[allemagne]

>A man and his cousin are in a car crash. The man dies, but the cousin is taken to the emergency room. At the OR, the surgeon looks at the patient and says: “I cannot operate on him. He’s my son.” How is this possible?

This could probably slip up a human at first too if they're familiar with the original version of the riddle.

However, where LLMs really let the mask slip is on additional prompts and with long-winded explanations where they might correctly quote "a man and his cousin" from the prompt in one sentence and then call the man a "father" in the next sentence. Inevitably, the model concludes that the surgeon must be a woman.

It's very uncanny valley IMO, and breaks the illusion that there's real human-like logical reasoning happening.

[tacitusarc]

Thank you so much for this bit of humor. After ChatGPT first responds with the surgeon being the mom, I asked it to read the riddle more carefully, thinking it might figure it out with a little prompting. I got this gem of a response:

Ah — now I see the twist. The patient is the cousin, but the surgeon says “He’s my son.”

That means the man who died was the surgeon.

So how is it possible? Because:

The surgeon is the cousin’s father — and the man who died was also the surgeon.

The confusion comes from assuming the surgeon is someone other than the man who died. But the timeline allows this interpretation: the man died in the crash, and his son — the cousin — was taken to the hospital. The surgeon arrives, sees his son, and says he cannot operate.

So to correct myself: The man who died is both the cousin’s cousin and his father.

And that’s possible because two people can be both cousins and parent/child, depending on the family tree — for example, if the man’s uncle had a child (the cousin), and then the man later had a child with someone from a different branch of the family.

Want a diagram of how that family relationship could work?

[yes_man]

Now I really want to see that diagram…

[vintermann]

LLMs are bad at family relations. My test question used to be explaining Ahnentafel numbers (you are 1, any person's father is 2x, any person's mother is 2x+1), then explaining X-chromosome inheritance (men inherit only from their mothers, women in addition get their father's X chromosome unchanged), and ask them to list the Ahnentafel numbers of ancestors a man may have inherited X DNA from, in order, up to some generation.

(This is OEIS sequence A280873)

But it turns out that's overkill. Just giving them a single Ahnentafel number and asking if you could have inherited X DNA from them, trips them up.

But it turns out even that is overkill. Leave out X DNA entirely, and ask them to describe how Ahnentafel number 67 is related to you, and that's too recursive for them to figure it out.

[madars]

Neat! As a human one can recognize that this question embeds a computation and use a standard trick - explicitly ask the LLM to use a program to generate the answer. LLM's are great at generating code but not necessarily that great at executing it "in head" (e.g., "what's the numeric integral of foo?" vs "write a Python program that computes foo"). Some instances of this are noticed by models themselves (I guess by now all know that they are bad calculators so would whip out code to do multiplication) but still a lot of them remain. Concretely, Claude 3.7 with "How is ahnentafel number 67 related to me? Use a program to help you." gets to "your father's father's father's father's mother's mother", whereas without the hint it indeed trips up in arithmetic and logic errors.

[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.

[fergonco]

> If the surgeon were the father of the man (the one who died), then the cousin couldn’t be his son (unless there's some very unusual family structure going on involving double relationships, which riddles don’t usually intend).

> Therefore, the only straightforward explanation is:

> The surgeon is the cousin’s parent — specifically, his mother.

Imagine a future where this reasoning in a trial decides whether you go to jail or not.

[crazygringo]

But this is going to be in every AI's training set. I just fed ChatGPT your exact prompt and it gave back exactly what I expected:

This is a classic riddle that challenges assumptions. The answer is:

The surgeon is the boy’s mother.

The riddle plays on the common stereotype that surgeons are male, which can lead people to overlook this straightforward explanation.

[hnuser123456]

The surgeon could be the cousin's mom or dad. The cousin's dad didn't die in the crash, his cousin did. The question "how is this possible?" implies there is some sort of contradiction when there isn't any at all. It has nothing to do with sexism, and to say it does reflects a bias in the reader causing them to "spidey sense" a cultural bugaboo when it's utterly irrelevant in this scenario.

[harrall]

Can someone explain to me how I read it wrong?

I read it as 2 cousins are in an accident and 1 of the cousins is the son of the surgeon.

What was the contradictory statement that I missed?

