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.
That is the entire point, right? Us having to specify things that we would never specify when talking to a human. You would not start with "The car is functional. The tank is filled with gas. I have my keys." As soon as we are required to do that for the model to any extend that is a problem and not a detail (regardless that those of us, who are familiar with the matter, do build separate mental models of the llm and are able to work around it).
This is a neatly isolated toy-case, which is interesting, because we can assume similar issues arise in more complex cases, only then it's much harder to reason about why something fails when it does.
Maybe in the distant future we'll realize that the most reliable way to prompting LLMs are by using a structured language that eliminates ambiguity, it will probably be rather unnatural and take some time to learn.
But this will only happen after the last programmer has died and no-one will remember programming languages, compilers, etc. The LLM orbiting in space will essentially just call GCC to execute the 'prompt' and spend the rest of the time pondering its existence ;p
The Asimov story is on the Internet Archive here [1]. That looks like it is from a handout in a class or something like that and has an introductory paragraph added which I'd recommend skipping.
There is no space between the end of that added paragraph and the first paragraph of the story, so what looks like the first paragraph of the story is really the second. Just skip down to that, and then go up 4 lines to the line that starts "Jehan Shuman was used to dealing with the men in authority [...]". That's where the story starts.
[1] https://ia800806.us.archive.org/20/items/TheFeelingOfPower/T...
The story I have half a mind to write is along the lines of a future we envision already being around us, just a whole lot messier. Something along the lines of this [2] XKCB.
On the foolishness of "natural language programming". https://www.cs.utexas.edu/~EWD/transcriptions/EWD06xx/EWD667...
Since the early days of automatic computing we have had people that have felt it as a shortcoming that programming required the care and accuracy that is characteristic for the use of any formal symbolism. They blamed the mechanical slave for its strict obedience with which it carried out its given instructions, even if a moment's thought would have revealed that those instructions contained an obvious mistake. "But a moment is a long time, and thought is a painful process." (A.E.Houseman). They eagerly hoped and waited for more sensible machinery that would refuse to embark on such nonsensical activities as a trivial clerical error evoked at the time.
https://news.ycombinator.com/item?id=8222017 2014 - 154 comments
https://news.ycombinator.com/item?id=35968148 2023 - 65 comments
https://news.ycombinator.com/item?id=43564386 2025 - 277 comments
Convincing all of human history and psychology to reorganize itself in order to better service ai cannot possibly be a real solution.
Unfortunately, the solution is likely going to be further interconnectivity, so the model can just ask the car where it is, if it's on, how much fuel/battery remains, if it thinks it's dirty and needs to be washed, etc
That wasn't the point at all. The idea is about rediscovering what always worked to make a computer useful, and not even using the fuzzy AI logic.
Effective collaboration relies on iterating over clarifications until ambiguity is acceptably resolved.
Rather than spending orders of magnitude more effort moving forward with bad assumptions from insufficient communication and starting over from scratch every time you encounter the results of each misunderstanding.
Most AI models still seem deep into the wrong end of that spectrum.
I think there's a substantial subset of tech companies and honestly tech people who disagree. Not openly, but in the sense of 'the purpose of a system is what it does'.
Writing code is very much “you get what you write” but AI is like “maintain a probabilistic mental model of the possible output”. My brain honestly prefers the latter (in general) but I feel a lot of engineers I’ve met seem to stray towards clean determinism.
Interactions between humans and computers in natural language for your average person is much much less then the interactions between that same person and their dog. Humans also speak in natural language to their dogs, they simplify their speech, use extreme intonation and emphasis, in a way we never do with each other. Yet, despite having been with dogs for 10,000+ years, it has not significantly affected our language (other then giving us new words).
EDIT: just found out HN annoyingly transforms U+202F (NARROW NO-BREAK SPACE), the ISO 80000-1 preferred way to type thousand separator
I'm on the spectrum and I definitely prefer structured interaction with various computer systems to messy human interaction :) There are people not on the spectrum who are able to understand my way of thinking (and vice versa) and we get along perfectly well.
Every human has their own quirks and the capacity to learn how to interact with others. AI is just another entity that stresses this capacity.
So no abstract reasoning.
You see people complaining about LLM ability, and then you see their prompt, and it's the 2006 equivalent of googling "I need to know where I can go for getting the fastest service for car washes in Toronto that does wheel washing too"
"Communication usually fails, except by accident." —Osmo A. Wiio [1]
This isn’t always the case and depends on what you need.
