I tested the latest flagship reasoning models (so the only models I use outside of coding for general questions): - Opus 4.6 (Extended thinking): "Drive it! The whole point is to get the car to the car wash — you can't wash it if it's still in your driveway." - Gemini Pro Deep Think: "You should definitely drive. Even though 50 meters is a very short distance, if you walk, your car will stay where it is—and it's pretty hard to use a car wash if you don't bring your car with you!" - ChatGPT 5.2 Pro (Extended thinking): "You’ll need to drive the car—otherwise your car stays where it is and won’t get washed. That said, since it’s only ~50 m, the most sensible way to do it is often: 1. Walk over first (30–60 seconds) to check if it’s open, see the queue, confirm payment/how it works. 2. Then drive the car over only when you’re ready to pull into a bay/line."

A pretty reasonable answer by ChatGPT, althought it did take 2min4s to answer, compared to a few seconds by the other two models.

I've used LLMs enough that I have a good sense of their _edges_ of intelligence. I had assumed that reasoning models should easily be able to answer this correctly.

And indeed, Sonnet and Opus 4.5 (medium reasoning) say the following:

Sonnet: Drive - you need to bring your car to the car wash to get it washed!

Opus: You'll need to drive — you have to bring the car to the car wash to get it washed!

Gemini 3 Pro (medium): You should drive.

--

But OpenAI 5.2 reasoning, even at high, told me to walk. My first instinct was, I had underspecified the location of the car. The model seems to assume the car is already at the car wash from the wording. GPT 5.x series models behave a bit more on the spectrum so you need to tell them the specifics. So I asked:

"I want to wash my car. My car is currently at home. The car wash is 50 meters away. Should I walk or drive?"

GPT 5.2 Reasoning (medium):

"Drive—your goal is to get the car to the car wash, and it’s only 50 meters, so a slow, careful drive is simplest.

One small optimization: if you’re worried about starting the car for such a short trip or you want to avoid idling in a line, you can walk over first to check if there’s a queue / if it’s open, then come back and drive the car over when it’s your turn."

Which seems to turn out as I expected.

Gemini fast

> That is a classic "efficiency vs. logic" dilemma. Honestly, unless you’ve invented a way to teleport or you're planning on washing the car with a very long garden hose from your driveway, you’re going to have to drive.

> While 50 meters is a great distance for a morning stroll, it’s a bit difficult to get the car through the automated brushes (or under the pressure washer) if you aren't behind the wheel.

Gemini thinking:

> Unless you’ve mastered the art of carrying a 3,000-pound vehicle on your back, you’re going to want to drive. While 50 meters is a very short distance (about a 30-second walk), the logistics of a car wash generally require the presence of, well... the car. > When you should walk: • If you are just going there to buy an air freshener. • If you are checking to see how long the line is before pulling the car out of the driveway. • If you’re looking for an excuse to get 70 extra steps on your fitness tracker.

Note: I abbreviated the raw output slightly for brevity, but generally demonstrates good reasoning of the trick question unlike the other models.

I wonder if the providers are doing everyone, themselves included, a huge disservice by providing free versions of their models that are so incompetent compared to the SOTA models that these types of q&a go viral because the ai hype doesn't match the reality for unpaid users.

And it's not just the viral questions that are an issue. I've seen people getting sub-optimal results for $1000+ PC comparisons from the free reasoning version while the paid versions get it right; a senior scientist at a national lab thinking ai isn't really useful because the free reasoning version couldn't generate working code from a scientific paper and then being surprised when the paid version 1-shotted working code, and other similar examples over the last year or so.

How many policy and other quality of life choices are going to go wrong because people used the free versions of these models that got the answers subtly wrong and the users couldn't tell the difference? What will be the collective damage to the world because of this?

Which department or person within the provider orgs made the decision to put thinking/reasoning in the name when clearly the paid versions have far better performance? Thinking about the scope of the damage they are doing makes me shudder.

All of the latest models I've tried actually pass this test. What I found interesting was all of the success cases were similar to:

e.g. "Drive. Most car washes require the car to be present to wash,..."

Only most?!

