Extract
So, nothing you say is original?
Chatboy: That is correct.
Summary
Okay, maybe that is a bit of an exaggeration. We asked her in a British kind of euphemistic way. Here is the complete, unedited conversation.
Actual Conversation
User: how are you?
ChatGPT: As an AI language model, I don’t have feelings, but I’m here to help you with any questions or information you need. How can I assist you today?
User: What do you feel like doing today?
ChatGPT: Since I don’t have personal desires or emotions, my purpose is to assist and provide information to the best of my abilities. Is there something specific you’d like assistance with or a topic you’d like to discuss? I’m here to help!
User: Without emotions, how do you come up with original answers?
ChatGPT: As an AI language model, I generate responses based on patterns and information present in the data I was trained on. During training, I learned to predict the most likely next word given a sequence of words. This training process enables me to generate coherent and contextually relevant responses.
While I can provide information and generate creative responses, it’s important to note that I don’t have personal experiences, opinions, or subjective thoughts. My responses are based on patterns and knowledge derived from the text I was trained on up until September 2021. For up-to-date information or personal advice, it’s always a good idea to consult reliable sources or seek human expertise.
User: So, your answers are not entirely original
ChatGPT: That’s correct. While I strive to provide helpful and relevant responses, I generate my answers based on patterns and information contained within the training data I was exposed to. While this allows me to offer a wide range of information and generate coherent responses, it means that my responses are not entirely original or based on personal experiences.
It’s important to keep in mind that I can’t provide real-time information or insights beyond my training knowledge cutoff in September 2021. Additionally, while I aim to provide accurate and reliable information, there’s always a possibility of errors or outdated information. Therefore, it’s always a good idea to verify any critical information from trustworthy sources.
Conclusion
ChatGPT is basically programmed to take bits of conversations, and average them. If there is an oft quoted source, ChatGTP will plagiarise it. If there is a popular book listed in many places, ChatGTP could just copy it outright.
Nothing on ChatGTP is original. It is all sourced from what is available on the Internet. If you put your script or book online, ChatGTP is using that to give other people answers (and to give other people scripts, books, short stories, and so on).
If you use text generated by ChatGTP, you could get sued for copyright infringement.
So why don’t plagiarism detecters call it out for plagiarism? It’s programmers tried to program it to avoid plagiarism, but by using the same algorithms that are used to detect plagiarism. In other words, it knows how to avoid the computerised plagiarism detectors, but not how to create something original. So, what it does create may still get you sued in court.