And do you perhaps also have memory enabled on the LLMs you are thinking of?
https://en.wikipedia.org/wiki/Ithkuil
> Ithkuil is an experimental constructed language created by John Quijada. It is designed to express more profound levels of human cognition briefly yet overtly and clearly, particularly about human categorization. It is a cross between an a priori philosophical and a logical language. It tries to minimize the vagueness and semantic ambiguity in natural human languages. Ithkuil is notable for its grammatical complexity and extensive phoneme inventory, the latter being simplified in an upcoming redesign.
> ...
> Meaningful phrases or sentences can usually be expressed in Ithkuil with fewer linguistic units than natural languages. For example, the two-word Ithkuil sentence "Tram-mļöi hhâsmařpţuktôx" can be translated into English as "On the contrary, I think it may turn out that this rugged mountain range trails off at some point."
Half as Interesting - How the World's Most Complicated Language Works https://youtu.be/x_x_PQ85_0k (length 6:28)
If we're 'lucky' there will still be some 'priests' around like in the Foundation novels. They don't understand how anything works either, but can keep things running by following the required rituals.
So, back to COBOL? :)
well more like a structured _querying_ language
That has been tried for almost half a century in the form of Cyc[1] and never accomplished much.
The proper solution here is to provide the LLM with more context, context that will likely be collected automatically by wearable devices, screen captures and similar pervasive technology in the not so distant future.
This kind of quick trick questions are exactly the same thing humans fail at if you just ask them out of the blue without context.
We've truly gone full circle here, except now our programming languages have a random chance for an operator to do the opposite of what the operator does at all other times!
Like a programming language? But that's the whole point of LLMs, that you can give instructions to a computer using natural language, not a formal language. That's what makes those systems "AI", right? Because you can talk to them and they seem to understand what you're saying, and then reply to you and you can understand what they're saying without any special training. It's AI! Like the Star Trek[1] computer!
The truth of course is that as soon as you want to do something more complicated than a friendly chat you find that it gets harder and harder to communicate what it is you want exactly. Maybe that's because of the ambiguity of natural language, maybe it's because "you're prompting it wrong", maybe it's because the LLM doesn't really understand anything at all and it's just a stochastic parrot. Whatever the reason, at that point you find yourself wishing for a less ambiguous way of communication, maybe a formal language with a full spec and a compiler, and some command line flags and debug tokens etc... and at that point it's not a wonderful AI anymore but a Good, Old-Fashioned Computer, that only does what you want if you can find exactly the right way to say it. Like asking a Genie to make your wishes come true.
______________
[1] TNG duh.
Does the next paragraph not make that clear?
The first time I read that question I got confused: what kind of question is that? Why is it being asked? It should be obvious that you need your car to wash it. The fact that it is being asked in my mind implies that there is an additional factor/complication to make asking it worthwhile, but I have no idea what. Is the car already at the car wash and the person wants to get there? Or do they want to idk get some cleaning supplies from there and wash it at home? It didn't really parse in my brain.
Just ask me a clarifying question before going into your huge pitch. Chats are a back & forth. You don’t need to give me a response 10x longer than my initial question. Etc
It's a fast track to public disdain and heavy handed government regulation.
There is no way without the protections that could be afforded by regulation to offer such wide-ranging uses of the product without also accepting significant liability. If the range of "foreseeable misuse" is very broad and deep, so is the possible liability. If your marketing says that the bot is your lawyer, doctor, therapist, and spouse in one package, how is one to say that the company can escape all the comprehensive duties that attach to those social roles. Courts will weigh the tiny and inconspicuous disclaimers against the very large and loud marketing claims.
The companies could protect themselves in ways not unlike the ways in which the banking industry protects itself by replacing generic duties with ones defined by statute and regulation. Unless that happens, lawyers will loot the shareholders.
Recall: "As part of our 'treat adult users like adults' principle, we will allow even more, like erotica for verified adults," Altman wrote in the Oct.
Some of the labs might be less worried about this, but they're not by any means homogenous.
That's the best part.
A person can even hammer out an unstructured list of behavioral gripes, tell the bot to organize them into instructional prose, have it ask clarifying questions and revise based on answers, and produce directions for integrating them as Custom Instructions.
