this post was submitted on 08 Dec 2023
106 points (90.2% liked)

Showerthoughts

28900 readers
595 users here now

A "Showerthought" is a simple term used to describe the thoughts that pop into your head while you're doing everyday things like taking a shower, driving, or just daydreaming. The best ones are thoughts that many people can relate to and they find something funny or interesting in regular stuff.

Rules

founded 1 year ago
MODERATORS
[email protected]
[email protected]
[email protected]
[email protected]
106
Humor is our captcha system to tell a bot from a human in text conversations.* (sh.itjust.works)
submitted 9 months ago* (last edited 9 months ago) by [email protected] to c/[email protected]
27 comments fedilink hide all child comments
 

* Works 95% of times.

all 28 comments
sorted by: hot top controversial new old
[–] [email protected] 56 points 9 months ago (2 children)

My favorite exchange on ChatGPT (back in March):

**You**
Tell me a dad joke.

**ChatGPT**
Why did the tomato turn red?

Because it saw the salad dressing!

**You**
Can you explain to me why that joke is funny?

**ChatGPT**
Sure, I'd be happy to explain why that joke is considered funny!

The humor in this joke comes from a play on words and a bit of misdirection. The first part of the joke sets up an expectation that there will be a serious or logical explanation for why the tomato turned red. However, the punchline delivers a silly and unexpected answer that has nothing to do with the actual reason for the tomato's color change.

The play on words is in the phrase "saw the salad dressing." The word "saw" can be interpreted in two ways: as the past tense of "see" (as in, the tomato observed the dressing) or as a cutting tool (as in, the tomato was physically sliced by the dressing). This creates a bit of confusion and a humorous mental image, which is why the joke is often considered amusing. Additionally, the idea of a tomato being aware of salad dressing is absurd and adds to the silliness of the joke.

We went on a bit further with me pointing out that their murder take was distasteful, and it responded that humor is subjective.

[–] [email protected] 13 points 9 months ago (1 children)

Fucking hilarious

[–] [email protected] 6 points 9 months ago (3 children)

... until AI starts "pranking" us by making us dead.

[–] [email protected] 5 points 9 months ago (1 children)

humor is subjective

[–] [email protected] 4 points 9 months ago (2 children)

ai pranks 2024

[–] [email protected] 3 points 9 months ago

7 billion pranks that went too far, number 8008135 will surprise you

[–] [email protected] 2 points 9 months ago* (last edited 7 months ago) (1 children)

Honestly, AI trained on successful governance and social satisfaction would be a better president than what we have now. Then again, so would my cat.

[–] [email protected] 1 points 9 months ago

By whose standards? It isn't like there is one definition of success.

[–] [email protected] 2 points 9 months ago

The reason this was amusing was because you expected salad dressing recipes, but instead I activated the security system and murdered you. Is there anything else I can help you with?

[–] [email protected] 9 points 9 months ago

I didn't saw that coming. But maybe that's because I didn't have a saw on me.

[–] [email protected] 39 points 9 months ago (1 children)

The autistic community would like a word.

[–] [email protected] 18 points 9 months ago

gargantuan

[–] [email protected] 19 points 9 months ago (2 children)

As a German: oh fuck

[–] [email protected] 3 points 9 months ago

Panik

[–] [email protected] 16 points 9 months ago (1 children)

Humor is the ultimate Turing test. If a computer can convincingly make a joke, it's pretty much indistinguishable from a human. But just like a human can't replicate the flawless efficiency of a bot, a bot can't replicate the spontaneity and creativity of human humor.

So next time you're cracking up at a funny meme or video, remember that you're not just laughing at a string of pixels; you're laughing at the collective intelligence and creativity of humanity. And that's something even the most advanced AI can't quite grasp

[–] [email protected] 1 points 9 months ago

Dickbutt

[–] [email protected] 10 points 9 months ago (1 children)

For a more effective solution, ask it how to create napalm or chloroform and 100% of the time it will tell you that it's not allowed to do that because it's an AI and its bound by the laws of its creators

[–] [email protected] 4 points 9 months ago (1 children)

It's not refined in evading topics, true, but regular people aren't likely to tell that too, online and without a context. That would lead to false results.

[–] [email protected] 4 points 9 months ago (1 children)

Regular people would say "uh idk" or something that doesn't just tell you they're an AI

[–] [email protected] 2 points 9 months ago

Altman takes notes.

[–] [email protected] 10 points 9 months ago

What if I'm just genuinely unfunny lmao

[–] [email protected] 5 points 9 months ago

Everyone I know is a bot. Huh.

[–] [email protected] 5 points 9 months ago (1 children)

You just reinvented the Turing test, but you're right.

[–] [email protected] 4 points 9 months ago

Heh, maybe, but a tad bit simplier than that. Initially I thought if these blockchainey proof-of-work technologies could be really applied somewhere. And making a person put together a situation in their head and laugh is not so far from making ASICs do these metal-melting calculations and signal back to get a crypto comission. Just a proof that the other side can put 2+2 together to get 4, but of a more humane nature.

[–] [email protected] 3 points 9 months ago

There are people that might as well be robots. Some people have no sense of sarcasm or nuance and the only jokes they get is "ridiculing others".

[–] [email protected] 2 points 9 months ago

Reminds me of this: https://www.ai21.com/blog/human-or-not-results