One of the very first programs I “wrote”, and by that I mean “copied by hand from a book”, was a BASIC version of ELIZA, the famous “chat” program by Joseph Weisenbaum. I was a kid, just learning to program, and this sent me down a spiral into the history of artificial intelligence where I learned about the Turing Test, created by Alan Turing in 1950, which says, simplified, that the goal of natural language processing is to create a chat program such that, if a person is sitting at the other end, that person can’t tell if they’re talking to a human or a computer.

Well, it’s been 70+ years at this point and man are we getting close. There’ve been a million chat programs and competitions since then, I’ve played with a lot of them, and they’ve all been quite terrible. In fact if you’re trying to break one – after all it is a test, not a game – it’s usually pretty easy. But if you’re not? If you honestly just want the content that comes from a conversation, with back and forth question and answer? Wait’ll you get a load of ChatGPT.

As I always do, I just walked up and started hitting it with Shakespeare questions. I wasn’t trying to trick it, I was just asking what I thought might be interesting exploration of what it could be expected to do. What follows is unedited transcript.

I started out with an easy one. And I got back an easy response. It’s probably not copied from Wikipedia, but it reads like it could have been. I didn’t expect much.

That was kind of cool. I not only got an answer, I got a reasonable and grammatically correct answer. Often in the older versions of these chat engines, trying to express something in a different way meant just doing some dumb word swapping. This one’s maybe doing a little of that (“tragic” = “very sad”) but it does a lot more than swap out words.

Ok, let’s make it a little more challenging.

Fascinating. Again, like the first question it feels very Wikipedia-like. But it’s serving these answers up in a matter of seconds. And it’s not like this things got a database of what people might ask. I’m relatively certain I’m one of the few people drilling down on random Shakespeare combinations.

I don’t know what I expected here, but I like this answer. It implies strongly that this thing understood my question, understands not only the characters of Hamlet but the elements of tragedy and comedy, and makes a valiant attempt to offer suggestions about how they might fit together.

Ok, two more then I want to go back and play with it some more.

I don’t know why people keep getting so excited about using this thing to generate original content – it’s not going to offer opinions, and it knows when that’s what you’re asking. So this heavily suggests that all we can ever really get out of it (well, for now) is factual responses.

This is basically the same question, yes. But do you see why I left it in here? It literally tells me, “You just asked me the same question in a different way.” So not only is it doing a ridiculously impressive job answering the questions, but it’s keeping your conversation in context and using that as part of the answer.

I wasn’t terribly impressed by the art generators that were all the rage a few months ago. This, on the other hand. I could talk to this thing all day.

Being a computer scientist and a Shakespeare geek is a little weird sometimes. For as long as I can remember, I’ve seen Shakespeare’s work – and, by extension, his universe – as a structured body of text to be manipulated however I am able. When you have the ability to code at your fingers, structured data is your playground. All you see is “Plays have scenes, scenes have dialogue, dialogue has lines that are spoken by speakers…” and then you build it back up from there.

People usually go one of two routes with this knowledge. First, they run word analysis and try to come up with reasons why Shakespeare liked to use “dark” words earlier in his career, or how often he used synonyms for love. Stuff like that.

Or, according to the new AI world where everything is “machine learning”, they “train” a model on how Shakespeare wrote, and then they generate fresh new content “in the style of Shakespeare.” I always hate these, because “in the style of Shakespeare” can be said with fewer words as, “not Shakespeare.”

I’ve always looked at it differently. I see characters, and how they relate to each other. In my dream world, where I’m a younger man with more time and energy to work on projects that have no monetary value but are infinitely fascinating to me, I want to read in the text of a play in such a way that each character turns into a chatbot, and the user can do stuff like walk through Romeo and Juliet from different character perspectives, stopping to talk to each character. “Ask TYBALT why he hates ROMEO.” Stuff like that. I think that would be awesome. I’ve often thought of how far I could really take it. I’ve just never written it.

Of course, once you get into interacting with the story, you have to start creating new content. Shakespeare and “interactive fiction” is not new. The name Ryan North might be best known – he actually published a “choose your own adventure” version of Hamlet. But it’s a much smaller universe than either books or games. You basically get to work with people who were looking for you already. It’s a match made in heaven.

So I’m a bit giddy to have found the interactive Twine game We Are Not All Alone Unhappy sitting in an article about newly published SF inspired by Shakespeare. This one’s a little different. It’s not a book. It’s a small game where you pick two Shakespeare characters (from a pre-chosen list of nine) and see if they get a “happy ending.” Who decides that? Well, the author does – Cat Manning. And the math geeks may jump right to the numbers and realize that there are only 72 possible combinations to run through. But each of those combinations is a spin on “what happens when you put these two characters in a room”, so that’s 72 pages of original Shakespeare-related content, and that’s what we’re here for.

There is a game and a goal. Each character has empty hearts next to their name. Find them a happy ending, you fill a heart. The goal is to fill all the hearts. There are 28 hearts and 72 combinations so you won’t play for too long before stumbling across the good matches. Nobody said it’s a difficult game. But those of us who have personal relationships with Shakespeare characters will have that much more fun saying, “Oh, I wonder what would happen if I put Mercutio and Kate in a room together?”

I’m also finding that I disagree with some of the results 🙂 and wish they were longer. Some are real dead ends. Some are a little softcore, so reader beware. But if you’re always on the lookout for interesting and slightly geeky new ways to play with Shakespeare content, it’s definitely worth playing with.

https://borrowers-ojs-azsu.tdl.org/borrowers/article/view/342/607

There’s a story told about the movie Marathon Man, that saw Dustin Hoffman working together with Sir Laurence Olivier. Hoffman, a method actor, was playing a man who hadn’t slept in three days … so, he didn’t sleep for three days. Upon hearing this, his co-star Sir Laurence told him, “My dear boy, why don’t you try acting?”

I was surprised to see Hoffman’s name on a Shakespeare story, because I can’t remember seeing him in any major Shakespeare film credits. Turns out we’re talking about Peter Hall’s 1989 The Merchant of Venice, as told by his Portia, Geraldine James. Highlights:

• Hoffman wanted to do Shakespeare. So, of course, he goes to Peter Hall. Because that’s what you do when you have no Shakespeare credit, you go to the FOUNDER OF THE ROYAL SHAKESPEARE COMPANY. That’s a little like saying I think I can fix the economy, somebody get me Joe Biden on the phone.
• He said, “Will you direct me in Hamlet?” Hall, to his credit, said, “Ummmm….maybe try something else first before you tackle Hamlet.” So he ends up as Shylock.
• James quotes Hoffman as saying “I’ve just realized, you can’t improvise this shit.” Thank god nobody gave him a Hamlet.

https://nationalpost.com/news/world/dustin-hoffman-was-mad-he-couldnt-alter-shakespeares-dialogue-co-star-recalls