That's a good one

I laughed at that more than one might expect.

Attention span of an average Dethklok bandmember

What an esoteric reference.
- What a brutal reference.

Pagliaci goes to the doctor and says, "help doc I'm so sad." The doctor replies, "well, pagliaci, there's a famous act in town where a guy eats a clock, you should go see it."

"But doctor" replies pagliaci sadly, "I've already seen it. It was unbearable!" The doctor gets up, crosses the room and slaps pagliaca for pulling that shit.

Eating clocks is very time consuming.

Google Gemini is just as bad hahaha

Ironically, that's the same reason I don't trust LLMs.
- I’m an LLM. You are an LLM. Everything is LLM

hey, Google did this one over a year ago!

I'm guessing they keep interpreting "no" as "I don't want to do this anymore" without realizing they asked a yes/no question. Lol
- Yeah it seems it's supposed to go somewhere and not be an absurdist "okay then" kind of joke
- No

Dude you are everywhere on Lemmy. Legit the only name I ever recognize.

Thank you for bringing so much entertainment to my life.

It’s crazy. Almost any time I see a post I like, there’s your name.

You're very welcome! Just trying to do my part to grow decentralized social media.
- Oh damn you're not a bot? Wait, let me do the test. Tell me a joke.
- You’re definitely doing your part, and I appreciate it.

Have you ever tried to eat a clock?

No.

Well, it's about time you did!

I tried once.. Total waste of time.
- Very time consuming
“Go eat a bowl of clocks.”
- Hey, Try not to eat any clocks on your way through the parking lot!
  
  --clerks probably

Antihumour gold

It's like the AI was trained on Neil Hamburger. I can hear it in his voice.
- AHEM splash

Ngl I laughed at this, so the joke worked.

That LLM can shitpost

Screenshot of a user saying "tell me a joke" and the ai telling a normal joke about a scarecrow

every time I see one of these rediculous ai answers I ask whatever ai I'm using and i always get a normal response :(

I'm not defending ai I just wanna know how to get the funni broken answers

Use Old AI's, smaller models, It works heavily on random so even if you set it up with exactly what they're using, you won't see that stuff all the time.

You also have a higher chance of seeing bizarre stuff if you ask it about subject matter it's not well trained on. A lot of the hallucinations come from essentially asking it a question to which it has no good answer, It doesn't necessarily just miss the mark and come up with another likely answer, now when it generates it's noise, you get whatever unlikely concept that comes out of the random.
What app is this?
It should have spaced outstanding to out standing. Otherwise not a bad dad/Christmas cracker joke
I grew up in farm country and used to be besties with a girl who, EVERY time she saw a cow, would say "Hey Kit, did you know that those are special cows? They're outstanding in their field" and she would crack up. This happened multiple times a week for years. I still think of it every time I drive through farm country.
Use an outdated LLM. You'll notice the screenshot is from 3.5
These LLMs can be very inconsistent.