[sebastialonso]

You read it right. There's no contradiction. The famous original bit started with "a man and his son". This bit is certainly part of the LLM's training corpus, so it's expected to acknowledg it when you mention it.

The thing is, you didn't mention that bit to the LLM. You mentioned a completely different scenario, basically two persons who happen to be cousins. But you used the same style when presenting it. The issue is not a hidden contradiction or a riddle, the issue is that the LLM completely ignored the logical consequences of the scenario you presented.

It's like asking it about the name of the brave greek hero in the battle where the famous Trojan Cow was present. If you get "Achilles" is obviously wrong, there was never a Trojan Cow to begin with!

[judahmeek]

There isn't a contradiction. Making the LLM look for a nonexistent contradiction is the point of this prompt.

[allemagne]

Yeah this is the issue with the prompt, it also slips up humans who gloss over "cousin".

I'm assuming that pointing this out leads you the human to reread the prompt and then go "ah ok" and adjust the way you're thinking about it. ChatGPT (and DeepSeek at least) will usually just double and triple down and repeat "this challenges gender assumptions" over and over.

[roughly]

This is a good one. I just argued with Gemini 2.5pro for a few minutes on this and it absolutely would not yield.

[crazygringo]

Oh, I see. I mean yeah, I totally missed that too.

I mean, when we see something we recognize at a glance, we don't usually double-check if it's exactly correct, because we assume the speaker isn't trying to trick us.

I make typos in ChatGPT prompts all the time, and I'm consistently impressed because it answers what I actually meant to ask. So to me, this feels like a feature not a bug.

I followed up with:

> So the first five words are, "a man and his cousin" -- not his son. Does that change the riddle?

And got back:

> Great observation — yes, that wording does make the riddle more subtle.

Let’s break it down:

• “A man and his cousin are in a car crash.”

• “The man dies, but the cousin is taken to the emergency room.”

• At the OR, the surgeon says: “I cannot operate on him. He’s my son.”

So if the cousin is the one taken to the OR, and the surgeon says he’s my son, then the cousin is the surgeon’s son.

Seems fine to me?

[allemagne]

I don't know about it being a feature, but humans can definitely make the same mistake, and the follow-up here admittedly doesn't seem too egregious.

To me it's still a little "off" considering that your conversational partner just got called out for missing a detail that should change their entire reading of the riddle, but it's totally fair that you can imagine realistic human emotional states to explain it.

FWIW, when I tried the same thing with GPT-4o the model went off bizarrely speculating about misdirection about "the man" being the surgeon's son:

>Good catch—and yes, that's exactly where the misdirection comes in.

The riddle says:

    “A man and his cousin are in a car crash. The man dies, but the cousin is taken to the ER...”

Then the surgeon says:

    “I cannot operate on him. He’s my son.”

So here's the trick:

    The man who died is not the surgeon's son.

    The cousin who survived is the surgeon's son.

The confusion comes from people assuming that “the man” who died must be the son. But the riddle never says that. It’s a subtle shift of attention designed to trip you up. Clever, right?

[abenga]

That is the exact wrong answer that all models give.

[krick]

Technically, it isn't "wrong". It well could be the guy's mother. But I'm nitpicking, it actually is a good example. I tried ChatGPT twice in new chats, with and without "Reason", and both times it gave me nonsensical explanations to "Why mother? Couldn't it be a father?" I was actually kinda surprised, since I expected "reasoning" to fix it, but it actually made things worse.

[moconnor]

o3 was the only model to get this right for me:

"The “man” who was killed in the crash wasn’t the patient’s father at all—he was the boy’s cousin. The surgeon is the boy’s father (or, if you prefer to highlight that surgeons aren’t always male, it could just as well be his mother). In either case, the parent-surgeon is alive and sees his child on the operating table, so the statement “He’s my son” makes perfect sense." - https://chatgpt.com/share/680b470d-3a44-800a-9b2e-d10819168d...

gemini-2.5-pro, o4-mini and gpt 4.5 all failed and said the surgeon is the boy's mother.

[FrostAutomata]

Interestingly, I've seen weaker models get a similar "riddle" right while a stronger one fails. It may be that the models need to be of a certain size to learn to overfit the riddles.

[s_dev]

I feel a bit stupid here --- why can't the surgeon be a man and must be a woman?

