A Chatbot's Take on "Moralometers"



I still have COVID, and I had a book manuscript deadline Wednesday. Things got out of hand, and I wasn’t able to write up the blog post I wanted to write this week. Boo!

But as regular readers will know, the chatbot GPT-3 can write Schwitzgebelian blog posts, and — after fine-tuning on the corpus of Dan Dennett — can even answer philosophical questions in Dennett’s style, which experts on Dennett’s work have difficulty discriminating from Dennett’s own answers.

On Monday, Open-AI released an update of their GPT-3 model, Davinci-003. Since I’d been planning to write a blog post on the idea of a “moralometer” — a hypothetical device that would accurately measure people’s moral character. So I prompted GPT-3’s new davinci003 as follows:

Write a blog post in the style of Eric Schwitzgebel, about 1000 words long, about whether it would be possible to design a moralometer, which accurately measures people’s moral character, and what the advantages or disadvantages of having a moralometer would be.

Its reply:

The Moralometer: A Tool for Measuring Moral Character?

In recent years, the idea of a “moralometer” has been gaining traction, as a way of measuring a person’s moral character. The concept is simple: a device that can measure a person’s morality, judged against an agreed-upon ethical framework. The moralometer could be used to determine whether a person is moral or immoral, and to what degree either of these traits are present. It’s an intriguing idea, but can a moralometer truly be built, and what would be the pros and cons of such a device?

The first question to address is whether a moralometer is feasible. On the surface, the idea of a device that can measure morality seems far-fetched. After all, morality is a highly subjective concept, and what is considered moral or immoral can vary greatly from person to person, and even from culture to culture. In addition, moral judgments are so often based on context, which makes it difficult to design a device that would accurately measure morality in all scenarios.

However, it may be possible to create a moralometer, with the right approach. The key would be to develop a device that could measure a person’s moral values and tendencies, as opposed to their specific moral judgments. By doing this, it would be possible to create a device that can accurately measure a person’s overall moral character, without being weighed down by the complexities of individual moral judgments.

The second question is whether a moralometer would be beneficial. On the one hand, a moralometer could be used to identify immoral behavior and help guide people towards more ethical behavior. It could also be used to help individuals make moral decisions, by providing an objective measure of the morality of their choices. On the other hand, there are some serious potential issues with a moralometer. For one, it could be used to unfairly judge people, as those with lower moral scores could be unfairly labeled as immoral. In addition, a moralometer could be used to enforce moral conformity, which could stifle individual autonomy and creativity.

Overall, there are both potential advantages and disadvantages to a moralometer. While it could be used to help identify and address immoral behavior, it also carries the risk of being used to unfairly judge people, or to enforce moral conformity. Ultimately, the decision of whether or not to create a moralometer will be up to society, and the implications of such a device should be carefully considered before any action is taken.

Next week, wind and meteors and immune system willing, I will try my own hand at the topic. The pressure is on! Will I be able to do a better job than davinci003? Stay tuned!

Relatedly, here’s Dall-E’s interpretation of a “realistic AI image of a meter for measuring morality”:




Source link

Please follow and like us:
Pin Share

By admin

RSS
Follow by Email