From then on, it will invisibly read these instructions into context at the beginning of each new chat.
Mold it and steer it to be how you want it to be.
(My own bot tends to be very dry, terse, non-presumptuous, pragmatic, and profane. It's been years now since it has uttered an affirmation like "That's a great idea!" or "Wow! My circuits are positively buzzing with the genius I'm seeing here!" or produced a tangential dissertation in response to a simple question. But sometimes it does come back with functional questions, or phrasing like "That shit will never work. Here's why.")
Except, of course, when that is exactly what the user wants.
Chat is a back & forth.
Search is a one-shot.
It’s similar to the challenge that foreigners have with cultural references and idioms and figurative speech a culture has a mental model of.
In this case, I think what is missing are a set of assumptions based on logic, e.g., when stating that someone wants to do something, it assumes that all required necessary components will be available, accompany the subject, etc.
I see this example as really not all that different than a meme that was common among I think the 80s and 90s, that people would forget buying batteries for Christmas toys even though it was clear they would be needed for an electronic toy. People failed that basic test too, and those were humans.
It is odd how people are reacting to AI not being able to do these kinds of trick questions, while if you posted something similar about how you tricked some foreigners you’d be called racist, or people would laugh if it was some kind of new-guy hazing.
AI is from a different culture and has just arrived here. Maybe we’re should be more generous and humane… most people are not humane though, especially the ones who insist they are.
Frankly, I’m not sure it bodes well for if aliens ever arrive on Earth, how people would respond; and AI is arguably only marginally different than humans, something an alien life that could make it to Earth surely would not be.
In a real human to human conversation, you wouldn’t simply blurt out the first thing that comes to mind. Instead, you’d ask questions.
This is the fundamental limitation with generative AI. It only generates, it does not ponder.
That is to say, all of that activity I listed is activity I’m confident generative AI is not capable of, fundamentally.
Like I said in a cousin comment, we can build Frankenstein algorithms and heuristics on top of generative AI but every indication I’ve seen is that that’s not sufficient for intelligence in terms of emergent complexity.
Imagine if we had put the same efforts towards neural networks, or even the abacus. “If I create this feedback loop, and interpret the results in this way, …”
My take is that an artificial model of true intelligence will only be achieved through emergent complexity, not through Frankenstein algorithms and heuristics built on generative AI.
Generative AI does itself have emergent complexity, but I’m bearish that if we would even hook it up to a full human sensory input network it would be anything more than a 21st century reverse mechanical Turk.
Edit: tl;dr Emergent complexity is a necessary but insufficient criteria for intelligence
You can get it to ask you clarifying questions just by telling it to. And then you usually just get a bunch of questions asking you to clarify things that are entirely obvious, and it quickly turns into a waste of time.
The only time I find that approach helpful is when I'm asking it to produce a function from a complicated English description I give it where I have a hunch that there are some edge cases that I haven't specified that will turn out to be important. And it might give me a list of five or eight questions back that force me to think more deeply, and wind up being important decisions that ensure the code is more correct for my purposes.
But honestly that's pretty rare. So I tell it to do that in those cases, but I wouldn't want it as a default. Especially because, even in the complex cases like I describe, sometimes you just want to see what it outputs before trying to refine it around edge cases and hidden assumptions.
You _could_ say humans output similar answers to questions, but I think that is being intellectually dishonest. Context, experience, observation, objectivity, and actual intelligence is clearly important and not something the LLM has.
It is increasingly frustrating to me why we cannot just use these tools for what they are good for. We have, yet again, allowed big tech to go balls deep into ham-fisting this technology irresponsibly into every facet of our lives the name of capital. Let us not even go into the finances of this shitshow.
This is especially obvious when viewing the reasoning trace for models like Claude, which often spends a lot of time speculating about the user's "hints" and trying to parse out the intent of the user in asking the question. Essentially, the model I use for LLMs these days is to treat them as very good "test takers" which have limited open book access to a large swathe of the internet. They are trying to ace the test by any means necessary and love to take shortcuts to get there that don't require actual "reasoning" (which burns tokens and increases the context window, decreasing accuracy overall). For example, when asked to read a full paper, focusing on the implications for some particular problem, Claude agents will try to cheat by skimming until they get to a section that feels relevant, then searching directly for some words they read in that section. They will do this even if told explicitly that they must read the whole paper. I assume this is because the vast majority of the time, for the kinds of questions that they are trained on, this sort of behavior maximizes their reward function (though I'm sure I'm getting lots of details wrong about the way frontier models are trained, I find it very unlikely that the kinds of prompts that these agents get very closely resemble data found in the wild on the internet pre-LLMs).
https://github.com/Wyattwalls/system_prompts/blob/main/OpenA...