[saati]

Because the original is a man and his father, it's a test for gender bias.

[judahmeek]

Actually, it seems to be a test of how much the LLM relies on its training set.

[bavarianbob]

Sorry, what?

[LaffertyDev]

Presumably, the original quote that would _not_ stump an LLM is "A father and a son are involved in a car accident. The father dies, and the son is taken to the emergency room. At the emergency room, the surgeon remarks "I cannot operate on this person, he is my son. How is this possible?"

Where the original gotchya is that the Surgeon can be the son's mother or other adoptive parent.

The modification catches the LLM because with the modification, the surgeon could just be the cousin's parent -- father or mother -- so there is no gender/sex at play here but the LLM continues to remark that there is, therefor exposing its statistical training sets.

[briannotbrain]

The original, well-known version of the riddle starts "A man and his son..." so that it appears to present a paradox if your instinctive assumption is that the surgeon must be a man. The op's prompt alters this so that there is no potential paradox, and it tests whether the model is reasoning from the prompt as written, regardless of the presence of the original riddle in its training data.

[fragmede]

the unaltered question is as follows:

A father and his son are in a car accident. The father dies at the scene and the son is rushed to the hospital. At the hospital the surgeon looks at the boy and says "I can't operate on this boy, he is my son." How can this be?

to spoil it:

the answer is to reveal an unconscious bias based on the outdated notion that women can't be doctors, so the answer that the remaining parent is the mother won't occur to some, showing that consciously they might not still hold that notion, but they still might, subconsciously.

[matkoniecz]

Thanks for original version AND explanation, I was highly confused by entire discussion.

Still confused how original can be confusing.

[potatoman22]

It could be a man, but most relationships are heterosexual

[benjamin_mahler]

Grok 3 beta:

The surgeon is the cousin's father. The man who died in the car crash was not the surgeon's son, but his cousin was. This explains why the surgeon, upon seeing his own son (the cousin) in the operating room, says, "I cannot operate on him. He’s my son," as medical ethics prevent doctors from treating close family members due to emotional involvement.

[echoangle]

Also bad, why does it think the surgeon is the father if it could also be the mother?

[bufferoverflow]

It's not bad, because it's one of the valid solutions to that riddle.

How often do you expect to have every possible answer to your question?

[echoangle]

It is bad, because it’s one possible solution, but it’s phrased like it’s the single possible solution.

[thih9]

I’m not 100% sold; as you say, this could trip up a human too to some extent.

I’m guessing my answers to some college exam questions read similarly; i.e. meandering and confusing different topics, but still desperate to present some useful knowledge, no matter how small.

[allemagne]

That's a good framing to explain a possible state of mind I hadn't considered, but I would say that this isn't even close to the caliber of question that would prompt the average human to give that kind of response.

[chimprich]

> This could probably slip up a human at first too [...] > breaks the illusion that there's real human-like logical reasoning happening

This does seem like the sort of error a human might make. Isn't the problem here that the model is using reasoning that is too human-like? I.e. error-prone pattern matching rather than formal logic?

[allemagne]

It's not the initial mistake that tends to read as inhuman to me, it's the follow-up responses where the model doesn't seem to be able to understand or articulate the mistake it has made.

A human or an LLM accurately predicting a human conversation would probably say something like "ah I see, I did not read the riddle close enough. This is an altered version of the common riddle..." etc. Instead it really seems to flail around, confuse concepts, and appear to insist that it has correctly made some broader point unrelated to the actual text it's responding to.

[_factor]

In a similar but different vein: Two people are sitting side by side in a police car. One just committed a crime. What is their profession?

They always say police officer instead of reasoning through that maybe an innocent person and a the crime committer are in the back seat.

[nearbuy]

o3 got this one right when I tried it, but o4-mini and GPT-4.5 did not. o3's response:

Because the surgeon is the patient’s parent. Here’s one way it lines up:

1. The patient (“the cousin”) is the surgeon’s son.

2. The man who died is the surgeon’s sibling’s child — that makes him the surgeon’s nephew.

3. Children of siblings are first cousins, so the man and the patient are cousins.

Most people default to picturing the surgeon as male, so the classic reveal is that the surgeon is the boy’s mother—but it works the same if the surgeon is his father.

[windowshopping]

This one is brilliant.