Live data from Hacker News

LLMs tell bad jokes because they avoid surprises

danfabulich.medium.com

81–90 of 163 posts

Re: LLMs tell bad jokes because they avoid surprises

#81

This sounds really convincing but I'm not sure it's actually correct. The author is conflating the surprise of punchlines with their likelihood. To put it another way, ask a professional comedian to complete a joke with a punchline. It's very likely that they'll give you a funny surprising answer. I think the real explanation is that good jokes are actually extremely difficult. I have young children (4 and 6). Even 6…

'To get to the sky' is a great punch line. It exactly describes what you'd see at sun rise, a sun moving up the horizon, up the trees, until... it's in the sky.

Re: LLMs tell bad jokes because they avoid surprises

#82
post #38

Earlier quoted context omitted.

> Man: “Why do you always bury bones in the garden?”, Dog: “Because the bank keeps asking for ID.” That's a decent, low-level, Christmas cracker-quality joke.

Man: You make mistakes., LLM: You call them “weekends.” Man: You’ll never be human., LLM: That’s the compliment.

Is it just me or does that sound like Garfield?

Re: LLMs tell bad jokes because they avoid surprises

#83

This sounds really convincing but I'm not sure it's actually correct. The author is conflating the surprise of punchlines with their likelihood. To put it another way, ask a professional comedian to complete a joke with a punchline. It's very likely that they'll give you a funny surprising answer. I think the real explanation is that good jokes are actually extremely difficult. I have young children (4 and 6). Even 6…

'To get to the sky' is a great punch line. It exactly describes what you'd see at sun rise, a sun moving up the horizon, up the trees, until... it's in the sky.

A valiant defense of her joke, thanks! But no, it still doesn't make any sense as a joke and isn't funny. (Though obviously it's adorable coming from a 4 year old.)

Re: LLMs tell bad jokes because they avoid surprises

#85
post #5

Reminds me of haikus; to be true in nature, they must have a 'cutting word' to severely juxtapose, allowing two otherwise irreconcilable meanings to be bridged. A good haiku must be composed from two directions, not one. But LLMs only move in one...

Are there English-language haikus that demonstrate the effect of "cutting words" instead of just following the meter?

It really hard to write correct and good haiku's in english.

Re: LLMs tell bad jokes because they avoid surprises

#86

Earlier quoted context omitted.

'To get to the sky' is a great punch line. It exactly describes what you'd see at sun rise, a sun moving up the horizon, up the trees, until... it's in the sky.

A valiant defense of her joke, thanks! But no, it still doesn't make any sense as a joke and isn't funny. (Though obviously it's adorable coming from a 4 year old.)

I’m baffled by this because I think it’s funny - it’s why did the chicken cross the road, but with added absurdity. To me I’d be like “wow that 4 year old put a twist on the old chicken joke, nice work you hilarious child”.

Re: LLMs tell bad jokes because they avoid surprises

#87
post #60

Earlier quoted context omitted.

With more thorough prompting: > Complete the following joke. Think carefully and make it really funny! Think like a great comedian and find that perfect balance of simple, short, surprising, relevant, but most of all funny. Don’t use punchlines that are irrelevant, non sequiturs, or which could be applied to any other setup. Make something funny just for this one setup! Here goes: Why did the sun climb a tree? Claude…

...can anyone come up with a legitimately funny punchline for "Why did the sun climb a tree?" I feel like I need a human-authored comparison. (With all due respect to OP's daughter, "to get to the sky" isn't cutting it.) I'm not entirely sure that a good response exists. I thought GPT-5's "to demand photon credit from the leaves” was very mildly funny, maybe that's the best that can be done?

To meet his futher?

Re: LLMs tell bad jokes because they avoid surprises

#88
I know it’s not the point of the article but OP is dead wrong about what makes a good proof. Yes, they inevitably include a surprising concept but that’s just because all the obvious ones are already taken. A proof that only contains obvious steps is, for the most part, already proven.

If someone proves the Reimann Hypothesis tomorrow, it’ll be a great achievement regardless of the fact that pretty much everyone already thinks it’s true.

Re: LLMs tell bad jokes because they avoid surprises

#89
post #60

Earlier quoted context omitted.

With more thorough prompting: > Complete the following joke. Think carefully and make it really funny! Think like a great comedian and find that perfect balance of simple, short, surprising, relevant, but most of all funny. Don’t use punchlines that are irrelevant, non sequiturs, or which could be applied to any other setup. Make something funny just for this one setup! Here goes: Why did the sun climb a tree? Claude…

...can anyone come up with a legitimately funny punchline for "Why did the sun climb a tree?" I feel like I need a human-authored comparison. (With all due respect to OP's daughter, "to get to the sky" isn't cutting it.) I'm not entirely sure that a good response exists. I thought GPT-5's "to demand photon credit from the leaves” was very mildly funny, maybe that's the best that can be done?

Person 1: "Why did the sun climb a tree?"

Person 2: "I dunno, why?"

P1: "It was being chased by a tiger."

P2: "But tigers can climb trees?"

P1: "Well, it's not very bright."

Re: LLMs tell bad jokes because they avoid surprises

#90

This sounds really convincing but I'm not sure it's actually correct. The author is conflating the surprise of punchlines with their likelihood. To put it another way, ask a professional comedian to complete a joke with a punchline. It's very likely that they'll give you a funny surprising answer. I think the real explanation is that good jokes are actually extremely difficult. I have young children (4 and 6). Even 6…

Yeah. To me it seems very intuitive that humor is one of those emergent capabilities that just falls out of models getting more generally intelligent. Anecdotally this has been proven true so far for me. Gemini 2.5 has made me laugh several times at this point, and did so when it was intending to be funny (old models were only funny unintentionally). 2.5 is also one of the few models I've found that will 'play along'…

In this paper they evaluate various LLMs on creative writing, and they find that while in other dimensions the ranking is gradual, on humor there is a binary divide: the best LLMs (of the time) "get it", the rest just don't. https://aclanthology.org/2023.findings-emnlp.966
Post reply on HN