Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

LLMs tell bad jokes because they avoid surprises

danfabulich.medium.com

Post reply on HN
Print view View original

141–150 of 163 posts

Re: LLMs tell bad jokes because they avoid surprises

#141

Post by codechicago277 »

Wowfunhappy wrote: post #78
brookst wrote: 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?

Because it was tired of setting

Re: LLMs tell bad jokes because they avoid surprises

#142

Post by codechicago277 »

shagie wrote: post #110
Wowfunhappy wrote: post #78

Earlier quoted context omitted.

...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?

https://chatgpt.com/share/68a209d3-ef34-8011-8f60-1a256f6038... I'm going to go with "Because it wanted a higher noon." was probably its best one of that set... though I'll also note that while I didn't prompt for the joke, I prompted for background on "climbing" as related to the sun. I believe the problem with the joke is that it isn't one that can be funny. Why is a raven like a writing desk? Personally, I didn't…

The answer to “why is a raven like a writing desk” is generally considered to be: “Poe wrote on both”, which is witty at least, if not laugh out loud funny.

Re: LLMs tell bad jokes because they avoid surprises

#143

Post by lmm »

542458 wrote: post #79
libraryofbabel wrote: post #75

> LLMs are trained to predict what the “next word” would be a sentence. Their objective requires the LLM to keep surprise to an absolute minimum. from which the author concludes that pre-training introduces bias against being able to tell jokes. I see no reason for this to be true. This feels like they’re imposing their intuitive understanding of surprise onto the emergent properties of a very complex process (“minim…

I think if what the author said was true, you’d be able to improve joke-writing ability by increasing temperature (i.e., allowing more unexpected tokens). I doubt this actually works. As an aside, I just asked gpt5-thinking to write some jokes on a specific niche topic, and I’d say it was batting maybe 20% of them being moderately funny? Probably better than I’d get out of a room of human beings. So much like with co…

> I think if what the author said was true, you’d be able to improve joke-writing ability by increasing temperature (i.e., allowing more unexpected tokens). I doubt this actually works.

I would think it would help tbh. Seems worth a try at least.

Re: LLMs tell bad jokes because they avoid surprises

#144

Post by zoeey »

I’ve tried using large models to come up with jokes. They can mimic the structure pretty well, but something always feels missing. It’s like following a recipe step by step but ending up with food that lacks real flavor. Sometimes they get close, but it rarely feels truly surprising. Maybe humor needs more than just structure. Maybe it needs a unique point of view.

Re: LLMs tell bad jokes because they avoid surprises

#147

Post by rossant »

monstertank wrote: post #39

This post got me wondering, so I asked chatgpt for jokes about hackernews as if made by various comedians...I laughed at one or two /shrug Bill Hicks (angry truth-telling prophet) "Hacker News is where ideas go to die. Not because they’re bad — but because 400 anonymous software prophets decided they’re God. And God doesn’t code, man." --- Bill Burr (ranty everyman, annoyed at everything) "I went on Hacker News once.…

That was... not that bad, actually.

Re: LLMs tell bad jokes because they avoid surprises

#148

Post by ajuc »

So there's 2 thesis in this article.

1. joke quality is how much sense the punchline makes as a completion of the setup minus the probability of finding the punchline given just the setup

2. jokes are subjective, people disagree wildly about how good a joke is, so if you aggregate preferences you get mediocre jokes at best.

I think 1 is the important part. If it was just 2 - comedians with widespread appeal wouldn't exist, but they do.

But 1 is basically the exact opposite of how LLM work. So it's no surprise it's hard for them.

It would be interesting to compare how well LLMs can estimate how funny a joke is vs how good they are at generating jokes.

Re: LLMs tell bad jokes because they avoid surprises

#149

Post by imatrix »

it's not about the punchline, it's about the fact that jokes are an extremely complicated thing. The reason? It's a highly abstract structure of information, not unlike low-level speech (how words are supposed to be put together in different languages), code (different programming languages have different rules for commands and sequences).

Even the best LLm's are still at the level of children in this abstraction, so they can't make "quality" jokes. They also suffer from not having a unique personality and being the average of everything. Until this is addressed, don't expect great jokes to come out of AI. It's almost the most challenging discipline. I wouldn't be afraid to make the comparison that the "joke" is the real Turing test.

Re: LLMs tell bad jokes because they avoid surprises

#150

Post by 4gotunameagain »

josephg wrote: post #66
amelius wrote: post #52

I'm sure there is a guy in OpenAI working on the theory of humor and how to make LLMs be comedians. Must be an interesting job.

I have no doubt plenty of smart engineers at tech companies would rather reinvent the wheel than read a book on theatre. But if anyone’s interested, there are plenty of great books talking about the philosophy of comedy, and why some things work on stage and some don’t. I highly recommend Keith Johnstone’s “Impro”. He’s the guy who invented modern improv comedy and theatre sports. He says things are funny if they’re…

> Maybe their obvious just isn’t the same as ours.

Of maybe they're just stochastic parrots and are devoid of intelligence, a necessity to make other intelligent beings laugh with novel jokes ;)

Post reply on HN