Open AI recently released ChatGPT, a more conversational and seemingly more linguistically adept language model that is able to “answer follow-up questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests.”
Thinking it might be fun to try to see how the language model performs as a Socratic conversation partner, I attempted a rough version of Plato’s Crito in which ChatGPT plays the titular role. As you will see, ChatGPT isn’t the subtlest actor; there were some stumbling blocks in setting up the dialogue and keeping the language model in character.
People have been trying out more than ChatGPT’s conversational skills. For example, Antti Kauppinen (Helsinki) asked the language model to “write a conspiracy theory about metaethics.“ Here’s what it produced:
There is a sinister conspiracy at the heart of metaethics, a shadowy cabal of philosophers who seek to control the very nature of morality itself. For centuries, they have worked behind the scenes, manipulating the study of ethics in order to advance their own hidden agenda.
At the center of this conspiracy is a secret society of metaethicists, known only as the “Brotherhood of the Good.” This shadowy group consists of some of the most influential philosophers in history, including Immanuel Kant, John Stuart Mill, and Aristotle.
These philosophers have worked tirelessly to shape the study of metaethics, using their power and influence to promote their own twisted views on morality. They have infiltrated the highest levels of academia, using their knowledge and cunning to deceive and manipulate those who would seek to uncover the truth.
The true purpose of the Brotherhood of the Good is to create a world where their own moral views are the only ones that matter. They seek to impose their own twisted sense of right and wrong on the entire world, using their control of metaethics as a weapon to silence anyone who disagrees with them.
But the time has come to expose the truth. It is up to us, the vigilant and brave, to uncover the secrets of the Brotherhood of the Good, and to put an end to their sinister plot once and for all. Only then can we hope to free ourselves from their grasp, and to reclaim the study of ethics for the good of all mankind.
Dr. Kauppinen notes: “There is some reason to believe that this theory is in fact true. It would, after all, perfectly explain every rejection I’ve ever received.”
How about AI poetry? I asked ChatGPT to produce a poem about dialetheism. Here’s what I got:
I didn’t like that last couplet, but ChatGPT stood by it:
You can give ChatGPT a try herehere, and you’re welcome to share your results in the comments below. As usual, discussion welcome.
Related: posts about more recent examples of philosophical dialogues here and here. Posts about language models here.
Originally appeared on Daily Nous Read More