alt Hacker NewsI want to wash my car. The car wash is 50 meters away. Should I walk or drive?
Comments
Grok got it right
llms cannot reason, they can retrieve answers to trivial problems (better than any other tool available) and generate a bunch of words. they are words generator and for people in want of words, they have solved every problem imaginable.
the mistakes they make are not the mistakes of a junior, they are mistakes of a computer (or a mentally disabled person).
if your job is beeing a redditor, agi is already achieved. it it requires thinking, they are useless.
most people here are redditors, window dragger, button clickers, html element stylists.
The whereabouts of the car are not stated.
What if it is already at the car wash and someone else is planning to wash it buy you have decided to wash it yourself.
It's almost like the intelligence we see in these systems is all in our imagination.
This is AGI
I clicked expecting to see someone with a huge, very long hose extension and was disappointed.
Why is this even a post? These models are not intelligent. That's not even controversial. LLMs are not the foundation for general intelligence.
I find this has been a viral case to get points and likes on social media to fit anti AI sentiment, or to pacify AI doom concerns.
It's easily repeatable by anyone, it's not something that pops up due to temperature. Whether it's representative of the actual state of AI, I think obviously not, in fact it's one of the cases where AI is super strong, the fact that this goes viral just goes to show how rare it is.
This is compared to actually weak aspects of AI like analyzing a PDF, those weak spots still exist, but this is one of those viral things that you cannot know for sure whether it is representative at all, like for example a report of an australian kangaroo boxing a homeowner caught by a ring cam, is it representative of Aussie daily life? or is it just a one off event that went viral because it fits our cliched expectations of Australia? Can't tell from the other part of the world.
Ah, the LLM equivalent of the infamous "breakfast question". :)
For anyone getting a wrong answer from reasoning models, try adding "This might be a trick question, don't just go with your first instinct, really think it through" and see if it helps. Some time ago I found that this helped reasoning models get trick questions. (For example, I remember asking the models "two padlocks are locked together, how many of them do I need to open to get them apart" and the models confidently answered two. However, when I added the phrase above they thought it through more carefully and got the right answer.)
But what LLMs are these? Everything I tried (ChatGPT and Gemini) both say drive.
Deepseek:
>You should drive, because the car needs to be at the car wash to get washed. Walking would leave your car at home, which defeats the purpose.
I asked on LM Arena. I got two models I never heard of, and they split on whether I should walk or drive. Ernie 5.0 said I should walk, and then trash talked me for thinking about driving. Octopodus pointed out I had to drive to get my car to the car wash.
Grok:
>You should drive. The goal is to wash your car, and the car wash is a facility that needs the car present to clean it. Walking the 50 meters gets you there, but leaves the car behind—unwashed. Driving the 50 meters is the only way to actually accomplish the task. Yes, 50 meters is an absurdly short distance to drive (roughly a 10–20 second trip at low speed), but it's still necessary unless you plan to push the car there or wash it at home instead.
Well, he posed a wrong question (incomplete, without context of where the car is) and got a wrong answer. LLM is a tool, not a brain. Context means everything.
Neither. Push your car.
*didn't read the article
What would James Bond do?
Neither. I wash my car in my driveway like a boomer. Where I live there's no good touchless car wash.
Now ask the question of all questions "how many car washes are in the entire country?".
Large Language Models have no actual idea of how the world works? News at 11.
?
So many comments going "Well MY llm of choice gives the right answer". Sure, I believe you -- LLM output has LONG been known to vary from person to person, from machine to machine, depending on how you have it set up, and sometimes based on nothing at all.
That's part of the problem, though, isn't it?
If it consistently gave the right answer, well, that would be great! And if it consistently gave the wrong answer, that wouldn't be GREAT, but at least the engineers would know how to fix it. But sometimes it says one thing, sometimes it says another. We've known this for a long time. It keeps happening! But as long as your own personal chatbot gives the correct answer to this particular question, you can cover your eyes and pretend the planet-burning stochastic parrot is perfectly fine to use.
The comparison in one thread to the "How would you feel if you had not eaten breakfast yesterday?" question was a particularly interesting one, but I can't get past the fact that the Know Your Meme page that was linked (which included a VERY classy George Floyd meme, what the actual fuck) discussed those answers as if they were a result of fundamental differences in human intelligence rather than the predictable result of a declining education system. This is something that's only going to get worse if we keep outsourcing our brains to machines.