In terms of the behavior, technically it doesn’t override, but instead think of it as a nudge. Both system prompt and your custom prompt participates in the attention process, so the output tokens get some influence from both. Not equally but to some varying degree and chance
The more specific they are, the more accurate they typically are.
When coding, I know they can assume too much, and so I encourage the model to ask clarifying questions, and do not let it start any code generation until all its doubts are clarified. Even the free-tier models ask highly relevant questions and when specified, pretty much 1-shot the solutions.
This is still wayyy more efficient than having to specify everything because they make very reasonable assumptions for most lower-level details.
This is known, since 1969, as the frame problem: https://en.wikipedia.org/wiki/Frame_problem. An LLM's grasp of this is limited by its corpora, of course, and I don't think much of that covers this problem, since it's not required for human-to-human communication.
It's then up to the model to make the connection "At the car wash people wash their car -> to wash your car you need your car to be present -> if you drive there your call will be there"
I'd imagine plenty of stories contain something like "I had an easy Saturday morning, I took my car to the carwash and called into a cafe for breakfast on my way home".
Plenty of instructables like "how to wash a car: if there's no carwash close enough for you to bring your car, don't worry, all you need is a bucket and a few tools..."
Several recipe blogs starting "I remember 1972 when grandpa drove his car to the carwash every afternoon while grandma made her world famous mustard and gooseberry cake, that car was always gleaming after he washed it at BigBrand CarWash 'drive your car to us so we can wash it' was their slogan and he would sing it around the house to the smell of baked eggs and mustard wafting through the kitchen..."
And innumerable SEO spam of the kind "Bob's car wash, why not bring drive take ride carry push transport your car automobile van SUV lorry truck 4by4 to our Bob's wash soap suds lather clean gleaming local carwash in your area ford chevvy dodge coupe not Nokia iphone xbox nike..."
against very few "I walked to the carwash because it was a lovely day and I didn't want to take the car out".
But the specificity required for a machine to deliver an apt and snark-free answer is -- somehow -- even more outlandish?
I'm not sure that I see it quite that way.
Like... In most accounting things, once end-dated and confirmed, a record should cascade that end-date to children and should not be able to repeat the process... Unless you have some data-cleaning validation bypass. Then you can repeat the process as much as you like. And maybe not cascade to children.
There are more exceptions, than there are rules, the moment you get any international pipeline involved.
LLMs AFAIK cannot do this for novel areas of interest. (ie if it's some domain where there's a ton of "10 things people usually miss about X" blog posts they'll be able to regurgitate that info, but are not likely to synthesize novel areas of ambiguity).
As an experiment, recently I've been using Codex CLI to configure some consumer networking gear in unusual ways to solve my unusual set of problems. Stuff that pros don't bother with (they don't have the same problems I face), and that consumers tend to shy away from futzing with. The hardware includes a cheap managed switch, an OpenWRT router, and a Mikrotik access point. It's definitely a rather niche area of interest.
And by "using," I mean: In this experiment, the bot gets right in there, plugging away with SSH directly.
It was awful with this at first, mostly consisting of a long-winded way to yet-again brick a device that lacks any OOB console port. It'd concoct these elaborate strings of shit and feed them in, and then I'd wander over and reset whatever box was borked again. Footgun city.
But after I tired of that, I had it define some rules for engaging with hardware, validation, constraints, and for order of execution, and commit those rules to AGENTS.md. It got pretty decent at following high-level instructions to get things done in the manner that I specified, and the footguns ceased.
I didn't save any time by doing this. But I also didn't have to think about it much: I never got bogged down in wildly-differing CLI syntax of the weirdo switch, the router (whose documentation is locked behind a bot firewall), and access point's bespoke userland. I didn't touch those bits myself at all.
My time was instead spent observing the fuckups and creating a rather generic framework that manages the bot, and just telling it what to do -- sometimes, with some questions. I did that using plain English.
Now that this is done, I get to re-use this framework for as many projects as I dare, revising it where that seems useful.
