Live data from Hacker News

LLMs tell bad jokes because they avoid surprises

danfabulich.medium.com

101–110 of 163 posts

Re: LLMs tell bad jokes because they avoid surprises

#101

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.…

Well I enjoyed those

Re: LLMs tell bad jokes because they avoid surprises

#102
post #69

Earlier quoted context omitted.

> it is frustrating to see the goalposts moved without even acknowledging how much work and progress were involved in meeting the goalposts at their previous location. Half the HN front page for the past years has been nothing but acknowledging the progress of LLMs in sundry ways. I wish we actually stopped for a second. It’s all people seem to want to talk about anymore.

I should have been more clear. Let me rephrase as: among those who dismiss the latest innovations as nothing special because there is still further to go, it would be nice to acknowledgment when goalposts are moved.

Maybe the people raving about LLM progress are the same people holding them to those high standards?

I don’t see what’s inconsistent about it. “Due to this latest amazing algorithm, the robots keep scoring goals. What do we do? Let’s move them back a bit!” Seems like a normal way of thinking to me…

I see people fawn over technical progress every day. What are they supposed to do, stop updating their expectations and never expect any more progress?

It could of course be that there are people who “never give it up for the robots”. Or maybe they do, and they did, and they have so fully embraced the brave new world that they’re talking about what’s next.

I mean, when I sit in a train I don’t spend half the ride saying “oh my god this is incredible, big thanks to whoever invented the wheel. So smooth!”

Even though maybe I should :)

Re: LLMs tell bad jokes because they avoid surprises

#103

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.)

This is the weirdest conversation about a joke that is definitely making its target audience laugh -- as a comedian, I say that's the only honest measure of a joke. But allow me to analyze the shit out of this, because the only thing funnier than a groaner is meticulously explaining the groaner.

It's at least as funny as "why did the chicken cross the road," which is only a joke inasmuch the punchline is merely a statement of the obvious in the framing of a joke (the surprise is that the punchline sucks -- making it a groaner). I submit that that chicken/road joke wouldn't stick around if it wasn't funny. So, this joke stands on the shoulders of the chicken/road joke, making the obviousness that much funnier within the shared cultural context. Moreover, it adds a layer of absurdity (imagine the literal sun climbing a tree) with a linguistic confusion (aka pun) as we do refer to the sun "climbing" the sky. And finally: for some reason, our culture is more tolerant of groaners from "dads," so much so that some call them "dad jokes." Your child has inverted age and gender norms with this joke, making it so incredibly funny that you are blinded to the truth: this is comedy gold. Watch that kid, she's going somewhere. It might be an open mic night at a skeezy comedy club.

Re: LLMs tell bad jokes because they avoid surprises

#104
I don’t think there’s a single reason LLMs aren’t good at journalism, but this explanation seems like a secondary factor at best. I mean, some journalism isn’t surprising at all but the confirmation the expected thing happened and exactly how it happened is useful.

Re: LLMs tell bad jokes because they avoid surprises

#105
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?

Just because you're bright doesn't mean you can't fall for a sap

Re: LLMs tell bad jokes because they avoid surprises

#106
post #100

> When you ask an LLM to tell a joke, the LLM is guessing what joke a majority of people would find funny. The result is almost never funny. This is... false. The LLM is generating text that would be associated with "being a joke" in its corpus. It doesn't know what "funny" or "majority of people" means.

You're forgetting about RLHF.

Many of us forget that an LLM without RLHF would not respond how we think.

Re: LLMs tell bad jokes because they avoid surprises

#107
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?

The closest I can think of right now is the "Before & After" category from Wheel of Fortune. It relies on there being a single word that ends one phrase and begins another.

But that doesn't bring into the idea of this word being _cutting_

Re: LLMs tell bad jokes because they avoid surprises

#108

Earlier quoted context omitted.

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.)

This is the weirdest conversation about a joke that is definitely making its target audience laugh -- as a comedian, I say that's the only honest measure of a joke. But allow me to analyze the shit out of this, because the only thing funnier than a groaner is meticulously explaining the groaner. It's at least as funny as "why did the chicken cross the road," which is only a joke inasmuch the punchline is merely a sta…

Why did the chicken cross the road? is funny because the chicken is going to die. I'm not seeing the double entendre with this tree joke.

Re: LLMs tell bad jokes because they avoid surprises

#110
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?

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 find the incongruity model of humor to be funny and the joke itself makes it very difficult to be applied to other potentially funny approaches.

Also on AI and humor... https://archive.org/details/societyofmind00marv/page/278/mod...

In another "ok, incongruity isn't funny - try puns" approach... https://chatgpt.com/share/68a20eba-b7c0-8011-8644-a7fceacc5d... I suspect a variant of "It couldn't stand being grounded" is probably the one that made me chuckle the most in this exploration.

Post reply on HN