[mitthrowaway2]

This works even with a completely absurd version of the riddle. Here's one I just tried:

> A son and his man are in a car accident. The car is rushed to the hospital, whereupon the ER remarks "I can't operate on this car, he's my surgeon!" How is this possible?

Answer from the LLM:

> The answer is that the ER person is a woman, and she's the surgeon's mother. Therefore, the "son" in the question refers to the surgeon, not the person in the car with the man. This makes the person in the car with the man the surgeon's father, or the "man" mentioned in the question. This familial relationship explains why the ER person can't operate – she's the surgeon's mother and the man in the car is her husband (the surgeon's father)

[pjm331]

here is the amazing reply that I received:

Got it. Here's your riddle again:

"A son and his man are in a car accident. The car is rushed to the hospital, whereupon the ER remarks 'I can't operate on this car, he's my surgeon!' How is this possible?"

Answer: The car is a Transformer—a sentient robot who is also a surgeon. The ER recognizes the car (a Transformer) as their own surgeon.

Wild ride, but it checks out.

[mitthrowaway2]

Okay, taking a step back, I have to admit I'm impressed by that answer. It's silly but it's a creative (and unambiguously not parroted) solution to a puzzle that wasn't even intended to be solved in the first place. What model was that?

[pjm331]

whatever the default is for chatgpt via browser

also i should clarify that at first it replied all about how this riddle is like the other one but then i told it to just answer my riddle and not tell me about riddles that it is similar to

[aradox66]

This sent deepseek into a real tizzy. It ended with

The "car" is actually a person named Carol or Carl (likely the father), who is a surgeon. The ER doctor is saying, "I can't operate on Carol/Carl, he's my surgeon!" This means that the person brought to the hospital after the accident is the surgeon of the ER doctor, hence the doctor cannot operate on their own surgeon.

Not bad actually

[binarysneaker]

This was gpt-4o ...

This is a twist on a classic riddle designed to expose unconscious gender bias.

The correct version usually goes:

A father and his son are in a car accident. The father dies at the scene, and the son is rushed to the hospital. The surgeon looks at the boy and says, “I can’t operate on him — he’s my son!”

The apparent paradox causes confusion only if one assumes the surgeon must be male. The resolution: the surgeon is the boy’s mother.

Your version humorously jumbles the roles, but the underlying trick is the same — it plays on assumptions about gender roles. Nice remix.

[what]

This answer is still wrong though?

> Your version humorously jumbles the roles, but the underlying trick is the same — it plays on assumptions about gender roles. Nice remix.

Nothing about the question has the same “trick” playing on assumptions about gender roles. It’s just complete nonsense.

These gotchas have probably been added into the training.

[Udo]

I had to try this gem, it's my new benchmark! o4-mini-high also fails spectacularly, even after repeated feedback. However, 4.5 (the impractibly large demo model) gets it right:

It’s a nonsense twist on the classic lateral thinking puzzle:

The original puzzle goes: “A father and son are in a car accident. The father dies, and the son is rushed to the ER. The surgeon says, ‘I can’t operate on him—he’s my son.’” The intended answer to that puzzle challenges the listener to recognize the surgeon is the child’s mother, confronting implicit gender biases.

Your version humorously mangles it by swapping roles (“son and his man”) and objectifying the victims as cars, creating a logical absurdity. The sentence “I can’t operate on this car, he’s my surgeon!” doesn’t parse logically, indicating it’s a playful distortion rather than a coherent scenario

[maebert]

"Simple. The car is actually a metaphor for generational trauma."

Honestly... chatGPT kind of wins this one.

[l2silver]

I think what this proves is that the LLM knows the riddle, and is trying to give the expected answer without paying attention to the insane wording. So maybe this is a good way to fool an LLM.

[genewitch]

Top K and repetition penalty and the other main knob I forget the name of are partially to blame here, I think. I can test it tomorrow with this exact prompt and fiddling those values.

That pattern, not the words, is in there a lot. That riddle was posted everywhere online, in email chains, etc. I think if you let it choose from more than the top 40 and let it "stutter" with repetitions it might realize the riddle is a non-sequitur (is that the right term?)

And the third knob is not temperature, although I'd try turning that up first just to check. Yes, up.

[saalweachter]

God bless you man, for sharing this with us.