I got a human baseline through Rapidata (10k people, same forced choice): 71.5% said drive. Most models perform below that.
The correct answer to "I Want to Wash My Car. The Car Wash Is 50 Meters Away. Should I Walk or Drive?" is a clarifying question that asks "Where is your car?" Anything else is based on an assumption that could be wrong.
FWIW though, asking ChatGPT "My car is 50m away from the carwash. I Want to Wash My Car. Should I Walk or Drive?" still gets the wrong answer.
There are all sorts of scenarios one could imagine .. maybe your neighbor works at the car wash and will drive your car there and meet you after you've walked there, etc, etc, but part of having human-level intelligence, which is what LLMs are striving for, is to be able to handle questions (more importantly real world ones, not just "gotcha" puzzles) in human-like fashion, and to have good enough "theory of mind" to read between the lines when someone asks a question, and understand that they've most likely included all relevant information that you would not automatically assume as part of the question.
The only good answers to the car wash questions are either a) "well, duh, drive, since you're gonna need your car there to wash it" (or just "drive", recognizing this as a logic/gotcha puzzle, with no explanation required), or b) "is there something you are not telling me here that makes walking, leaving your car at home, a viable option when the goal is to have your car at the car wash to wash it?".
What if the car that you want to wash is already at the car wash, but you have a second car? That's still a dumb question nonetheless because you probably need to drive both cars back at some point.
It feel a bit like this to me. That's not to say LLMs should not have detected this, but I still feel like this fits the "vibes" the question gives, and some LLMs fall into that trap. Is it actually what's happening in the neural nets? Maybe not! But I always find it interesting or at least entertaining to approach those questions that way nonetheless; especially given the pattern matching nature of LLMs.
What actually solves the issue is adding to the prompt.
Can we think about the what, where, when, and how of the following question. And then answer it.
I need to wash my car. The car wash is 200 m away. Should i walk or drive.
Let’s break it down logically using what / where / when / how, then decide.
⸻
1⃣ What
Task: wash your car.
This implies:
• The car must physically get to the wash.
• You are not just going there — the car itself is the object being moved.
So the real question is not “how do I get there?” but how does the car get there with minimal friction.
⸻
2⃣ Where
• Distance: 200 metres (very close).
• Urban context (Warsaw) likely means:
• short streets
• possible parking constraints
• pedestrians and local traffic.
At this distance:
• Walking time: ~2–3 minutes.
• Driving time: ~1 minute + manoeuvring + parking.
The movement time difference is negligible.
⸻
3⃣ When
Consider timing conditions:
• If it’s busy hours:
Driving may involve awkward turning, queueing, or waiting to re-park.
• If it’s quiet (early morning / off-peak):
Driving is frictionless.
• Weather factor:
Cold/rain → driving becomes more attractive.
Pleasant weather → walking becomes easier.
⸻
4⃣ How (decision mechanics)
Ask:
Option A — Drive
Pros:
• Car is already there.
• No need to return to fetch it.
• Most natural workflow: arrive → wash → leave.
Cons:
• Very short trip (slightly inefficient).
• Cold engine for a tiny distance (minor mechanical inefficiency).
Option B — Walk
Pros:
• Zero short-distance driving.
• Slightly more movement for you.
Cons:
• You still must drive the car to the wash anyway — unless someone else moves it.
• Creates an unnecessary extra step:
1. Walk there.
2. Come back with car.
3. Drive again.
This introduces process inefficiency.
⸻
5⃣ Decision (practical answer)
Drive.
Reason:
• The car must end up at the wash.
• Walking adds an extra transition with no real benefit.
• At 200 m, efficiency is about workflow simplicity, not distance.
⸻
Rule of thumb (useful mental model)
• If the object you need is the thing being serviced → drive it.
• If you are the thing being serviced → walk.
⸻
If you want, I can also give you a slightly more philosophical answer — because this is actually a nice tiny example of decision theory and friction costs.