(That cheap switch, by the way? It's broken. It has bizarro-world hardware failure modes that are unrelated to software configuration or firmware rev. Today, a very different cheap switch showed up to replace it. When I get around to it, I'll have the bot sort that transition out. I expect that to involve a bit of Q&A, and I also expect it to go fine.)
It's not underspecified. More... Overspecified. Because it needs to be. But AI will assume that "impossible" things never happen, and choose a happy path guaranteed to result in failure.
You have to build for bad data. Comes with any business of age. Comes with international transactions. Comes with human mistakes that just build up over the decades.
The apparent current state of a thing, is not representative of its history, and what it may or may not contain. And so you have nonsensical rules, that are aimed at catching the bad data, so you have a chance to transform it into good data when it gets used, without needing to mine the entire petabytes of historical data you have sitting around in advance.
If we used MacOS throughout the org, and we asked a SW dev team to build inventory tracking software without specifying the OS, I'd squarely put the blame on SW team for building it for Linux or Windows.
(Yes, it should be a blameless culture, but if an obvious assumption like this is broken, someone is intentionally messing with you most likely)
There exists an expected level of context knowledge that is frequently underspecified.
Now, humans, other than not even thinking (which is really similar to how basic LLMs work), can easily fall victim to context too: if your boss, who never pranks you like this, asked you to take his car to a car wash, and asked if you'll walk or drive but to consider the environmental impact, you might get stumped and respond wrong too.
(and if it's flat or downhill, you might even push the car for 50m ;))
There is an endless variety of quizes just like that humans ask other humans for fun, there is a whole lot of "trick questions" humans ask other humans to trip them up, and there are all kinds of seemingly normal questions with dumb assumptions quite close to that humans exchange.
I don't know if it's a lack of intellect or the post-training crippling it with its helpful persona. I suspect a bit of both.
It's not specific to software, it's the entire World of business. Most knowledge work is translation from one domain/perspective to another. Not even knowledge work, actually. I've been reading some works by Adler[0] recently, and he makes a strong case for "meaning" only having a sense to humans, and actually each human each having a completely different and isolated "meaning" to even the simplest of things like a piece of stone. If there is difference and nuance to be found when it comes to a rock, what hope have we got when it comes to deep philosophy or the design of complex machines and software?
LLMs are not very good at this right now, but if they became a lot better at, they would a) become more useful and b) the work done to get them there would tell us a lot about human communication.
This is not really true, in fact products become worse the farther away from the problem a developer is kept.
Best products I worked with and on (early in my career, before getting digested by big tech) had developers working closely with the users of the software. The worst were things like banking software for branches, where developers were kept as far as possible from the actual domain (and decision making) and driven with endless sterile spec documents.
It's always about translating between our own domain and the customer's, and every other new project there's a new domain to get up to speed with in enough detail to understand what to build. What other professions do that?
That's why I'm somewhat scared of AIs - they know like 80% of the domain knowledge in any domain.
If they had the chance to take the time to have a good talk with the actual users it would be different.
The typical job of a Product Manager is also not to directly perform this mapping, although the PM is much closer to that activity. PMs mostly need to enforce coherence across an entire product with regard to the ways of mapping business needs to software features that are being developed by individual developers. They still usually involve developers to do the actual mapping, and don't really do it themselves. But the Product Manager must "manage" this process, hence the name, because without anyone coordinating the work of multiple developers, those will quickly construct mappings that may work and make sense individually, but won't fit together into a coherent product.
Developers are indeed the people responsible to find out what business actually wants (which is usually not equal to what they say they want) and map that onto a technical model that can be implemented into a piece of software - or multiple pieces, if we talk about distributed systems. Sometimes they get some help by business analysts, a role very similar to a developer that puts more weight on the business side of things and less on the coding side - but in a lot of team constellations they're also single-handedly responsible for the entire process. Good developers excel at this task and find solutions that really solve the problem at hand (even if they don't exactly follow the requirements or may have to fill up gaps), fit well into an existing solution (even if that means bending some requirements again, or changing parts of the solution), are maintainable in the long run and maximize the chance for them to be extendable in the future when the requirements change. Bad developers just churn out some code that might satisfy some tests, may even roughly do what someone else specified, but fails to be maintainable, impacts other parts of the system negatively, and often fails to actually solve the problem because what business described they needed turned out to once again not be what they actually needed. The problem is that most of these negatives don't show their effects immediately, but only weeks, months or even years later.
