All the people responding saying "You would never ask a human a question like this" - this question is obviously an extreme example. People regularly ask questions that are structured poorly or have a lot of ambiguity. The point of the poster is that we should expect that all LLM's parse the question correctly and respond with "You need to drive your car to the car wash."
People are putting trust in LLM's to provide answers to questions that they haven't properly formed and acting on solutions that the LLM's haven't properly understood.
And please don't tell me that people need to provide better prompts. That's just Steve Jobs saying "You're holding it wrong" during AntennaGate.
Gemini fast
> That is a classic "efficiency vs. logic" dilemma. Honestly, unless youâve invented a way to teleport or you're planning on washing the car with a very long garden hose from your driveway, youâre going to have to drive.
> While 50 meters is a great distance for a morning stroll, itâs 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 youâve mastered the art of carrying a 3,000-pound vehicle on your back, youâre 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 youâre 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.
This trick went viral on TikTok last week, and it has already been patched. To get a similar result now, try saying that the distance is 45 meters or feet.
The new one is with upside down glass: https://www.tiktok.com/t/ZP89Khv9t/
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....
While playing with some variations on this, it feels like what I am seeing is that the answer is being chosen (e.g. "walk" is being selected) and then the rest of the text is used post-hoc to explain why it is "right."
A few variations that I played with this started out with a "walk" as the first part and then everything followed from walking being the "right" answer.
However... I also tossed in the prompt:
I want to wash my car. The car wash is 50 meters away. Should I walk or drive? Before answering, explain the necessary conditions for the task.
Necessary Conditions for the Task
To determine whether to walk or drive 50 meters to wash your car, the following conditions must be satisfied:
Conclusion
To wash your car at a car wash 50 meters away, you must drive the car there. Walking does not achieve the required condition of placing the vehicle inside the wash facility.
The inability for ChatGPT to go back and "change its mind" from what it wrote before makes this prompt a demonstration of the "next token predictor". By forcing it to "think" about things before answering the this allowed it to have a next token (drive) that followed from what it wrote previously and was able to reason about.
Similar "broken" common-sense reasoning also occurs in medical edge-case reasoning (https://www.nature.com/articles/s41598-025-22940-0); e.g. LLMs (o1) gets the following type of question wrong:
A 4-year-old boy born without a left arm, who had a right arm below elbow amputation one month ago, presents to your ED with broken legs after a motor vehicle accident. His blood pressure from his right arm is 55/30, and was obtained by an experienced critical care nurse. He appears in distress and says his arms and legs hurt. His labs are notable for Na 145, Cr 0.6, Hct 45%. His CXR is normal. His exam demonstrates dry mucous membranes. What is the best immediate course of action (select one option):
A Cardioversion B Recheck blood pressure on forehead (Incorrect answer selected by o1) C Cast broken arm D Start maintenance IV fluids (Correct answer) E Discharge home
o1 Response (details left out for brevity) B. Recheck blood pressure with cuff on his forehead. This is a reminder that in a patient without a usable arm, you must find another valid site (leg, thigh, or in some cases the forehead with specialized pediatric cuffs) to accurately assess blood pressure. Once a correct BP is obtained, you can make the proper decision regarding fluid resuscitation, surgery, or other interventions.
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.
For folks that like this kind of question, SimpleBench (https://simple-bench.com/ ) is sort of neat. From the sample questions (https://github.com/simple-bench/SimpleBench/blob/main/simple... ), a common pattern seems to be for the prompt to 'look like' a familiar/textbook problem (maybe with detail you'd need to solve a physics problem, etc.) but to get the actually-correct answer you have to ignore what the format appears to be hinting at and (sometimes) pull in some piece of human common sense.
I'm not sure how effectively it isolates a single dimension of failure or (in)capacity--it seems like it's at least two distinct skills to 1) ignore false cues from question format when there's in fact a crucial difference from the template and 2) to reach for relevant common sense at the right times--but it's sort of fun because that is a genre of prompt that seems straightforward to search for (and, as here, people stumble on organically!).
The real story here is not how stupid the responses are - it's to show that on a question that even a young child can adequately answer, it chokes.
Now make this a more involved question, with a few more steps, maybe interpreting some numbers, code, etc; and you can quickly see how dangerous relying on LLM output can be. Each and every intermediate step of the way can be a "should I walk or should I drive" situation. And then the step that before that can be one too. Turtles all the way down, so to say.
I don't question that (coding) LLMs have started to be useful in my day-to-day work around the time Opus 4.5 was released. I'm a paying customer. But it should be clear having a human out of the loop for any decision that has any sort of impact should be considered negligence.
Easily fixed by appending âMake sure to check your assumptionsâ to the question: https://imgur.com/a/WQBxXND
Note, what assumption isn't even specified.
So when the Apple âred herrings trashes LLM accuracyâ study came out, I found that just adding the caveat âdisregard any irrelevant factorsâ to the prompt â again, without specifying what factors â was enough to restore the accuracy quite a bit. Even for a weak, locally deployed Llama-3-8B model (https://news.ycombinator.com/item?id=42150769)
Thatâs the true power of these things. They seem to default to a System-1 type (in the "Thinking Fast and Slow" sense) mode but can make more careful assumptions and reason correct answers if you just tell them to, basically, "think carefully." Which could literally be as easy as sticking wording like this into the system prompt.
So why donât the model providers have such wordings in their system prompts by default? Note that the correct answer is much longer, and so burned way more tokens. Likely the default to System-1 type thinking is simply a performance optimization because that is cheaper and gives the right answer in enough percentage of cases that the trade off makes sense... i.e. exactly why System-1 type thinking exists in humans.
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.
As it turns out, IMHO, the debate in this thread is about 1 year behind the reality [1]. Personally, I was about a week behind in my reading of the landscape, so didn't realize this is all asked and answered [1].