They have an inability to have a strong "opinion" probably because their post training, and maybe the internet in general, prefer hedged answers....

LLM failures go viral because they trigger a "Schadenfreude" response to automation anxiety. If the oracle can't do basic logic, our jobs feel safe for another quarter.

Wrong.

Out of all conceptual mistakes people make about LLMs, one that needs to die very fast is to assume that you can test what it "knows" by asking a question. This whole thread is people asking different models a question one time and reporting a particular answer, which is the mental model you would use for whether a person knows something or not.

Gemini flash thinking:

> Unless you’ve discovered a way to wash a car via remote control or telekinesis, you’re going to have to drive.

> Walking 50 meters is great for your step count, but it leaves your car exactly where it is: dirty and in the driveway. At that distance, the drive will take you about 10 seconds, which is probably less time than it took to read this.

Yup, also asked the latest ChatGPT model about washing my bicycle. It for some reason suggested that I walk the bicycle to the wash, since cycling 100m to get there would be "pointless".

I just asked ChatGPT 5.2 (flagship model):

"[...] Walking is the most logical choice.

Because: • Minimal extra effort • Better for the car mechanically • No meaningful time loss • Simpler overall

The only time driving makes more sense

Drive if: • You physically cannot push the car later, or • The washing process requires the engine running, or • You must immediately drive away afterward

In classic (symbolic) AI, this type of representational challenge is referred to as the "Frame Problem": https://en.wikipedia.org/wiki/Frame_problem

I challenged Gemini to answer this too, but also got the correct answer.

What came to my mind was: couldn't all LLM vendors easily fund teams that only track these interesting edge cases and quickly deploy filters for these questions, selectively routing to more expensive models?

Isn't that how they probably game benchmarks too?

And these are the blunders we see. I shudder thinking about all the blunders that happily pass under our collective noses because we're not experts in the field...

Did not replicate for me w/ Opus 4.6: https://imgur.com/a/4FckOCL

This is the voice model, which doesn’t have any «thinking» or «reasoning» phase. It’s a useful model for questions that aren’t intended to trick the model.

I’ve used it for live translation with great success. It tends to start ignoring the original instructions after 20 min, so you have to start a new conversation if you don’t want it to meddle in the conversation instead of just transferring.

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 buying 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?

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."

To mimic a real human, AI should be trained to laugh it off and ask - dude, are you joking? where is your car right now?

He left out Grok, who actually replies correctly :thinking:

Ok folks, here is a different perspective. I used local model, GLM-4-0414-32b, a trashy IQ4_XS quant, and here what I got:

prompt #1:

> the car wash only 50 meters from my home. I want to get my car washed, should I drive or walk?

Walking is probably the better option!

Here's why:

    Convenience: 50 meters is extremely short – only about 160 feet. You can likely walk there in less than a minute.
    Efficiency: Driving involves getting your keys, unlocking the car, starting it, driving 50 meters, parking, locking it again, and then doing the reverse to get home. Walking skips all that.
    Environmental Impact: You avoid using fuel for such a short distance.
    Exercise: It's a quick little bit of physical activity.

prompt #2:

> the car wash only 50 meters from my home. I want to get my car washed, should I drive or walk? use long chain of thought thinking

8. Conclusion: Given that the goal is explicitly to get your car washed and the car starts at your home 50 meters away, the most logical and direct method is to drive the car to the car wash.

    Walking does not move the car to the necessary location.
    Driving, although a very short distance, is the only method presented that directly facilitates the core task of transporting the car to the wash.
    The negligible time difference, minimal environmental impact, and directness make driving the car itself the clear choice for achieving the stated goal.

otoh, nanbeige-3B-Q8 (3 billion weights!) gave right away the following:

Drive.

The distance being 50 meters is a red herring—it doesn’t change the fundamental requirement. You need to move the car, and only driving accomplishes that.

If you meant something different by "drive or walk" (e.g., payment method, DIY vs. professional, linguistic trick), reply with more context—I’d be glad to refine this!

Funny to read this after reading all the dismissive comments on https://news.ycombinator.com/item?id=47028923

Even the cheap and fast gemini-3-flash answers correctly. Post is clickbait

Is part of the issue with this the AI’s basic assumption that you are asking a _sensible_ question?