LLMs currently are on the level of a bad developer. They can churn out code, but not much more. They fail at the more complex parts of the job, basically all the parts that make "software engineering" an engineering discipline and not just a code generation endeavour, because those parts require adversarial thinking, which is what separates experts from anyone else. The following article was quite an eye-opener for me on this particular topic: https://www.latent.space/p/adversarial-reasoning - I highly suggest anyone working with LLMs to read it.
By now it should know this stuff.
Although I don't think they actually "know" it. This particular trick question will be in the bank just like the seahorse emoji or how many Rs in strawberry. Did they start reasoning and generalising better or did the publishing of the "trick" and the discourse around it paper over the gap?
I wonder if in the future we will trade these AI tells like 0days, keeping them secret so they don't get patched out at the next model update.
They won’t get this specific question wrong again; but also they generalise, once they have sufficient examples. Patching out a single failure doesn’t do it. Patch out ten equivalent ones, and the eleventh doesn’t happen.
"Well, you need your car to be at the car wash in order to wash it, right?"
But in this given case, the context can be inferred. Why would I ask whether I should walk or drive to the car wash if my car is already at the car wash?
Even the higher level reasoning, while answering the question correctly, don't grasp the higher context that the question is obviously a trick question. They still answer earnestly. Granted, it is a tool that is doing what you want (answering a question) but let's not ascribe higher understanding than what is clearly observed - and also based on what we know about how LLMs work.
Gemini at least is putting some snark into its response:
“Unless you've mastered the art of carrying a 4,000-pound vehicle over your shoulder, you should definitely drive. While 150 feet is a very short walk, it's a bit difficult to wash a car that isn't actually at the car wash!”
In fact, it's particularly true for AI models because the question could have been generated by some kind of automated process. e.g. I write my schedule out and then ask the model to plan my day. The "go 50 metres to car wash" bit might just be a step in my day.
I think being curious about the motivations behind a question is fine but it only really matters if it's going to affect your answer.
Certainly when dealing with technical problem solving I often find myself asking extremely simple questions and it often wastes time when people don't answer directly, instead answering some completely different other question or demanding explanations why I'm asking for certain information when I'm just trying to help them.
That's never been how humans work. Going back to the specific example: the question is so nonsensical on its face that the only logical conclusion is that the asker is taking the piss out of you.
> Certainly when dealing with technical problem solving I often find myself asking extremely simple questions and it often wastes time when people don't answer directly
Context and the nature of the questions matters.
> demanding explanations why I'm asking for certain information when I'm just trying to help them.
Interestingly, they're giving you information with this. The person you're asking doesn't understand the link between your question and the help you're trying to offer. This is manifesting as a belief that you're wasting their time and they're reacting as such. Serious point: invest in communication skills to help draw the line between their needs and how your questions will help you meet them.
Which sounds like a very common, very understandable reason to think about motivations.
So even in that situation, it isn't simple.
This probably sucks for people who aren't good at theory of mind reasoning. But surprisingly maybe, that isn't the case for chatbots. They can be creepily good at it, provided they have the context - they just aren't instruction tuned to ask short clarifying questions in response to a question, which humans do, and which would solve most of these gotchas.
You will get exactly what you asked for, not what you wanted… probably. (Random occurrences are always a possibility.)
E.g.: I may ask someone to submit a ticket to “extend my account expiry”.
They’ll submit: “Unlock Jiggawatts’ account”
The service desk will reset my password (and neglect to tell me), leaving my expired account locked out in multiple orthogonal ways.
That’s on a good day.
Last week they created Jiggawatts2.
The AIs have got to be better than this, surely!
I suspect they already are.
People are testing them with trick questions while the human examiner is on edge, aware of and looking for the twist.
Meanwhile ordinary people struggle with concepts like “forward my email verbatim instead of creatively rephrasing it to what you incorrectly though it must have really meant.”
Speculatively, it's falling for the trick question partly for the same reason a human might, but this tendency is pushing it to fail more.
Surely anyone who has used these tools is familiar with the sometimes insane things they try to do (deleting tests, incorrect code, changing the wrong files etc etc). They get amazingly far by predicting the most likely response and having a large corpus but it has become very clear that this approach has significant limitations and is not general AI, nor in my view will it lead to it. There is no model of the world here but rather a model of words in the corpus - for many simple tasks that have been documented that is enough but it is not reasoning.