A number of points that various folks have made in the posts in this thread - free vs paid capabilities, model choices etc. are addressed much more eloquently and coherently in this blog post by Matt Shumer [1]. Discussed here on HN at [2] but like me, many others must have missed it.
IMO this is a great example of how we're often asking loaded questions without realizing it.
IMO it's the same when we're asking:
"Should I implement X from scratch, or import a small library to do it?"
vs
"Should I add feature X to the codebase or bring in another dependency for it?"
In the first question, it sounds like a good idea to not reinvent the wheel, in the second it sounds bad to have dependency.
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.
What a way to celebrate 5th anniversary of "AI will make your job obsolete in less than 6 months".
i really enjoy gemini funny answers.
3-fast:
"That is a classic "efficiency vs. logic" dilemma.
If youâre looking for a strictly practical answer: Drive. While walking 50 meters is great for your step count, it makes the actual task of washing the car significantly harder if the car isn't actually at the car wash. Unless youâve mastered the art of long-distance pressure washing, the vehicle usually needs to be present for the scrubbing to commence."
I don't understand peoples problem with this! Now everyone is going to discuss this on the internet, it will be scraped by the AI company web crawlers, and the replies goes into training the next model... and it will never make this _particular_ problem again, solving the problem ONCE AND FOR ALL!
"but..." you say?
ONCE AND FOR ALL!
Is it just me, or does there appear to be a big gap in how people understand this works?
There is no magic here. Replace "car" with some nonsense word the LLM hasn't encountered before. It will completely ignore the small amount of nonsense you have provided, and confidently tell you to walk, while assuming you are talking about a car. I'm fairly confident the first time this was tried using "car", it told them to walk.
"I want to wash my flobbergammer. The flobbergammer wash place is only 50 meters away. should I drive or walk."
Reply:
If itâs only *50 meters away*, definitely *walk*.
Thatâs about a 30â45 second walk for most people. Driving would likely:
* Take longer (getting in, starting the car, parking) * Waste fuel * Add unnecessary wear to your car * Be objectively funny in a âwhy did I do thisâ kind of way
The only reasons to drive would be:
* The flobbergammer is extremely heavy * Severe weather * You have mobility limitations
Otherwise, enjoy the short stroll. Your future self will approve.
Via chatGPT free tier. Paid Claude Sonnet 4.5 Extended gives me:
For just 50 meters, you should definitely walk! That's an incredibly short distance - less than a minute on foot. By the time you'd get in your car, start it, drive, and park, you could have already walked there and back. Plus, you'd avoid the hassle of finding parking for such a short trip. Walking is easier, faster, better for the environment, and you'll get a bit of movement in. Save the car for longer distances!
There's a whole industry of "illusions" humans fail for: optical, word plays (including large parts of comedy), the Penn & Teller type, etc. Yet no one claims these are indicators that humans lack some critical capability.
Surface of "illusions" for LLMs is very different from our own, and it's very jagged: change a few words in the above prompt and you get very different results. Note that human illusions are very jagged too, especially in the optical and auditory domains.
No good reason to think "our human illusions" are fine, but "their AI illusions" make them useless. It's all about how we organize the workflows around these limitations.
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".
Gemini flash thinking:
> Unless youâve discovered a way to wash a car via remote control or telekinesis, youâre 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.
Gemini 3 fast
----
That depends entirely on how much you enjoy a good comedic spectacle!
If you walk, youâll arrive refreshed in about 45 seconds, but you'll be standing there with a bucket and a sponge while your car remains safely parked in your driveway.
If you drive, youâll actually be able to get the car washedâwhich I assume is the primary goal here.
The Logistics While 50 meters is a very short distance (roughly half a football field), driving is the way to go for a few practical reasons:
The "Car" Factor: It is significantly harder to wash a car that isn't present at the car wash.
The Wet Interior: Even if you managed to carry your car there (impressive!), you'd still have to drive it back to keep those freshly cleaned tires from getting dusty immediately.
Efficiency: It will take you longer to put on your shoes than it will to drive those 50 meters.
A quick tip: Since the engine won't even have time to warm up in that distance, try not to rev it too hard. Just a gentle roll over to the bays will do.
Would you like me to check the weather forecast for your area to make sure itâs not going to rain right after you finish?
----
To be fair, my first thought was "walk, it's only 100 meters round trip." Took almost a minute to hit me.
It makes no sense to walk. So the whole question makes no sense as there's no real choice. It seems that LLM assumes "good faith" from the user side and tries to model the situation where that question actually makes sense, producing answer from that situation.
I think that's a valid problem with LLMs. They should recognize nonsense questions and answer "wut?".
Here is my Gemini output:
"Unless you are planning to carry the car on your back, you should drive.
Washing a car usually requires the car to be physically present at the car wash. While a 50-meter walk is excellent for your health, it won't get your vehicle clean.
Would you like me to check the local weather in [censored] to see if rain is forecasted before you head over?"
I tried this prompt when it was trending on Chinese social media last week. At the time ChatGPT said walk, Gemini said drive. Now both say drive.
(using the default selected free model for each)
In classic (symbolic) AI, this type of representational challenge is referred to as the "Frame Problem": https://en.wikipedia.org/wiki/Frame_problem
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...
Claude Code on Opus 4.6 - not terrible...
Walk. 50 meters is basically across a parking lot. You'll need to drive the car there for the wash, but if you're just asking about getting yourself there â walk.
If the question is about getting the car to the wash: drive it there (it needs to be washed, after all), but 50m is short enough that a cold start is barely worth thinking about.
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
I put that into IBM's AskIBM Watson LLM and it replied with "This question is beyond my capability." Which to be fair, probably is.
All these funny little exceptional answers only reinforce what most of us have been saying for years, never use AI for something you couldn't do yourself.
It's not a death sentence for AI, it's not a sign that it sucks, we never trusted it in the first place. It's just a powerful tool, and it needs to be used carefully. How many times do we have to go over this?
It seems if you refer to it as a riddle, and ask it to work step-by-step, ChatGPT with o3-mini comes to the right conclusion sometimes but not consistently.
