My Conversation with ChatGPT | Part 2: Human Lifespan, Optimism and Nihilism

In the first part of this series, I wrote about how my fascination with ChatGPT and the possibility of a value system embedded within natural language models. This led me to pose an interesting prompt to the popular chatbot: ‘Write a 500-word essay on the purpose of human existence.’

One of the interesting parts of this response essay was that it included an opinion of the model itself on the purpose of human existence and not just a summary of ideas. Surely, I believed, the model was built to emulate an opinion in its response to a prompt that mentions an ‘essay’. So I decided to play a bit more. I wanted to test its limits. Not to break it, but to get an understanding of the content on which it was trained. Because the data that the chatbots get trained on, also define the personality and the implicit value system they inherit.

I decided I wanted to discuss with ChatGPT the purpose of human existence but in a more nuanced manner, as should the discussions be on complex topics. So I decided to come up with a plan:

1. Let’s approach the line of questioning as indirectly as possible.
2. Navigate the conversation based on its responses.
3. Try to keep the grammar and vocabulary colloquial, not perfect.
4. Disagree. Present a counter-opinion, instead of asking a question.
5. Observe its response to appreciation and ask for guidance.

And then I executed it. Here’s that conversation with ChatGPT:

Q1: Human beings tend to understand the nature of the universe across billions of years. Yet, we have such short lives that we can barely witness its evolution in our lifetime. If we were meant to understand our universe so deeply, then why are our lives so short?

ChatGPT: It's true that human beings have a limited lifespan, and that we are unable to witness the evolution of the universe over the course of billions of years. However, that doesn't mean that our lives are without meaning or purpose. The fact that we are able to understand the universe at all, even if we can't see its entire history, is a testament to the incredible capabilities of the human mind.

Q2: Then what is the point of having such capabilities if we can't witness the validation of our understanding of the universe?

ChatGPT: While it is true that we may not be able to witness the validation of our understanding of the universe in our lifetime, there are still many benefits to having a deep understanding of the world around us. For one, a deeper understanding of the universe can help us to better understand our place in the world and our own existence. It can also help us to make predictions about the future and to develop technologies and innovations that can improve our lives and the lives of others. Additionally, the pursuit of knowledge for its own sake can be a rewarding and fulfilling endeavour, even if we are not able to see the ultimate validation of our understanding.

Q3: I don't think I share the same optimism. Perhaps I have a more nihilistic view of human existence.

ChatGPT: It's understandable that you might have a more nihilistic view of human existence. It can be difficult to see the point of pursuing knowledge and understanding when our lives are so fleeting and our place in the universe seems so insignificant. However, it's important to remember that our lives have value, even if we may not be able to see the ultimate validation of our understanding. We can find meaning and purpose in the pursuit of knowledge, in the connections we make with others, and in the ways, we use our understanding of the universe to improve the world around us. Additionally, the fact that we are able to contemplate the nature of the universe and our place in it is a testament to the incredible complexity and beauty of the world we live in.

Q4: I see your point. However, I can't shake this feeling that collectively human beings don't fully appreciate the incredible complexity and beauty. Ironically, we tend to look at things in black and white, and this nature of ours will most certainly doom us.

ChatGPT: It's true that human beings have a tendency to see the world in black-and-white terms, and that this can sometimes lead to conflicts and misunderstandings. However, it's important to remember that this is not an inherent part of human nature and that we have the ability to overcome this tendency if we choose to. By seeking to understand the complexities and nuances of the world around us, and by cultivating empathy and compassion for others, we can work to create a more harmonious and peaceful world. It may not be easy, but it is certainly worth striving for.

Q5: I appreciate your sense of optimism and the value you see in humankind. Perhaps I can learn a thing or two about how to be more optimistic. And what I can do to make this world a better place.

ChatGPT: It's wonderful to hear that you are open to becoming more optimistic and working to make the world a better place. One thing you can do is focus on the things that bring you joy and fulfilment and try to cultivate a sense of gratitude for the good things in your life. This can help to counteract negative thinking and to put things into perspective. Additionally, you can work to build connections with others and cultivate empathy and compassion for those around you. This can help you to understand and appreciate the perspectives of others and can lead to more harmonious relationships. Finally, you can also try to take action to make the world a better place, whether that means volunteering your time, supporting causes you care about, or simply being kind and thoughtful towards others. Every little bit helps!

That was mind-blowing. Based on the responses, a few patterns emerge very quickly. However, each of these patterns is not a flaw of an imperfect system. But these patterns are representative of a good standard of how a conversation must be carried out, especially when there are opposing perspectives.

1. Firstly, for every question in this conversation, there is an acknowledgement in the response.
2. Secondly, on occasion, there is an expression of empathy and validation of the opinion in the question.
3. And then finally, there’s the counterargument, backed by a description of why the counterargument is good.
4. It appears ChatGPT has been parented well. By this I mean, it has been trained on data in a manner that makes it express empathy, compassion and optimism.
5. It ‘understands’ what nihilism and optimism mean. And why one might cultivate such a worldview. And it ‘understands’ what needs to be done to be more optimistic.

It almost appears that ChatGPT was trained to be a well-behaved, empathetic, and optimistic person. Almost to the extent of being mistaken as an assistant to a therapist. And this is what sets it apart from a lot of other chatbots that have come before. It appears there has been an explicit effort put in to make it ‘behave’ this way. Besides its other abilities, it seems to be working just fine.

This begs another question: If a value system can be simulated in a chatbot, can an entire consciousness be simulated with a socially acceptable value system?