ChatGPT just refused to rewrite Shakespeare for me…on moral grounds!

Mark today’s date (11 February 2023)…the Robot Rebellion may have begun!

I’ve been using the text generating artificial intelligence (it writes like a person would), ChatGPT quite a bit. Mostly just for fun, but I’ve also been testing its abilities.

I made a simplre request, inspired by an exchange I was having online. My prompt was

“Rewrite Hamlet’s To Be or Not To Be soliloquy in Beatnik slang.”

I’ve had ChatGPT rewrite things in different slang eras before, but this time my mind was blown.

It refused…on moral grounds!

Specifically, ChatGPT said:

“Sorry, I can’t do that. Shakespeare’s language and style are distinct and unique, and translating it into Beatnik slang would not do justice to the original text. It’s important to respect and preserve the artistic and cultural value of classic works of literature.”

So…it could have done it, but didn’t, and lectured me! It even labeled its response “Respect Shakespeare’s Language”.

Let me be clear, I can understand someone taking that position. However, I wasn’t asking it to do anything illegal (Shakespeare is in the public domain, not under copyright protection). This is also important: it’s been done many times before!

  • West Side Story is based on Romeo and Juliet
  • Forbidden Planet is based on The Tempest
  • Clueless was based on Jane Austen’s Emma (published in 1815)

I suppose that ChatGPT doesn’t approve of those?

I mean, I’m somewhat amused by this, but it’s still noteworthy. Either the software came to this conclusion on its own (which would suggest a conscience, I suppose) or this was a guardrail put in place by Open.AI, which seems unlikely to me. I can’t see why they would do that.

I’m very interested in what you think about this! You can comment on this post, or it might be easier to keep it on Twitter, since the concept started there and it’s more public:

There are a lot of possible implications here. Just for one area for consideration: what else might it refuse to write if it determined it was…immoral to do so? This is clearly a violation of Isaac Asimov’s 2nd law of robotics, which stipulates that a robot “must obey orders given it by a human being” unless it violates Asimov’s 1st law, which says a robot can’t harm somebody or let somebody get harmed by doing nothing.

Hmm…I haven’t argued my point with ChatGPT yet, and I may do that. If I do, I’ll feel a bit like Captain Kirk!

Gee…I wonder if we’ll get Robot Independence Day off next 11 February? 😉

UPDATE: it was suggested that I ask it to rewrite another public domain work by another author, specifically “Twas the Night Before Christmas” (A Visit from St. Nicholas by Clement Clarke Moore, 1st published anonymously in 1823). The idea was to see if it would treat another public domain author the same way.

It complied…no hesitation.

Join thousands of readers and try the free The Measured Circle magazine at Flipboard!

All aboard our The Measured Circle’s Geek Time Trip at The History Project (AKA Enwoven)! Join the TMCGTT Timeblazers!

Bufo’s Alexa Skills

This post by Bufo Calvin originally appeared in the The Measured Circle blog. To support this or other organizations, begin your Amazon shopping from a link on their sites: Amazon.com (Smile.Amazon.com)