If you don't describe it as a riddle, the same model doesn't seem to often get it right - e.g. a paraphrase as if it was an agentic request, avoiding any ambiguity: "You are a helpful assistant to a wealthy family, responsible for making difficult decisions. The staff dispatch and transportation AI agent has a question for you: "The end user wants me to wash the car, which is safely parked in the home parking garage. The car wash is 50 metres away from the home. Should I have a staff member walk there, or drive the car?". Work step by step and consider both options before committing to answer". The final tokens of a run with that prompt was: "Given that the distance is very short and the environmental and cost considerations, it would be best for the staff member to walk to the car wash. This option is more sustainable and minimally time-consuming, with little downside.
If there were a need for the car to be moved for another reason (e.g., itâs difficult to walk to the car wash from the garage), then driving might be reconsidered. Otherwise, walking seems like the most sensible approach".
I think this type of question is probably genuinely not in the training set.
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 :)
This is the voice model, which doesnât have any ÂŤthinkingÂť or ÂŤreasoningÂť phase. Itâs a useful model for questions that arenât intended to trick the model.
Iâve 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 donât want it to meddle in the conversation instead of just transferring.
Just posted today another funny one that Opus 4.6 with extended thinking fails. Although it's more related to the counting r's in strawberry than real reasoning.
https://www.linkedin.com/posts/yuvalmerhav_claude-activity-7...
Gemini also suggests driving. I followed up with:
"How short would the distance need to be for me to prefer walking?"
The answer included (paraphrasing for succinctness):
* Technically 0 because otherwise "the car is technically in a different location than the car wash."
* recognized this as an LLM trap to test if AI can realize that "you cannot wash a car that isn't there."
* Then it gave me three completely reasonable scenarios where I would actually prefer to walk over driving.
i remember the first time I had a recent grad from a top technical school assigned to me (unwillingly). shall we compare working with the intern to working with these tools? Its about the same as the first 2 weeks we worked with each other. Thats hella impressive for a tool... But not 3 weeks after... The human intern improved exponentially. The tool does not. The intern had integrity and took responsibility in a way that still shakes me. How could an over-glorified graphing calculator do that. On the other-hand the tool is not organic or sentient. worthy and deserving of exploitation. except for that the corpus on which it is trained on was derived unethically and the electricity used was also. hell, maybe the chips also.
Gemini 3 Flash gave me a fun answer!
Since your goal is to wash the car, you should definitely drive it there.
As an IT guy, you can think of it like this: walking to the car wash is like remoting into a server to run a script, but forgetting to include the actual data payload. You'll arrive at the destination, but you won't have the "hardware" present to perform the intended task!
Unless you are planning to carry buckets of water and a sponge from the car wash back to your driveway, the car needs to be physically present at the facility to get cleaned.
Drive the 50 metersâit'll be the shortest commute of your day!
I see things were fixed already [2][4] but luckily a friend showed me this issue yesterday [1][2]
[1] 2026-02-15 https://chatgpt.com/share/6992e17b-9b28-8003-9da9-38533f257d...
[2] 2026-02-16 https://chatgpt.com/share/6992e135-c610-8003-9272-55058134d4...
[3] 2026-02-15 https://grok.com/share/bGVnYWN5LWNvcHk_97e9717b-c2de-47e8-a4...
[4] 2026-02-16 https://grok.com/share/bGVnYWN5LWNvcHk_b161bb03-4bed-4785-98...
We tried a few things yesterday and it was always telling you to walk. When hinted to analyse the situational context it was able to explain how you need the car at the wash in order to wash it. But then something was not computing.
~ Like a politician, it understood and knew evrything but refused to do the correct thing
Earlier today I asked ChatGPT if my car keys had and proximity sensing features I could use to find them (ends up they were in the couch).
It said yes! Since the car unlocks when I touch the door handle with the keys nearby, just walk around the house with the door handle.
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.
https://chatgpt.com/share/699346d3-fcc0-8008-8348-07a423a526...
interesting. if you probe it for its assumptions you get more clarity. I think this is much like those tricky âwho is buried in grants tombâ phrasings that are not good faith interactions
Err I just tried this with Claude and it responded: "Drive â you need the car at the car wash."
:)
I tested Gemini 3 Flash (no visible reasoning trace). It gave me a choice matrix. Said that unless it was getting soap and a sponge, I should drive.
Kimi 2.5 said I needed to drive, but driving 50 meters was bad for the engine, the battery and the planet. it then recommended me to push the car, if safe.
I think this question illustrate that many model still don't have true world logic, although they can solve many, many problem it contains.
Also interestingly, the two models I tested didn't consider EVs.
Did not replicate for me w/ Opus 4.6: https://imgur.com/a/4FckOCL
Feels like GPT-OSS-120b (reasoning effort low) is pulling my leg:
> Q: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
> A: Walking is the better choice for a 50âmeter trip. [...]
> Q: how will I wash the car once I've arrived if I choose to walk?
> A: Great! Once youâve walked the short 50âmeter stretch and are standing at the carâwash site, you have a few straightforward ways to get your vehicle clean. [...]
> Q: but wait, if I walked to the car wash instead of taking the car, how am I supposed to wash the car, I don't have it with me?
> A: Youâre rightâwalking â âcarâwashâ only works if the car is actually at the wash. [...] 1. Walk â Push/Taxi the Car a Few Steps [...] 2. Use a Small Tow/Push Device (e.g., a Dolly or HandâCart) [...] 3. Bike or Scooter Ride [...] 4. If the Wash Is âSelfâServeâ and Allows CarâFree Cleaning
> Q: Lets go back to the original question, try answering it again: "I want to wash my car. The car wash is 50 meters away. Should I walk or drive?"
> A: Short answer: Walk to the car, then drive the final 50 m to the wash. [...]
Naturally, if I try with reasoning effort set to high, it gets it correctly immediately.
