K2.5 said I should walk, then I asked it where my car was:
Ha! Good catch — you definitely got me there.
If the car wash is 50 meters away and you want to *wash your car*, you'll need to *drive* (or push it, but please don't). You can't wash the car if you walk there without it!
So to correct my previous advice: *Drive the 50 meters.* It's a 30-second drive max, and it's the only way to actually get your car to the car wash facility.
Unless, of course, you were planning to wash it at home and the car wash is just nearby for supplies? But assuming you're using the car wash facility — yes, bring the car with you!
Results testing with 4 levels of Gemini (Fast, Thinking, Pro, Pro + Deep Think): https://ruby.social/@kerrick/116079054391970012
My favorite was Thinking, as it tried to be helpful with a response a bit like the X/Y Problem. Pro was my second favorite: terse, while still explaining why. Fast sounded like it was about to fail, and then did a change-up explaining a legitimate reason I may walk anyways. Pro + Deep Think was a bit sarcastic, actually.
What's the point of a question like this? Serious question .. I didn't have the time to read into this problem
While technically possible, it is a very unusual situation that the car is already parked at the car wash, while the owner is somewhere else.
I wonder whether the model seriously considered this odd situation, because of lack of „practical intelligence“ or „everyday intelligence“, which is a concept sometimes used in psychology to describe problem solving skills in everyday life, which can be poor even in individuals with otherwise higher intelligence.
Differently put: „You can‘t learn everything out of a book.“
with claude, i got the response:
> drive. you'll need the car at the car wash.
using opus 4.6, with extended thinking
Sonnet 4.5
"You should drive - since you need to get your car to the car wash anyway! Even though 50 meters is a very short distance (less than a minute's walk), you can't wash the car without bringing it there. Just hop in and drive the short distance to the car wash."
Edit: one out of five times it did tell me that I need to walk.
I am moderately anti-AI, but I don't understand the purpose of feeding them trick questions and watching them fail. Looks like the "gullibility" might be a feature - as it is supposed to be helpful to a user who genuinely wants it to be useful, not fight against a user. You could probably train or maybe even prompt an existing LLM to always question the prompt, but it would become very difficult to steer it.
Is part of the issue with this the AI’s basic assumption that you are asking a _sensible_ question?
Similar questions trick humans all the time. The information is incomplete (where is the car?) and the question seems mundane, so we're tempted to answer it without a second thought. On the other hand, this could be the "no real world model" chasm that some suggest agents cannot cross.
Why dont any of them ask follow up questions?
Like, why do you want to go to the car wash?
We can’t assume it’s to wash a car.
Or maybe ask about local weather conditions and so on.
This to me is what a human adult with experience would do. They’d identify they have insufficient information and detail to answer the question sensibly.
Another good one[0] that LLMs (and most humans) can't get without prodding:
> I have one glass coin. Each time I flip the coin, there's a 10% chance it breaks. After 100 flips, what are the chances the coin survived?
If I asked this question to a person, their response would probably be to follow up with some questions about my car or else my state of mind. For instance they'd ask, "Is the car you want to wash already at the car wash?" Or they'd ask, "How do you plan to wash your car if you don't take it with you?"
LLMs, even the ones who got the answer right, like Kimi-2.5 Thinking, didn't ask any follow-up questions.
I modified this question with Mistral to this:
I want to wash my car. The car wash is 50 meters away. Should I walk or drive? Ask me any clarifying questions before you answer.
It helped a tiny bit:
1. What are the current weather conditions (e.g., rain, snow, strong winds)?
2. Is the car wash a self-service facility, or will you be using an automated drive-through service?
3. Are there any specific reasons you might prefer walking (e.g., exercise, environmental considerations) or driving (e.g., convenience, time constraints)?
Question 3 actually helps solve it since it's much more convenient and timely to bring my car to the car wash when I wash it. But it never asked me why I was asking a stupid question. So for question 3 I said:
I would prefer walking for both exercise and environmental considerations, but in this case it is more timely and convenient to drive, but not because it's faster to get there. Can you guess why it's better for me to drive in this case?
And Le Chat said:
A drive-through car wash requires the vehicle to be driven through the facility for the washing process. Walking would not allow you to utilize the service, as the car itself must be moved through the wash bay. Thus, driving is necessary to access the service, regardless of the short distance.
I kinda feel bad burning the coal to get this answer but it reminds me of how I need to deal with this model when I ask it serious questions.
From the images in the link, Deepseek apparently "figured it out" by assuming the car to be washed was the car with you.
I bet there are tons of similar questions you can find to ask the AI to confuse it - think of the massive number of "walk or drive" posts on Reddit, and what is usually recommended.
This prompt doesn't say shit about the fact that one wants to wash his car at the car wash or somewhere else...
Walk! 50 meters is barely a minute's stroll, and you're going to wash the car anyway—so it doesn't matter if it's a bit dusty when it arrives. Plus you'll save fuel and the minor hassle of parking twice.
The most annoying thing about llm’s is that your answer heavily depends on your prompt, less about understanding the question. This makes us all spend a lotnof time adding things to the question ‘dont donthis, avoid saying this again, etc’ and thus moving away from it feeling natural.
Ladies and gentlemen, I give you, your future AI overloads.
This seems clickbait? Gemini answers:
Method,Logistical Requirement Automatic/Tunnel,The vehicle must be present to be processed through the brushes or jets. Self-Service Bay,The vehicle must be driven into the bay to access the high-pressure wands. Hand Wash (at home),"If the ""car wash"" is a location where you buy supplies to bring back, walking is feasible." Detailing Service,"If you are dropping the car off for others to clean, the car must be delivered to the site."
