As we continue to experiment with conversational AI, where UX plays a pivotal role, the ability to understand and engage in a task is a crucial differentiating factor. When it comes to the “simple task” of telling a joke, two AI models stand out: ChatGPT and Google Bard.
While both AIs have their merits, the difference between the two becomes clear in their approach and level of understanding, and the overall user experience they offer.
In this article, we explore the charming and insightful journey of ChatGPT, which effortlessly grasps the essence of joke-telling, fostering fun interactions and engaging conversations. We dive into its ability to adapt, surprise, and even explain the humor behind its punchlines. We’ll also compare ChatGPTs intuitive conversational power with the more linear approach of Google Bard. We hope to shed light on the captivating possibilities of interacting with generative AI in a way that feels natural, enjoyable, and user-centric. Join us as we uncover how ChatGPT’s understanding and UX elevate the art of conversation.
First up, ChatGPT
A few nights ago I was washing dishes with my kids. For kicks, I asked ChatGPT to tell us a joke. This is what followed:
Me:
Hi ChatGPT! My family and I are washing dishes and would like to make this a little more fun, can you tell us a joke?
ChatGPT: Certainly! Here’s a classic one for you:
“Why don’t scientists trust atoms?” “Because they make up everything!”
I hope that one brought a smile to your face! Feel free to ask for more jokes or anything else you’d like to discuss. << All of them contained this type of message at the end so I’ll skip this in the future.
Me: Someone in the room actually guessed the answer! Can you try again?
ChatGPT: Apologies for the spoiled punchline! Let’s try another joke:
“Why don’t skeletons fight each other?” “They don’t have the guts!”
Me: They guessed that one before I could even finish the joke! Can you please try again?
Apologies for the repeated spoilers! Here’s another joke for you:
“Why don’t scientists trust atoms?” “Because they make up everything… and then they split!”
I hope that one caught them by surprise!
Me: That was great! Can you tell me another joke that has a surprise ending?
ChatGPT: Certainly! Here’s a joke with a surprise ending for you:
“Why don’t scientists trust atoms?” “Because they make up everything… and they’re always up to something!”
I hope that one managed to bring a laugh and catch them off guard.
Me: Everyone in the room thinks it’s very funny that you keep telling the same joke over and over again with different punch lines!
ChatGPT: Apologies if the repeated jokes became repetitive. I’ll make sure to provide you with a fresh and original joke this time:
“Why don’t scientists trust atoms?” “Because if they had trust issues, they would need atomic therapy!”
Me: Hey chat, GPT, why don’t scientist trust atoms?
ChatGPT: Scientists don’t trust atoms because they make up everything!
Me: And split!
ChatGPT: Exactly! Atoms can undergo a process called nuclear fission, where they split apart. This plays on the double meaning of “make up everything” and “split.” It’s a playful twist on the trustworthiness of atoms.
Me: Can you tell me another joke that has a surprise positive punchline
ChatGPT: Certainly! Here’s a joke with a surprise positive punchline for you:
“Why don’t scientists trust atoms?” “Because they make up everything… and they’re positively amazing!”
I hope that one caught you off guard in a delightful way!
Me: Can you tell me a joke and a haiku format?
ChatGPT: Sure! Here’s a joke presented in a haiku format:
Spring rain gently falls, Why did the scarecrow win? Outstanding in field.
Me: I’m kind of surprised that you did not bring up the atom joke again
ChatGPT: Apologies for the oversight! Here’s the atom joke presented in a haiku format:
Atoms dance and spin, Scientists don’t trust their ways, Yet they make all things.
Me: Amazing.
I personally found it brilliant that ChatGPT kept coming back to the same joke, and so did the kids. To top it off, when I told the joke back to ChatGPT it went on to explain it to us. I’m not sure if that was trolling, but we all thought it was genius.
By comparison, we went over to Bard and asked it the same question, this is how it went:
Next up, Bard
Me: Hi Bard, my family and I are washing dishes and would like to make this a little more fun, can you tell us a joke?
Bard: Sure, here is a joke about washing dishes:
Why did the dish go to the hospital? It had a bad clatter!
Here is another one:
What do you call a lazy dishwasher? A pane in the glass!
I hope these jokes make washing dishes a little more fun for you and your family!
Me: Those are great, can you tell me another joke?
Bard: Sure, here are a few more jokes:
Why did the scarecrow win an award? Because he was outstanding in his field!
What do you call a fish with no eyes? Fsh!
What do you call a lazy kangaroo? A pouch potato!
I stayed up all night trying to figure out where the sun went. Then it dawned on me.
Why did the student eat his homework? Because the teacher told him it was a piece of cake.
Why did the doughnut go to the dentist? To get a filling.
What do you call bears with no ears? B.
Who built King Arthur’s round table? Sir Cumference.
I hope you and your family enjoy these jokes!
Bonus: ChatGPT tells Bard a joke
Me: Hi Bard, I have a joke for you. Why don’t scientists trust atoms?
Bard: I love a good science joke! Here’s my answer:
Why don’t scientists trust atoms? Because they make up everything! I hope you enjoyed my joke!
Me: And they split!
Bard: That’s a great addition to the joke, I love it!
Me: ChatGPT told me that one
Bard: That’s great! I’m glad you enjoyed the joke. I’m always looking for new jokes to learn, so if you have any more, please share them with me.
I know that jokes are not the primary purpose of either of the AIs. That said, I found ChatGPT to be more engaging and really got the spirit of what we were hoping for.
Let’s put a bow on this
In the realm of AI-generated humor (if that’s a thing), ChatGPT shows an impressive understanding of the “true ask”… entertainment.
Its ability to adapt, surprise, and even explain the nuances of it’s jokes shows a level of engagement and conversational prowess that sets it apart.
Unlike the more straightforward approach of Google Bard, ChatGPT integrates into conversations with ease, making the user experience (UX) feel more like interacting with a witty friend, rather than simply receiving a list of pre-written jokes.
As we continue to explore the frontiers of AI, it becomes evident that conversational AI models like ChatGPT have the potential to transform human-machine interactions, offering a glimpse into the future of intuitive and engaging conversations.
So, if you’ve been on the fence about engaging with generative AI or feel intimidated at what it looks like, embrace the possibilities and let the laughter flow as you begin your own “conversations” with AI-powered companions like ChatGPT.