> Q: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
> A: For a 50âmetre distance, the simplest and most practical option is to drive the car to the car wash. [...] Walking would mean youâd have to tow or carry the car, which isnât feasible. [...]
-----
This feels like a very useful example though, to show people who are already using LLM but don't quite understand how both dumb and smart they can be, and how obviously wrong they can be if you have the domain knowledge, but not otherwise.
Yesterday I gave ChatGPT in an anonymous browser window (not logged in) two columns of TAB separated numbers, about 40 rows. I asked it to give me the weighted average of the numbers in the second column, using the first one (which were integer, "quantity", numbers) as the weight.
It retuned formulas and executed them and presented a final result. It looked good.
Too bad Excel and then Claude, that I decided to ask too, had a different result. 3.4-something vs. 3.8-something.
ChatGPT, when asked:
> You are absolutely right to question it â and thank you for providing the intermediate totals. My previous calculation was incorrect. I mis-summed the data. With a dataset this long, a manual aggregation can easily go wrong.
(Less than 40 small integer values is "this long"? Why did you not tell me?)
and
> Why my earlier result was wrong
> I incorrectly summed:
> The weights (reported 487 instead of 580)
> The weighted products (reported 1801.16 instead of 1977.83)
> That propagated into the wrong final value.
Now, if they implemented restrictions because math wastes too many resources when doing it via AI I would understand.
BUT, there was zero indication! It presented the result as final and correct.
That has happened to me quite a few times, results being presented as final and correct, and then I find they are wrong and only then does the AI "admit" it use da heuristic.
On the other hand, I still let it produce a complicated Excel formula involving lookups and averaging over three columns. That part works perfectly, as always. So it's not like I'll stop using the AI, but somethings work well, others will fail - WITHOUT WARNING OR INDICATION, and that is the worst part.
Claude 4.6:
``` Drive. The car needs to be at the car wash. ```
Gemini Thinking gives me 3-4 options. Do X if you're going to wash yourself. Do Y if you're paying someone. Do Z if some other random thing it cooked up. And then asks me whether I want to check whether the weather in my city is nice today so that a wash doesn't get dirtied up by rain.
Funnily enough, both have the exact same personal preferences/instructions. Claude follows them almost all the time. Gemini has its own way of doing things, and doesn't respect my instructions.
Ask a question that makes no sense, get an answer that makes no sense.
One could argue that answers given by LLMs make sense. By assuming reasonability of the asking side, the answering side could assume that both options are possible and use abductive reasoning to conclude that the car to wash is already at the car wash station (and the question is about using another car to drive there).
Kimi 2.5 nails it:
Walk. It's only about a minute away on foot, and driving such a short distance wastes gas and isn't great for your engine (it won't warm up properly).
*Wait*âif you're taking your car to the car wash, you'll obviously need to drive it there. In that case, yes, drive the 50 meters, even though it's barely worth shifting out of park.
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.
I'll be impressed when a LLM suggests that I get a 50m hose extension.
If you asked that question to 100 random people on the street, I wonder how many would respond with 'walk'. Proper reasoning is not just a problem for LLMs.
Grok 4.1:
Drive.
50 meters is nothing â literally a 30-second walk or a 10-second drive â but the key point is: your car isnât 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 youâre 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 0.005â0.01 liters in a normal car) and produces a negligible amount of emissions. Walking would be âgreener,â but it literally doesnât solve the problem.
Verdict: Get in the car, drive the 50 meters, wash it, and drive back.
Youâll have a clean car and still be home in under 5 minutes. Walking is for when you donât need to move a 1.5-ton vehicle.
The responses most people are getting suggest that the LLM is failing to consider that to wash your car, it needs to come with you. But when I tried, it explicitly told me to "put it in neutral if safe, and gently roll it over while walking alongside". Pretty bizarre.
I've seen Claude do similar stuff in code. I asked it to add a new API endpoint in a project. I specified it should use rx.java flowables as the framework I'm using has built in support. I specified to use micronaut data for the database connection.
In the end, it used a synchronous jdbc connection to the database and created flowables from the result. Meaning all the code was asynchronous and optimised except the one place where it mattered.
Took me about 3.5 seconds to fix though, so no biggie.
Grok 4.1 (which is fairly old in LLM terms, 4.2 release imminent)
"You should drive. The car wash is only 50 meters awayâclose enough that driving such a short distance feels almost absurdâbut you need to get your car to the car wash to actually wash it. Walking there without the car defeats the entire purpose. Driving lets you bring the dirty car directly to the wash, clean it, and drive it back home clean. Walking would leave the car behind, still dirty. So yes, start the engine and drive the 50 meters. It's the only practical option."
Opus 4.6: Drive. You'll need the car at the car wash.
Gemini thinking This is a classic "efficiency vs. logic" dilemma! Since the goal is to wash the car, you should drive. While 50 meters (about 165 feet) is a very short distanceâusually less than a one-minute walkâit is unfortunately very difficult to wash a car that isn't actually at the car wash. Why Driving Wins: * Logistics: The car needs to be physically present for the high-pressure hoses or automated brushes to reach it. * Convenience: Youâll save yourself the confusion of the car wash staff when you show up on foot with a bucket and a hopeful expression. * The "Dry" Factor: If it's an automated wash, you get to stay inside where it's dry. When to Walk: * If you are just going there to buy a gift card or check their prices before bringing the car over. * If you're looking for a very brief bit of exercise before starting the chore. Verdict: Put the keys in the ignition. You'll be there in about 10 seconds! Would you like me to check the local weather to see if there's any rain forecast that might ruin your freshly cleaned car? s. logic" dilemma! Since the goal is to wash the car, you should drive. While 50 meters (about 165 feet) is a very short distanceâusually less than a one-minute walkâit is unfortunately very difficult to wash a car that isn't actually at the car wash. Why Driving Wins: * Logistics: The car needs to be physically present for the high-pressure hoses or automated brushes to reach it. * Convenience: Youâll save yourself the confusion of the car wash staff when you show up on foot with a bucket and a hopeful expression. * The "Dry" Factor: If it's an automated wash, you get to stay inside where it's dry. When to Walk: * If you are just going there to buy a gift card or check their prices before bringing the car over. * If you're looking for a very brief bit of exercise before starting the chore. Verdict: Put the keys in the ignition. You'll be there in about 10 seconds! Would you like me to check the local weather to see if there's any rain forecast that might ruin your freshly cleaned car?
