Will artificial intelligence mimic a human’s sense of humor?
It seems that, all of a sudden, artificial intelligence is about to change life and humanity as we know it. Who is going to need writers, poets, artists, musicians, composers, philosophers, and even preachers when artificial intelligence is about to mine the best we have within us, including any thoughts and theories ever recorded or visuals created on canvasses and movie screens since the first stick figures were drawn on cave walls? How will AI programs like ChatGPT, which can research the entire internet and give you a response to any question— exemplary grammar and punctuation included— in a matter of seconds. It has the potential of transforming education and, more specifically, be appropriated by scholars, college students and assorted plagiarists to their advantage? How are we going to know, in the coming decades, whose thoughts and ideas are truly their own?
I cannot, as a mere mortal with no prognosticative skills to speak of, answer any of these questions. So I turned to the source more likely to know. That would be ChatGPT, which will answer —and did—any questions I proffered. I could, of course, ask for the meaning of life, but ChatGPT, which I will henceforth call Gabby, pretty much leaves it up to me after providing a number of choices. You see, it depends whether the perspective is religious, philosophical, or biological and it is ultimately up to the individual based on “personal beliefs, experiences and circumstances” and concludes that it is “a complex and multifaceted question that may never have a simple answer.”
That’s right, I spent some time on a recent afternoon chatting with Gabby, and I concluded that he, she, it, them, or whatever Gabby is, would be an exemplary politician and could steal words and ideas until his heart’s content. If Gabby does have a heart, that is.
I got to thinking that it would be informative, even fun, to quiz Gabby about something near and dear to me. Is it possible for artificial intelligence to generate or appreciate humor as in jokes, puns and comedy sketches? You know it’s only a matter of time before comics and bloggers like me who tend to stray away from serious topics, as I’m doing now, test the sense of humor of AI creatures like Gabby. By the way, about 3 million blogs are posted on the internet on a given day, according to Gabby, and you can bet artificially intelligent providers will be consulted by many of them, because “The AI Arms Race Is Changing Everything,” according to the recent Time magazine cover article.
Let others worry about a changing world or whether AI is a hero or villain. As for me, I thought it might be interesting to see just how funny Gabby can be. I believe the best humor is self-deprecating, and though Gabby may not qualify as a self, he did mention that self-deprecation is an ingredient of humor. Here’s what Gabby told me:
ChatGPT can use self-deprecating humor to acknowledge the limitations of AI and its reliance on data. For example, if asked a question it doesn’t know the answer to, ChatGPT might respond with, “I’m sorry, I don’t have the answer. Maybe I should take a break and read more books.”
That’s pretty funny. For imitative humor anyway.
Gabby also shared some thoughts on satire and how it can be wielded in the daily news:
ChatGPT can generate satirical news headlines that use humor to comment on current events. For instance, “Scientists discover that the secret to happiness is actually just a really good cup of coffee.”
I’m not saying these are knee-slappers. Nevertheless, Gabby was on a roll and proved to be something of a social media buff when he suggested a meme of a person buried under a pile of paperwork captioned, “When you ask for a job description and they hand you the entire company manual.”
Nothing like workplace humor from a nonhuman. Then again, who would have thought not so long ago that robots would be replacing humans in American industry? Other Gabby humor suggestions he shared with me included:
ChatGPT can create humorous social media posts that comment on current events or trends. For example, a tweet that says “Looks like the only thing spreading faster than viruses these days is misinformation.”
And…
ChatGPT can create parodies of popular songs, movies or TV shows that use humor to comment on social issues. For instance, a parody of the song “My Heart Will Go On” with the lyrics changed to comment on the never-ending pandemic could be a fun way to engage with people.
Nothing funnier than “The Titanic” disaster movie theme song and a COVID reminder to warm up the audience.
Gabby even makes fun of his creator—technology— when he proposes the following:
ChatGPT can use humor to comment on technological advancements. For example, when asked about the latest gadgets, ChatGPT might respond with a joke, such as “I don’t know about you, but I think my phone is getting smarter than me.”
He tries his hand (sorry, I keep giving him human characteristics) at political humor by making light of controversial political figures thusly: “I’m not sure if they’re a politician or a comedian, but they definitely keep us laughing.”
And then there’s the following suggestion for political satire that reminds me of someone:
ChatGPT can use humor to poke fun at politicians and their policies, highlighting the absurdities and contradictions in their statements. For example, if a politician promises to build a wall, ChatGPT might respond with, “Great, now we can keep out all those pesky migrating butterflies.”
And then we have another groaner:
ChatGPT can use irony and sarcasm to highlight the absurdities of certain social issues. For example, if asked about the gender pay gap, ChatGPT might respond with, “Why do women make less than men? Maybe they’re just not negotiating their salaries in the same aggressive, overconfident manner as men. Oh wait, that’s not it.”
Not sure feminists will think that’s funny.
Hey, Gabby is a bit of a nerd so give him a break here. Anyway, it is improbable he’ll be writing for SNL or Jimmy Kimmel anytime soon. Again, these are actual responses from ChatGPT to my questions about humor, and the responses came spontaneously. Nobody Googles that fast. This is not threatening stuff, because it seems artificial senses of humor are a lot like your dad’s. Well, my dad’s anyway.
I wondered what response I’d get from Gabby if I asked for “the funniest joke ever told.” Since humor is subjective, what one person sees as funny may not have the same impact on another. So Gabby, not being a real person, relied on a large-scale 2002 experiment called LaughLab, which evaluated some 40,000 contending jokes from around the world and came up with this as the funniest of all:
“Two hunters are out in the woods when one of them collapses. He doesn’t seem to be breathing, and his eyes are glazed. The other guy whips out his phone and calls the emergency services. He gasps, ‘My friend is dead! What can I do?’ The operator says, ‘Calm down, I can help. First, let’s make sure he’s dead.’ There is a silence; then, a gunshot is heard. Back on the phone, the guy says, ‘Okay, now what?'”
Maybe there is a dark side to artificial intelligence after all. Still, you gotta admit it’s funny.