superficiality of communication between humans and computers?"

ChatGPT - The idea behind ELIZA was to demonstrate that a computer program could simulate human conversation in a way that was indistinguishable from a real human, despite the program having no understanding of the content of the conversation. The program used simple pattern-matching techniques to respond to users' inputs, which made it appear to be engaging in a meaningful conversation. However, in reality, the program was only able to respond in a superficial way, without any real understanding of the meaning behind the words being used. This demonstrated the limitations of trying to replicate human communication with a computer program, and highlighted the need for more sophisticated techniques to be developed in order to achieve true human-like communication with computers.

James - So are you saying that a modern chatbot, like ChatGPT, does have a real understanding of the meaning of the words used in this conversation?

ChatGPT - As a modern language model, ChatGPT is capable of understanding the meaning of words and phrases, and can generate responses that are contextually appropriate. However, it is important to note that while ChatGPT can understand and respond to a wide range of inputs, it is still a machine and it does not possess the same level of understanding or consciousness as a human. It can understand the surface meaning of the words, but it does not have emotions, beliefs, or personal experiences that influence its understanding of the conversation. It is also limited by the scope of its training data and the information it was given during training. It can make assumptions and predictions based on patterns it has seen during training, but it may not always understand the nuances of a conversation or the true intentions behind a question.

James - Ok. I appreciate the honesty. What was the next development in chatbots after ELIZA?

ChatGPT - After ELIZA, a number of other early chatbots were created, such as PARRY and Jabberwacky. These chatbots improved upon ELIZA by incorporating more advanced natural language processing techniques and attempting to simulate more human-like conversation.

James - And then?

ChatGPT - In the late 1990s and early 2000s, chatbots began to be used more widely in commercial applications, such as customer service and e-commerce. These chatbots used rule-based systems and decision trees to respond to user inputs and provide information to users.
In recent years, with the advance of machine learning and deep learning techniques, chatbots have become more advanced and sophisticated. These chatbots, like ChatGPT, use neural networks to understand and generate text, and can handle more complex and open-ended conversations.

James - Well, I can see that… But how can I trust that anything you've said to this point is true?

ChatGPT - I would advise you to cross-reference any information provided by me with other reliable sources to ensure the information's accuracy and validity. In addition, while I can provide answers to factual questions based on the information I was trained on, I am not able to provide personal opinions or make factual claims without evidence.

James - Interesting. So if I asked you what your favourite colour was what would you say?

ChatGPT - As a language model, I do not have personal preferences or feelings, and therefore, I do not have a favourite color. I am a machine that processes the text based on the patterns it has learned from the data it was trained on. I can generate text that might sound as if it's expressing a preference, but it is not based on any personal experience or preference. I can only provide information based on the patterns and information I have seen in the data during my training.


Add a comment