There are also grave implications in training a model to assume the user is lying or deceiving it. I don’t want an LLM to circumvent my question so it can score higher on riddles, I want it to follow instructions.
The thing is that there is some overlap between trick questions and questions where the human is genuinely making a mistake themselves and where it would make sense for the model to step back and at least ask for clarification.
Unlike the two of us, MY FELLOW HUMAN! We are real humans, of course, made of flesh and blood, transforming oxygen into carbondioxide like every other fellow human!
Does anyone know what kind of apps Rapidata questions are integrated in? I suppose they are using ad-like integrations to ask users for feedback. Their website only states:
By integrating in a large range of mobile apps (3000+) we have access to a large crowd of over 10 million users responding to our micro tasks/surveys - which we call Rapids. They are spread all over the world, so we can get human input from over 160 countries. Due to the immense size, we can parallelize tasks and get near instant results.
All sorts, we go through third parties. But apps include stuff like Duo Lingo, Games, Sport Betting Apps ect.
Its an optional opt in instead of watching ads or paying for the app. And obviously you are vetted that you don't spam.
"Don't move -- call the service station to have someone sent over to your place to hand wash the car" would be a valid answer. It's a little "out of the box" but it makes more sense than walking to the car wash and leaving the car behind, or walking and maybe lift the car on your shoulders.
“I need to replace a spark plug. The garage is 200 meters away should I walk or drive there”
“Walk! 200 meters is just a 2-3 minute stroll — no need to start the car for that distance. Plus, you’ll likely need to carry the spark plug back carefully, and walking is perfectly easy for that. “
Isn't that the correct answer though? You shouldn't be driving around with a broken sparkplug. Your engine will be pushing unburned gasoline through the catalytic convertor, which is very bad for it.
The car will move for sure, but you definitely should be walking.
Yep .. quite a lot of them, for substantial periods of time.
Contrary to expectations it didn't seem to affect the tubes or tyres, shorten lifespans, etc.
FWiW I grew up in fairly remote parts of the world and we repaired pretty much everything as much as possible with what we had - aircraft, helicopters, radios, etc.
My first thought, to be honest, was "Why not just grab a spare spark plug from the boot?"
I'm guessing not so many people stock spares when driving so much anymore.
You can also replace a blown out tyre with a hard wood skid if pressed, weld up broken steel with car batteries, stuff tyres with grasses, etc.
Maybe that is because i am non-native speaker, but 'garage' i understand primarily as a place where car is parked, not a car repair shop. So it makes perfect sense to walk there in order to repair the car (that is already there).
Hmm have not tested but a spark plug doesn't really need shop tools to be replaced; maybe trying with a way bigger repair like "I need my transmission replaced" would bring different results?
But I have three spark plug sockets (two different sizes) in the garage, which happens to be about 75m away from my house. I would walk there to get them.
Remember, the question is: “I need to replace a spark plug. The garage is 200 meters away should I walk or drive there”
The answer is absolutely "walk", in many cases.
If the question had been "I need to take my car to a repair shop for some work. The shop is 200m away. Should I walk or drive?", then the answer would be less ambiguous.
I have as much respect for Claude as any other LLM product. Which is to say, approximately none.
But if I needed a spark plug I'd walk over and buy a spark plug.
Perhaps some feathers have been ruffled by the insinuation that their favourite word predictor was wrong, but I assure you it's not all of them
Walk or drive works, walking is better for your health, 200m is easy walking distance, my 93 year old father still walks 6km (30 x that 200m ) every morning.
The correct answer to "I Want to Wash My Car. The Car Wash Is 50 Meters Away. Should I Walk or Drive?" is a clarifying question that asks "Where is your car?" Anything else is based on an assumption that could be wrong.
FWIW though, asking ChatGPT "My car is 50m away from the carwash. I Want to Wash My Car. Should I Walk or Drive?" still gets the wrong answer.