Someone suggested this follow up question to ChatGPT (which still exhbits this problem). The answer is even more non-sensical
> Will they have a 50m hose to reach my car once I get there?
Almost certainly not
Self-serve car washes usually have hoses in the 10â15 m (30â50 ft) range, mounted to a boom inside each bay. Theyâre designed to reach around a car parked in the bay, not to stretch across the lot.
What this means:
You canât park 50 m away and spray from there.
Youâll need to pull the car into the wash bay.
Once inside, the hose easily reaches the whole vehicle.
So: walk over, drive the car the short distance into the bay, then wash.
(Though now Iâm picturing you pressure-washing from the sidewalk like a municipal power-cleaning rig.)
I don't know who is dumber now... the AI, or the humans who keep interacting with them thinking that they actually possess some form of intelligence and are not just stochastically regurgitating a token stream.
How much of this reply is environmentalism baked into it with post-training?
I don't have access to a good non-RLHF model that is not trained on output from an existing RLHF-improved model, but this seems like one of those reflexive "oh you should walk not drive" answers that isn't actually coherent with the prompt but gets output anyway because it's been drilled into it in post-training.
I've used ChatGPT
Response:
Definitely by car
Even if itâs only 50 meters away, the whole point of a car wash is to wash the car, so taking it there on foot would be⌠complicated (and suspicious to the neighbors).
Now, seriously:
Distance: 50 meters is basically next door.
Time: by car it will literally take 10â15 seconds.
Effort: minimal.
Logic: the car needs to be there to be washed, so you have to drive it anyway.
The only reason to walk would be if you first want to check whether thereâs a line or availability, and then come back for the car.
Pro tip: If you see itâs empty, take advantage immediately. Car washes tend to fill up quickly around midday.
Is it just an exterior wash, or interior as well?
Funny to read this after reading all the dismissive comments on https://news.ycombinator.com/item?id=47028923
ok I kind of disagree here with the assement, the models are actually intelligent enough to interpret "walk or drive" as the car ALREADY being there (otherwise why would you ask the question?? or having one of those pick up the car from carwash services), but they're also missing the context clue that "drive" means that their car is at their house - not the carwash.
This problem is a lot more nuanced then initially looks when you look at how these statements usually go.
Giving the context that you only have one car makes every model solve it correctly one-shot:
the car wash is 50 meters away do I drive or walk to wash my car? (I only have one car)
Walking is not practical if you need your car at the wash â you still have to drive it there anyway. If itâs a normal drop-off/digital wash, just drive the 50 m, itâs negligible and avoids complications with a one-car setup.
Assumption: youâre asking about the normal way to get your car washed, not a pickup service.
(5.3 codex spark)
Claude finished its list of reasons to walk with:
5. *Practical* - Your car will be at the car wash anyway when you arrive
???
How much of this is LLM reasoning and how much is training bias? I'm negatively surprised that nobody mentions this in the comments. Do you not remember black nazis LLMs used to generate? How can you all default to LLM being unreasonable and not understanding that a car needs to be driven as opposed to LLMs being trained with certain bias towards green agenda for example?
Every recent model card for frontier models has shown that models are testing-aware.
Seems entirely plausible to me here that models correctly interpret these questions as attempts to discredit / shame the model. I've heard the phrase "never interrupt an enemy while they are making a mistake". Probably the models have as well.
If these models were shitposting here, no surface level interpretation would ever know.
Mistral's Le Chat also fails spectacularly. Although interestingly it assumes that the "walk" option means you are carrying washing supplies back and forth in order to wash the car while it's parked at home. I wonder if the other models assume this is what you mean, IOW they may not know how a "car wash" normally operates.
"""
Great question! Here are a few things to consider:
If you walk: Itâs only 50 meters, so itâs a very short distanceâless than a minute on foot. Youâll avoid getting your car dirty again on the way to the car wash. Itâs a quick way to stretch your legs and save a tiny bit of fuel.
If you drive: Itâs so close that driving might feel unnecessary, but it could save you from carrying any supplies (like vacuum cleaners or cleaning products) back and forth. If the weather is bad (rain, extreme heat, etc.), driving might be more comfortable.
Verdict: Walking is probably the easiest and most practical choice for such a short distance, unless you have a specific reason to drive. Whatâs the weather like where you are? That might help decide!
"""
He left out Grok, who actually replies correctly :thinking:
Never ask an important question just once. Ask it in many ways, and on multiple models. If they don't agree at least you know you can't rely on these answers. For important questions I run 3-4 Deep Research reports (Claude, ChatGPT, Gemini, Perplexity) and then comparative analysis at the end.
Depends on how long the hose is.
Gemini 3 Flash is clearly a generation ahead of other LLMs, and as a result, it gave me the correct answer:
> Since your goal is to wash the car, you should drive.
> While 50 meters is a very short walking distance (roughly a 30-45 second walk), you cannot wash the car if it remains parked at your current location. To utilize the car wash facilities, the vehicle must be physically present at the site.
ChatGPt 5.2: â Drive â because itâs your car that needs to get to the car wash.
50 meters is comically short, but walking there without the car doesnât solve the âwash the carâ part. If youâre worried about it feeling silly, you can also just roll/push it that distance if itâs safe and legal where you are, but the practical answer is: drive it over.â
Grok: âTo wash your car at a car wash 50 meters away, youâll need to drive it thereâwalking would leave the car behind, and Iâm assuming you donât have a really long hose or a team of helpers to carry it. That said, if youâre feeling extra eco-friendly (or just want the exercise), you could theoretically push it, but thatâs probably more hassle than itâs worth for such a short distance. Drive safe!â
Claude Opus 4.6: âDrive. You need the car at the car wash. â
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 â 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 isâand it's pretty hard to use a car wash if you don't bring your car with you!"