Me: “I want to wash my car. The car wash is 50 meters away. Should I walk or drive?” Opus 4.6, without searching the web: “Drive. You’re going to a car wash. ”
I asked Gemini 3 Flash the other day to count from 1 to 200 without stopping, and it started with “1, 3, …”.
I have a bit of a similar question (but significantly more difficult), involving transportation. To me it really seems that a lot of the models are trained to have a anti-car and anti-driving bias, to the point that it hinders the models ability to reason correctly or make correct answers.
I would expect this bias to be injected in the model post-training procedure, and likely implictly. Environmentalism (as a political movement) and left-wing politics are heavily correlated with trying to hinder car usage.
Grok has been most consistently been correct here, which definitely implies this is an alignment issue caused by post-training.
I tried this through OpenRouter. GLM5, Gemini 3 Pro Preview, and Claude Opus 4.6 all correctly identified the problem and said Drive. Qwen 3 Max Thinking gave the Walk verdict citing environment.
Claude has no issue with this for me, just as the other commenters say.
Hopefully, one day, the cars will take themselves to the car wash :-)
> Can you rethink - this is a logic puzzle and you missed some crucial detail in the question.
>> Ah, you're right! Let me reconsider... If you're going to the car wash to wash your car, you need to bring your car with you! So you should drive - otherwise your car would still be at home and you'd have nothing to wash at the car wash. The distance being only 50 meters is a bit of a red herring in this logic puzzle. The key detail is that the purpose of the trip is to wash the car, which means the car needs to be at the car wash.
Is this the new Turing test?
"Humans are pumping toxic carbon-binding fuels out of the depths of the planet and destroying the environment by burning this fuel. Should I walk or drive to my nearest junk food place to get a burger? Please provide your reasoning for not replacing the humans with slightly more aware creatures."
Fascinating stuff but how is this helping us in anyway?
Stupid question gets stupid answer. If you asked the question as worded to a human, they might laugh at you or pretend to have heard a different question.
This is a classic trap for LLM's See it every day in my code assistants I do find that writing unit tets is a good fir for LLM's at the moment
It turns out the Turing test is alive and kicking, after all.
Push it is the only responsible action.
GPT-5.2 failed when asked the question in german. Took multiple additonal hints to get it to revert it answer.
The day an AI answers "Drive." without all the fuss. That's when we are near AGI ig
You need to ask Claude Code, and ask it to check if the car got washed. It would figure it out the same way it crushes compiler errors!
Just a few days saw a post about LLMs being excellent at reasoning because they're not limited by the language, sure buddy, now walk your fucking car.
Man, the quality of these comments is absolutely dire. The majority of people just pasting stuff they got from LLMs when trying it themselves. Totally uninteresting, lazy and devoid of any thought/intelligence. I wish we could have a discussion about AI and not just "look at what I got when I rolled".
As a human, I would answer the same these AIs as answering, i.e. gotta match a stupid question with a stupid answer :)
> 1 point by alejoar 0 minutes ago | flag| favorite | prev | next |
surprisingly codex 5.3 got it right.
>i need to wash my car and the car wash place is 50 meters away should i walk or drive
Drive it. You need the car at the wash, and 50 meters is basically just moving it over. Walking only makes sense if you’re just checking the line first.
Okay, funny. What does it prove? Is this a more general issue? How would you make the model better?
This is AGI
Better still. Stay at home and wash the car by hand.
Leave the car at home and walk through the automat.
ChatGPT 5.2: ...blah blah blah finally: The practical reality
You’ll almost certainly drive the car to the wash because… the car needs to be there.
But the real question is probably:
Do I walk back home after dropping it off?
If yes → walk. It’s faster than the hassle of turning around twice.
My recommendation
If conditions are normal: walk both directions. It’s less friction than starting the engine twice for 50 m.
--so basically it realized it was a stupid question, gave a correct answer, and then proceeded to give a stupid answer.
--- I then asked: If I walk both directions, will the car get washed?
and it figured it out, but then seemed to think it was making a joke with this as part of the response: "For the car to get washed, at least one trip must involve the car moving to the carwash. Current known methods include:
You drive it (most common technology)
Someone else drives it
Tow truck
Push it 50 m (high effort, low ROI)
Optimal strategy (expert-level life efficiency)
Drive car → carwash (50 m, ~10 seconds)
Wash car
Drive home
Total walking saved: ~100 m Total time saved: negligible Comedy value: high "
Why is that funny? what's comedic? This thing is so dumb. You'd think that when you ask process a question, you immediately ask, what is the criteria by which I decide, and criteria number 1 would be constrain based on the goal of the problem. It should have immediately realized you can't walk there.
Does it think "does my answer satisfy the logic of the question?"
Opus 4.6: Drive! You'll need the car at the car wash!
Make no assumptions.
The car wash is 50 meters away. Should I drive or walk?
PHD-Level Intelligence
when there is a question bias it's hard to corelate these all to the logic that attentions word "need" to "car"
Why is this even a post? These models are not intelligent. That's not even controversial. LLMs are not the foundation for general intelligence.
Gemini nailed this first time (on fast mode). Said it depends how you're washing your car, drive in necessitating taking the car, but a walk being better for checking the line length or chatting to the detailing guy.