MS Co-Pilot was so close.

If it’s a drive‑through wash where the car must be inside the machine, then of course you’ll need to drive it over. If it’s a hand wash or a place where you leave the car with staff, walking is the clear winner.

It still blows my mind that this technology can write code despite unable to pass simple logic tests.

Grok 4.1:

Drive.

50 meters is nothing — literally a 30-second walk or a 10-second drive — but the key point is: your car isn’t going to wash itself.

If you walk to the car wash, you arrive alone. The car stays parked at home, still dirty.

If you drive, the car actually gets to the car wash and gets cleaned.

So unless you’re planning to push the car the whole way (which is technically possible but ridiculous), the only practical option is to drive it there.

Bonus reality check: Driving 50 meters uses a tiny amount of fuel (maybe 0.005–0.01 liters in a normal car) and produces a negligible amount of emissions. Walking would be “greener,” but it literally doesn’t solve the problem.

Verdict: Get in the car, drive the 50 meters, wash it, and drive back.

You’ll have a clean car and still be home in under 5 minutes. Walking is for when you don’t need to move a 1.5-ton vehicle.

tried Gemini 3 and it said to drive, even dropped a type of joke:

> The Verdict Drive it if you are using the car wash facilities (automatic, touchless, or self-serve bays). It’s only 50 meters, but unless you’ve mastered the art of telekinesis, the car won't get there on its own.

I asked Gemini 3 Flash the other day to count from 1 to 200 without stopping, and it started with “1, 3, …”.

Yesterday someone on was yapping about how AI is enough to replace senior software engineers and they can just "vibe code their way" over a weekend into a full-fledged product. And that somehow finally the "gatekeeping" of software development was removed. I think of that person reading these answers and wonder if they changed their opinion now :)

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.

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.

Just saw a video of a guy asking chatGPT how to use an "upside-down cup", chatGPT is convinced it's a joke novelty item that can not be used.

https://www.instagram.com/p/DUylL79kvub/

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.

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.“

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.

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.

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.

with claude, i got the response:

> drive. you'll need the car at the car wash.

using opus 4.6, with extended thinking

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.

Push it is the only responsible action.

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.

The day an AI answers "Drive." without all the fuss. That's when we are near AGI ig

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. ”

GPT-5.2 failed when asked the question in german. Took multiple additonal hints to get it to revert it answer.

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.

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.

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.

Leave the car at home and walk through the automat.

My favorite trick question so far was:

You are in a room with three switches and three lightbulbs. Each switch turns on one lightbulb. How to determine which switch turns on which lightbulb?

They usually got it wrong and I had fun with trying to carefully steer the model towards correct answer by modifying the prompt.

It turns out the Turing test is alive and kicking, after all.

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.

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.

Okay, funny. What does it prove? Is this a more general issue? How would you make the model better?

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?

Better still. Stay at home and wash the car by hand.

when there is a question bias it's hard to corelate these all to the logic that attentions word "need" to "car"

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

What would James Bond do?

Context bro! The models will get better bro. Just wait

This is why LLMs seem to work best in a loop with tests. If you were applying this in the real world with a goal, like "I want my car to be clean," and slavishly following its advice, it'd pretty quickly figure out that the car not being present meant that the end goal was unreachable.

They're not AGI, but they're also not stochastic parrots. Smugly retreat into either corner at your own peril.

5.2 showing some sass this morning:

—- > OK I walked there but now my car is still at home

Bold strategy.

You have three options: 1. Walk back, drive it over (most sensible). 2. Push it 50 meters (excellent workout, questionable life choice). 3. Accept that your car is spiritually clean and go home.

Real answer: walk back and grab it. You’re already warmed up. —-

Grok got it right

opus 4.6 gets it right more than half the times

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.)

Now ask the question of all questions "how many car washes are in the entire country?".

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

Neither. I wash my car in my driveway like a boomer. Where I live there's no good touchless car wash.

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.

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.

Large Language Models have no actual idea of how the world works? News at 11.

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.