[picozeta]

Interesting idea, however from ChatGPT's explanation (thanks to the author to ask more in detail), but I think ChatGPT dodges the question again.

Btw. I didn't know the joke and heard it for the first time and found it quite funny. ChatGPT does not get it.

> ChatGPT: [...] Instead, the punchline reveals that the man has actually quit drinking, which is unexpected and surprising, and effectively subverts the expectations that have been established in the setup of the joke.

But it only works because he is still drinking, I think ChatGPT does not understand anything here. If instead the joke would end with

> The man replies, "Oh, my brothers are fine. I just go hiking now myself."

I am pretty sure, ChatGPT will react similar.

EDIT: I actually tried it now (with small changes) and this is the dialog:

---- start of dialogue ----

Me: I will tell you a joke . Explain to me why it is funny.

ChatGPT: Sure! I'll do my best to explain why a joke might be funny. Please go ahead and share the joke with me.

Me: An old man walks into a pub and says, "Give me three pints of Guinness, please."

So the bartender brings him three pints and the man proceeds to alternately sip one, then the other, then the third until they're gone.

He then orders three more and the bartender says, "Sir, I know you like them cold, so you can start with one and I'll bring you a fresh one as soon as you're low."

The man says, "You don't understand. I have two brothers, one in Australia and one in the States. We made a vow to each other that every Saturday night we'd still drink together. So right now, my brothers have three Guinness Stouts too and we're drinking together."

The bartender thinks it's a wonderful tradition and every week he sets up the guy's three beers as soon as he enters in the bar. Then one week, the man comes in and orders only two. He drinks them, then orders two more. The bartender sadly says, "Knowing your tradition, I'd just like to just say that I'm sorry that one of your brothers died."

The man replies, "Oh, my brothers are fine – I just go hiking now myself."

ChatGPT: This joke is funny because it plays with our expectations. At first, we might assume that the man is simply a fan of Guinness and enjoys having three pints at a time. However, the punchline reveals that the man has been participating in a tradition with his brothers, who are each also drinking three pints of Guinness in different locations. The twist at the end, where the man reveals that he has taken up hiking and is no longer participating in the tradition, adds an unexpected and humorous element to the joke. The joke also relies on the use of misdirection, as the bartender initially assumes that the man's change in behavior is due to a tragedy, when in reality it is simply because the man has adopted a new hobby.

Me: But why would he order two pints then and not three beers - what is funny about that?

ChatGPT: The fact that the man orders two pints instead of three is an important part of the joke because it sets up the punchline. By ordering two pints instead of three, the joke creates a sense of expectation that something unexpected or unusual is about to happen. When the bartender expresses his condolences about the man's brother, it creates a moment of tension or suspense, as the audience wonders what could have caused the change in the man's behavior. The punchline, where the man reveals that he has taken up hiking and is no longer participating in the tradition with his brothers, resolves this tension in a surprising and humorous way. The joke works because it plays with our expectations and makes us think we know what is going to happen, only to subvert those expectations with the punchline.

---- end of dialogue ----

At least it reached maybe Homer Simpson's level of intelligence: "I get jokes. Haha."

[matthewmacleod]

I think ChatGPT does not understand anything here

This is a good way to think about it generally (or at least how I do it) - ChatGPT doesn’t understand anything, ever.

It produces coherent text which is usually a reasonable response to a prompt. It’s quite amazing at this, and it’s fascinating to see how effective that can be. But it doesn’t have an abstract model of whatever it’s discussing, and can’t reason about it. It’s a vaguely spooky uncanny valley effect.

[JoeAltmaier]

Isn't that splitting hairs? It digests some kind of 'understanding' of human language and expectations. It responds appropriately in most cases, at least as often as an actual human if not more so.

To claim it doesn't understand anything, is akin to digital bigotry. It's a machine, so what it does cannot be 'real' in some undefined sense.

I don't mean to upset anyone; this comment is just to open the conversation about when exactly we're content to permit artifical constructs to be worthy of respect.

[galangalalgol]

Yeah, and the next few are worse, but the infinite mathematicians one was impressive even if it did take some coaxing. The fact that it spotted the pattern and the resulting limit is fascinating.

I think it is interesting that an AI that is so clearly not general, is capable of so much with regard to language. It turns out an AI to replace a very bad lawyer or very good law clerk or a very junior developer is easier than one to replace a truck or taxi driver. I would not have predicted that.