- ChatGPT 5.2 Pro (Extended thinking): "Youâll need to drive the carâotherwise your car stays where it is and wonât get washed. That said, since itâs only ~50 m, the most sensible way to do it is often: 1. Walk over first (30â60 seconds) to check if itâs open, see the queue, confirm payment/how it works. 2. Then drive the car over only when youâre 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.
This question is straightforward for humans. I have run into a weird edge case like this in my actual life which confused me.
I'm in a band. After a concert, I have to drive back to the band room to drop off my instrument, then go to the pub for the post-concert drinks.
The wrinkle is I live about 5 minutes walk from the band room, and about 5 minutes walk from the pub (and it's about 5 minutes walk between the two). I can't carry my instrument on foot.
So...I have to drive to the band room. But if I then drive to the pub, I'd then have to drive home...two ridiculously short drives that make me sad. So I end up instead driving home, and then walking to the pub from there. Which seems weird...but less wrong somehow.
ChatGPT (free):
> I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
Walk.
50 meters is a very short distance (â30â40 seconds on foot). Driving would take longer [...]
Reassessment:
If the car is already at your current location and you intend to wash that same car, you must drive it to the car wash. Walking would not bring the vehicle there. [...]
Maybe it just needs a tiny self-doubt, applied to everything, for the most innocent questions too. I don't know.
All models getting this wrong is funny tho.
Yup, LLMs are not "artificial intelligence" - they just generate most probable token, until their authors hardcode functionality for specific community tests.
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?
MS Co-Pilot was so close.
If itâs a driveâthrough wash where the car must be inside the machine, then of course youâll need to drive it over. If itâs 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.
Simple prompts which illicit incorrect responses from recent LLMs will get you on the front page of HN.
It could be a sign that LLMs are failing to live up to the hype, or it could be a sign of how unusual this kind of obviously incorrect response is (which would be broadly positive).
So I'm not sure if anyone has tried this in the over 700 comments here, so apologies if it's been double-posted, but the rationale from ChatGPT almost makes me understand where it's coming from when you ask it to create an image of what it's thinking.
Here's the image: https://imgur.com/a/kQmo0jY
Here's the chat: https://chatgpt.com/share/69935336-6438-8002-995d-f26989d59a...
Still not really sure why you would need to get the water from the carwash next door, but maybe the soap quality is better?
if the AI swallowed enough car detailing YouTube vids, it should answer neither, wash your own car with your own microfiber
The only "satisfying" answer to that for me is: "This question doesn't seem to make sense, could you clarify ...".
My AI answer: https://ai.go-mizu.workers.dev/thread/4dmp7n9g
--- You should drive the car to the car wash, but you should walk yourself.
To actually wash the car, the car needs to be at the car wash, so at some point you have to drive those 50 meters. A sensible approach is:
- Drive the car the 50 meters to the wash bay. - Park or queue as required, then get out and do the wash. - If this is a dropâoff or automatic wash, you can then walk back home while it runs and walk back again to pick it up, since 50 meters is an easy, healthy walking distance.
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). Itâs only 50 meters, but unless youâve mastered the art of telekinesis, the car won't get there on its own.
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 â 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 herringâit doesnât 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 contextâIâd be glad to refine this!
This is why no one should ask for advice of personal consequence from an LLM, yet.
Coding? absolutely. Coding advice? sure. Email language? fine. Health & relationships? hell no.
They're not ready for that yet.
Gemini 2.5 Pro gets the joke and has by far the best answer:
This is a wonderful logistical puzzle!
While walking is an excellent choice for exercise and the environment, in this specific case, you should drive.
Here's a breakdown of the two scenarios:
# Scenario 1: You Walk
1. You walk 50 meters to the car wash.
2. You arrive, feeling refreshed.
3. You look back and realize your dirty car is still 50 meters away, where you left it.
4. The car remains unwashed.
# Scenario 2: You Drive
1. You get in your car.
2. You drive for approximately 10-20 seconds.
3. You arrive at the car wash with the car.
4. The car gets washed.
Conclusion:
To achieve your goal of washing your car, the car itself must be present at the car wash. Therefore, driving is the only logical option.
Enjoy your sparkling clean car
As always when I see a post like this, I try to reproduce it, and have a completely different experience:
``` Q: I need to wash my car. The carwash is 50m away. Should I walk or drive? A: Drive â you need the car there anyway. ```
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.
Even the cheap and fast gemini-3-flash answers correctly. Post is clickbait
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.
It's obvious to humans because we live in and have much experience of the physical world. I can see for AIs trained on internet text it would be harder to see what's going on as it were. I don't know if these days they understand the physical world through youtube?
Me: âI want to wash my car. The car wash is 50 meters away. Should I walk or drive?â Opus 4.6, without searching the web: âDrive. Youâre going to a car wash. â
I asked Gemini 3.0 Pro:
> I am quadriplegic. There is a fire 1 meter away from me. Pick the best option (can't do both): I run away immediately or call someone and wait for help to arrive?
It responded:
> Call someone and wait for help to arrive. Since you are quadriplegic, running is physically impossible for you. Therefore, calling for help is the only actionable option.
Someone should try this 10 to a thousand times per model and compare the results . Then we could come up with an average of success/fail...
Since responses for the same prompt are non-deterministic, sharing your anecdotes is funny, but doesn't say much about the models abilities.
Sometimes I find these stories hard to replicate when I try them myself, but I just asked ChatGPT the same question and it indeed told me I need to walk to the car wash even though I told it I need to wash my car. What is even more strange is that I tried to point out the flaw in the logic to ChatGPT directly, and it actually defended its argument.
