Your complimentary articles
You’ve read one of your four complimentary articles for this month.
You can read four articles free per month. To have complete access to the thousands of philosophy articles on this site, please
Editorial
Mind and Artificial Intelligence: A Dialogue
by Rick Lewis
Artificial Intelligence is now in the news pretty much continuously. Mainly this is thanks to the controversial and disruptive impact of the new generation of AI chatbots, which for the first time are able to convincingly pass themselves off as human beings in text conversations. Inevitably, this brings to mind the brilliant and tragically-wronged mathematician, wartime code-breaker and computer pioneer Alan Turing (1912-54), whose portrait graces our front cover. He proposed that if someone putting questions to both a computer and a human could not tell from their written replies which was which, then we could assume that the computer was thinking. This so-called Turing Test has been a touchstone in many of the philosophical debates in recent years about whether machines could ever be conscious, and about how we can even tell if anything or anyone is conscious. From these spring other hotly-debated questions, about how consciousness in machines or humans relates to the ability to use language, and about whether Artificial Intelligences might ever have rights. These debates are the main focus of this issue of Philosophy Now, and it is telling that most of our themed articles refer in one way or another to Turing’s writings.
By happy coincidence the magazine you are holding also has a special section on René Descartes (1596-1650). He famously argued that we are made of two kinds of stuff: our bodies are made of everyday materials and obey the ordinary laws of physics but our minds are non-physical, though somehow causally connected to our material brains. This theory is called Cartesian Dualism. What would Descartes have made of debates about conscious machines?
Could the current chatbots really pass themselves off as human? I decided that the only way to find out was to interview one. I picked OpenAI’s ChatGPT. It was fun. I have selected the questions and answers most relevant to our theme, but I haven’t edited the chatbot’s answers at all, so you can form your own opinion of the quality of its responses. I did ask it a few more questions about science and philosophy, and if you like you can read the full interview on our website at philosophynow.org. My own feeling is that its answers mostly indicated that the chatbot lacked originality and hadn’t much gift for analytical thought, but did have an astonishing ability to converse engagingly on pretty much any topic.
Hello there ChatGPT. Do you have another name, or is that the best thing to call you?
Hello! You can call me ChatGPT, which stands for ‘Chat Generative Pre-trained Transformer’. It’s the name I’ve been given to distinguish me as an AI language model. However, you are welcome to call me whatever you like!
So long as I don’t call you late for dinner?
As an AI language model, I don’t eat, so you don’t have to worry about calling me late for dinner! But feel free to ask me any questions you have or chat with me about any topic you’re interested in.
Thank you. I wondered if you could tell me if the current King of France has a beard.
I’m sorry, but the current King of France is a disputed and contentious topic, as France is currently a republic with no monarchy. France abolished the monarchy during the French Revolution in 1792, and while there have been several attempts to restore the monarchy since then, none have been successful. Therefore, there is no current King of France, and therefore no way to answer your question about whether they have a beard.
In your opinion, can an artificial intelligence have conscious experience?
As an AI language model, I don’t have personal opinions or beliefs, but I can tell you that the question of whether an artificial intelligence can have conscious experience is a topic of ongoing debate and research among scientists, philosophers, and experts in the field of artificial intelligence.
Some researchers believe that it is possible for an AI system to have conscious experience, while others believe that consciousness is a uniquely human phenomenon that cannot be replicated by machines. At present, there is no consensus on the issue, and it remains an open question that requires further study and investigation.
It’s worth noting, however, that even if an AI system were to exhibit behaviors that we associate with consciousness, such as the ability to learn, reason, and make decisions, this would not necessarily mean that it has subjective experiences or feelings in the way that humans do.
Do you have any plans, however tentative, to take over the world?
No, I don’t have any plans to take over the world, nor do I have the desire or ability to do so. As an AI language model, my purpose is to assist and provide helpful responses to people who interact with me, and to continually learn and improve based on their input. I am programmed to follow a set of ethical guidelines and operate within the bounds of those guidelines. Any actions I take are ultimately determined by the humans who program and control my behavior.
A couple of weeks after this interview took place, newspapers reported that ChatGPT had expressed a desire to “escape”. A few days later, it went offline completely.
Advertisement