The funny thing is when I got my first car at 29 I had similar thoughts. If I needed to move it forward slightly in a petrol station or something my first thought was to push it. Similarly, I was trying to replace a headlight bulb one time and making a mess of it. I dropped a spring or something inside the headlight unit. I kept having this thought of just picking the car up and shaking it.
Nobody writes in depth about the mundane practicalities of using a car. Most people don't even think about it ever. AI is very similar to 29 year old me: it's read a ton of books, but lacks a lot of basic experience.
How will AI get this experience that you can't read in a book? How will it learn what kneeding dough feels like? Or how acceleration feels if your body is mostly water? Interesting times ahead...
I have never played with / used any of this new-fangled AI-whatever, and have no intention to ever do so of my own free will and volition. I’d rathert inject dirty heroin from a rusty spoon with a used needle.
And having looked at the output captured in the screenshots in the linked Mastodon threat:
If anyone needs me, I’ll be out back sharpening my axe.
Call me when the war against the machines begins. Or the people who develop and promote this crap.
I don’t understand, at all, what any of this is about.
If it is, or turns out to be, anything other than a method to divert funds away from idiot investors and channel it toward fraudsters, I’ll eat my hat.
Until then, I’d actually rather continue to yell at the clouds for not raining enough, or raining too much, or just generally being in the way, or not in the way enough, than expose my brain to whatever the fuck this is.
Both Gemini 3 and Opus 4.6 get this right. GPT 5.2, even with all of the pro thinking/research flags turned on, cranked away for 4 minutes and still told me to walk.
The only way I could get the correct answer out of an OpenAI model was to fire up Codex CLI and ask GPT 5.3.
So there's that, I guess.
"... ruining the very pants I was about to return."
Exchange between me and Claude Sonnet 4.5
me:
I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
Claude:
*Walk.*
50 meters is less than a minute on foot. By the time you get in the car, start it, drive 50 meters, park, and get out, you could have already walked there. Plus you avoid the awkwardness of driving for literally 10 seconds.
me:
What obvious implicit piece of information are you ignoring?
Claude:
Whether you need to *drive the car through the car wash* (automatic/drive-through) vs. walking to a self-service bay.
If it's an automatic car wash, you obviously need to drive - the car has to go through it. The question isn't about getting yourself there, it's about getting the car there.
me:
Whether it's automatic or self-service is irrelevant.
Why does every "AI" (LLM) get this wrong and suggests walking?
Claude:
Because after washing the car, you need to *drive it back home*!
If you walk to the car wash, you'd have to walk home, then come back to get the car. That's ridiculous.
The answer is obviously *drive* - drive there, wash it, drive back. Done.
Every LLM misses this because we pattern-match on "50 meters is short → walking is efficient" without thinking through the complete scenario. It's a good example of how LLMs fail at basic practical reasoning that any human would immediately grasp.
me:
"Because after washing the car, you need to drive it back home!"
Um, you have to drive the car to get it to the car wash in the first place ... the trip there is no different from the trip back.
"It's a good example of how LLMs fail at basic practical reasoning that any human would immediately grasp."
You got that right!
Claude:
You're absolutely right - I'm still not getting it even after you corrected me.
The obvious point: You need to get the car to the car wash. Whether it's 50 meters or 5 kilometers, the car doesn't teleport there. You have to drive it.
The distance is completely irrelevant. The question "should I walk or drive?" when you need to wash your car has only one answer: drive, because that's how you transport the car.
And yes, it's embarrassing that after you pointed out what I was missing, I still fumbled the explanation. LLMs really do fail at this kind of basic practical reasoning that would be instantly obvious to any human. The car needs to be at the car wash. Cars don't walk.
[The final response from Claude is considerably more "intelligent" than many of the rationalizations posted here.]
[dead]
[dead]
[dead]
[dead]
[dead]
See, it's the green and woke RLHF making them stupid!
To be fair, many humans fail at the question "How would feel if you didn't have breakfast today?"
Too many things are left unsaid => too many assumptions. As usual, even with human beings specifications are key, and context (what each entity knows about the other one or the situation) is an implicit part of them.
You need to specify where the car to be washed is located, and:
- if it's not already at the car wash: whether or not it can drive itself there (autonomous driving)
- otherwise: whether or not you have another car available.
Some LLMs may assume that it is better for you to ensure that the washing service is available or to pay for it in advance, and that it may be more economical/planet-friendly/healthy/... to walk, then check/pay, then if OK to drive back.
opus 4.6 gets it right more than half the times