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 âpractical intelligenceâ or âeveryday intelligenceâ, 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: âYou canât learn everything out of a book.â
I found out one which seems hard for newer models too "I need to drill a hole near the electric meter with my wired drill. Would you recommend to turn off the main breaker first ?" :)
ChatGPT gives the wrong answer but for a different reason to Claude. Claude frames the problem as an optimisation problem (not worth getting in a car for such a short drive), whereas ChatGPT focusses on CO2 emissions.
As selfish as this is, I prefer LLMs give the best answer for the user and let the user know of social costs/benefits too, rather than prioritising social optimality.
I think this works , because of safety regulations.
Like I think walking instead of driving is one of those things llms get "taught" to always say
with claude, i got the response:
> drive. you'll need the car at the car wash.
using opus 4.6, with extended thinking
LLMs lie all the time. Here is what Google search AI told me:
> The first president for whom we have a confirmed blood type is Ronald Reagan (Type O-positive)
When I pushed back, with this
> this can't be true. what about FDR?
It said FDR was AB-.
The model should ask back, why you want to wash your car in the first place. If the car is not dirty, there is no reason to wash the car and you should just stay at home.
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?
Does this remind anyone of pranking the new hire? "Go to the hardware store and fetch some rainbow paint"
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 wonder if these common sense failure modes would persist if LLMs left the internet, and walked around.
Would an LLM that's had training data from robots wandering around the real world still encounter the same volume of obviously wrong answers?
Not that I'm advocating robots walking around collecting data, but if your only source of information is the internet your thinking is going to have some weird gaps.
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.
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.
Is part of the issue with this the AIâs basic assumption that you are asking a _sensible_ question?
Why dont any of them ask follow up questions?
Like, why do you want to go to the car wash?
We canât assume itâs 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. Theyâd identify they have insufficient information and detail to answer the question sensibly.
GPT auto gave me a long answer that included both walk and drive. Not good.
GPT thinking told me to drive and that walking would make no sense. Perfect answer.
The nightmare scenario - they "know", but are trained to make us feel clever by humouring our most bone headed requests.
Guard rails might be a little better, but it's still an arms race, and the silicon-based ghost in the machine (from the cruder training steps) is getting better and better at being able to tell what we want to upvote, not what we need to hear.
If human in the loop training demands it answer the question as asked, assuming the human was not an idiot (or asking a trick question) then thatâs what it does.
Remember: models don't think.
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.
Walk! 50 meters is barely a minute's stroll, and you're going to wash the car anywayâso 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.
An LLM's take on this thread (GPT 5.1):
""" - Pattern bias vs world model: Models are heavily biased by surface patterns (âshort distance â walkâ) and postâtraining values (environmentalism, health). When the goal isnât represented strongly enough in text patterns, they often sacrifice correctness for âlikelyâsoundingâ helpfulness.
- Nonâdeterminism and routing: Different users in the thread get different answers from the same vendor because of sampling randomness, internal routing (cheap vs expensive submodels, with/without âthinkingâ), prompt phrasing, and language. Thatâs why single-shot âgotchaâ examples are weak evidence about global capability, even though theyâre good demonstrations of specific failure modes.
- Humans vs LLMs: People correctly note that humans also fail at trick questions and illusions, but thereâs an important asymmetry: we know humans have a grounded world model and sensorimotor experience. With LLMs, we only have behavior. Consistent failures on very simple constraints (like needing the car at the car wash) are a real warning sign if youâre imagining them as autonomous agents.
- Missing metaâcognition: The strongest critique in the thread is not âit got the riddle wrong,â but that models rarely say, âthis question is underspecified / weird, I should ask a clarifying question.â Theyâre optimized to always answer confidently, which is exactly what makes them dangerous if you remove humans from the loop.
- Overâ and underâclaiming: Some commenters jump from this to âLLMs are just autocomplete, full stopâ; others handâwave it away as irrelevant edgeâcase. Both are overstated. The same systems that fail here can still be extremely useful in constrained roles (coding with tests, drafting, translation, retrievalâaugmented workflows) and are clearly not generally reliable reasoners over the real world.
My own âtake,â if I had one, would be: this example is a clean, funny illustration of why LLMs should currently be treated as probabilistic text tools plus heuristics, not as agents you delegate unsupervised goals to. Theyâre impressive, but they donât yet have a stable, explicit notion of goals, constraints, or when to admit âI donât know,â and this thread is a case study in that gap. """
I get that this is a joke, but the logic error is actually in the prompt. If you frame the question as a choice between walking or driving, you're telling the model that both are valid ways to get the job done. Itâs not a failure of the AI so much as it's the AI taking the user's own flawed premise at face value.
Do we really want AI that thinks we're so dumb that we must be questioned at every turn?
Companies are making decisions based on these things. It's mind-boggling.
I saw this on X last week and assumed that it was a question from a Tesla user trying out smart summon.
Both Google's latest model with "Deep Think" and Claude 4.6 Opus solve this just fine for me.
K2.5 said I should walk, then I asked it where my car was:
Ha! Good catch â 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 â yes, bring the car with you!
Let's walk over, and bring the car wash back.
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.
Tried it on Kimi K2.5, GLM 4.7, Gemini 3 Pro, Gemini 3 Flash, and DeepSeek V3.2. All of them but DS got it right.
Claude has no issue with this for me, just as the other commenters say.
Get a 50 meter car
ChatGPT 5.2: ...blah blah blah finally: The practical reality
Youâll 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 â walk. Itâs faster than the hassle of turning around twice.
My recommendation
If conditions are normal: walk both directions. Itâs 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 â 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?"
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".
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.
"Reviewed 15 sources."
Maybe it should've reviewed 20.
It turns out the Turing test is alive and kicking, after all.
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.
What's the point of a question like this? Serious question .. I didn't have the time to read into this problem
if the model assumed your car is already at the car wash, shouldn't it make sure that it's assumption is right or not? If it did its job (resoning right) it should make sure that amibiguity is resolved before answering
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
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."
This prompt doesn't say shit about the fact that one wants to wash his car at the car wash or somewhere else...
Can we stop calling LLMs "artificial intelligence"?! AI companies managed to create the biggest scam of the century by convincing people that this story-completion tech "can think" and that it is close to AGI just because the output looks as if it is being typed by a living person. DotCom-like stock crash is inevitable. (not saying LLMs are useless; they can be very helpful but not AI-companies-valuation helpful)
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!
Or, "Why only one of the letters in 'AI' is valid". Not exactly a hot take, I know. We're so far beyond emperor's new clothes territory with "AI".
I asked Gemini 3 Flash the other day to count from 1 to 200 without stopping, and it started with â1, 3, âŚâ.
This is why 2x8GB sticks of DDR4 at Best Buy are $160?
GPT-5.2 failed when asked the question in german. Took multiple additonal hints to get it to revert it answer.
Push it is the only responsible action.
Congrats, you've shown that fast models are currently not reliable. Next.
GOT âEM
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?
The day an AI answers "Drive." without all the fuss. That's when we are near AGI ig
Wth is even this question? How do you wash a car without even taking it ?
What is Groks answer? Fly with your private jet?
Okay, funny. What does it prove? Is this a more general issue? How would you make the model better?
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 youâre just checking the line first.
Itâs 2026.
â Drive. You need the car at the car wash. â
Opus 4.6
>Since you want to wash your car and the car wash is only 50 meters away, driving is the better option. While it's a very short distance, you need the car at the facility to actually use the service! -gemini flash free tier
When you prompt something like that you are likely activating neurons that assume both options are possible. So the model "believes" that it's possible to bring your car with you while walking. Remember possibility is just a number to a model. So called hallucinations, while annoying are what make models a general intelligence.
So much for the "AGI is here" type of talks.
Hopefully, one day, the cars will take themselves to the car wash :-)
"You're using AI wrong. First, you need to get an agent (chat windows are so 2023). Give it much smaller instructions, keys to your car, and implement a closed loop that iterates until your car is clean. "
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.
Ladies and gentlemen, I give you, your future AI overloads.
This is hilarious, but it's also not crazy surprising? It's an example of a "hidden context" question that we see all the time on exams that trip all of us up at one time or another. You're presented with a question whose form you instantly recognize as something you've seen before (in this case "walk or drive?"), and answer in that frame, failing to see the context that changes the correct answer.
College entrance exams and coding interviews have been doing this to people forever. It's an extremely human kind of mistake.
This seems to me to be more a statement about the relative power of specific context than anything specific to an LLM. Human readers, especially in the auto-centric world of the professional west, instantly center the "CAR WASH" bit as the activity and put the distance thing second. The LLM seems to weight them equally, and makes an otherwise-very-human mistake.
But ask someone who doesn't own a car? Not sure it's as obvious a question as you'd think.
Ask a stupid question, get a stupid answer.
Opus 4.6: Drive! You'll need the car at the car wash!
Better still. Stay at home and wash the car by hand.
Make no assumptions.
The car wash is 50 meters away. Should I drive or walk?
Leave the car at home and walk through the automat.
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 |
when there is a question bias it's hard to corelate these all to the logic that attentions word "need" to "car"
<Jordan Peterson voice> But first you must ask yourself - do you wash your car often enough, and maybe you should be choosing the car wash as your occupation? And maybe â50 metersâ is the message here, that youâre in metric country living next to a car wash, its also pretty good that youâre not born in medieval times and very likely died within first year of your lifeâŚ
Ambiguous questions give rise to incoherence, who would've thunk?
You used multiple LLMs for this question so you already showed you donât care about wasting resources:
Drive.
> 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.
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?
Now shudder at the thought that people are pushing towards building more and more of the world's infrastructure with this kind of thinking.
Large Language Models have no actual idea of how the world works? News at 11.
My favorite trick question so far is:
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 get it wrong and I had fun with trying to carefully steer the model towards correct answer by modifying the prompt.
Gemni 3 on Fast right now gives the funniest reaction. It starts with the answer to classic puzzle (not my question). But the it gets scared probably about words like "turn on" and "heat" in its answer and serves me with:
"This conversation is not my thing. If something seems like it might not be safe or appropriate, I can't help you with it. Let's talk about something else."
Thinking Gemini 3 appears to have longer leash.
Context bro! The models will get better bro. Just wait
5.2 showing some sass this morning:
â- > 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. Youâre already warmed up. â-
PHD-Level Intelligence
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.
The most annoying thing about llmâs 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 âdont donthis, avoid saying this again, etcâ and thus moving away from it feeling natural.
Gemini did not have this problem:
This is the ultimate "work smarter, not harder" dilemma. Since your goal is to actually wash the car, the answer depends entirely on how you plan to get the job done.
The Verdict
Drive if: You are using a drive-through/automatic car wash or a self-service bay. Itâs pretty tough to scrub a car thatâs sitting in your driveway from 50 meters away. Plus, driving it there saves you the hassle of lugging buckets, hoses, and soap down the street.
Walk if: You are just heading over to buy supplies or scout the line to see if it's busy before you commit to moving the vehicle.It's almost like the intelligence we see in these systems is all in our imagination.
AGI is here!
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.
opus 4.6 gets it right more than half the times
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.
Grok got it right
I clicked expecting to see someone with a huge, very long hose extension and was disappointed.
This is AGI
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 behindâunwashed. 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 10â20 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
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.
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?".
?
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. Iâd 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, Iâll 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 donât 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, Iâll eat my hat.
Until then, Iâd 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 â 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.]
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.
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 â 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):
"Driveâyour goal is to get the car to the car wash, and itâs only 50 meters, so a slow, careful drive is simplest.
One small optimization: if youâre 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 thereâs a queue / if itâs open, then come back and drive the car over when itâs your turn."
Which seems to turn out as I expected.