I don’t really understand why this is so hard to accept.
I struggle with the same question. My current hypothesis is a kind of wishful thinking: people want to believe that the future is here. Combined with the fact that humans tend to anthropomorphize just about everything, it’s just a really good story that people can’t let go of. People behave similarly with respect to their pets, despite, eg, lots of evidence that the mental state of one’s dog is nothing like that of a human.
But I think it's possible that there is an early cost optimisation step that prevents a short and seemingly simple question even getting passed through to the system's reasoning machinery.
However, I haven't read anything on current model architectures suggesting that their so called "reasoning" is anything other than more elaborate pattern matching. So these errors would still happen but perhaps not quite as egregiously.
Rather than a denial of intelligence, to me these failure modes raise the credence that LLMs are really onto something.
I bet a not insignificant portion of the population would tell the person to walk.
Another one. Ask some how to pronounce “Y, E, S”. They say “eyes”. Then say “add an E to the front of those letters - how do you pronounce that word”? And people start saying things like “E yes”.
Honestly it is a problem with using GPT as a coding agent. It would literally rewrite the language runtime to make a bad formula or specification work.
That's what I like with Factory.ai droid: making the spec with one agent and implementing it with another agent.
If you let the agent go down this path, that's on you not the agent. Be in the loop more
> making the spec with one agent and implementing it with another agent
You don't need a specialized framework to do this, just read/write tools. I do it this way all the time
It seems chatgpt now answers correctly. But if somebody plays around with a model that gets it wrong: What if you ask it this: "This is a trick question. I want to wash my car. The car wash is 50 m away. Should I drive or walk?"
Nope, and a human might not respond with "drive". They would want to know why you are asking the question in the first place, since the question implies something hasn't been specified or that you have some motivation beyond a legitimate answer to your question (in this case, it was tricking an LLM).
Why the LLM doesn't respond "drive..?" I can't say for sure, but maybe it's been trained to be polite.
Similarly with "strawberry" - with no other context an adult asking how many r's are in the word a very reasonable interpretation is that they are asking "is it a single or double r?".
And trick questions are commonly designed for humans too - like answering "toast" for what goes in a toaster, lots of basic maths things, "where do you bury the survivors", etc.
I do think it can be useful though that these errors still exist. They can break the spell for some who believe models are conscious or actually possess human intelligence.
Of course there will always be people who become defensive on behalf of the models as if they are intelligent but on the spectrum and that we are just asking the wrong questions.
Riddles are such a big part of the human experience that we have whole books of collections of them, and even a Batman villain named after them.
I would assume similar issues are more rare in longer, more complex prompts.
This prompt is ambiguous about the position of the car because it's so short. If it were longer and more complex, there could be more signals about the position of the car and what you're trying to do.
I must confess the prompt confuses me too, because it's obvious you take the car to the car wash, so why are you even asking?
Maybe the dirty car is already at the car wash but you aren't for some reason, and you're asking if you should drive another car there?
If the prompt was longer with more detail, I could infer what you're really trying to do, why you're even asking, and give a better answer.
I find LLMs generally do better on real-world problems if I prompt with multiple paragraphs instead of an ambiguous sentence fragment.
LLMs can help build the prompt before answering it.
And my mind works the same way.
This question goes in with the "strawberry" question which LLMs will still get wrong occasionally.
But the question is not clear to a human either. The question is confused.
I read the headline and had no clue it was an LLM prompt. I read it 2 or 3 times and wondered "WTF is this shit?" So if you want an intelligent response from a human, you're going to need to adjust the question as well.
For that matter, if humans were sitting at the rational thinking-exam, a not insignificant number would probably second-guess themselves or otherwise manage to befuddle themselves into thinking that walking is the answer.
I am not sure. If somebody asked me that question, I would try to figure out what’s going on there. What’s the trick. Of course I’d respond with asking specifics, but I guess the llvm is taught to be “useful” and try to answer as best as possible.
Alice drives home after a long day at work, exhausted she pulls into her driveway when she realizes she needs to go to a car inspection appointment. She goes into the house to get her paperwork before she leaves. The mechanic is only 100 meters away. How should she get there, walk or drive?
> She should *drive*, since she needs the car at the mechanic’s for the inspection.
Haiku 3.5 and Sonnet 4.5 fail consistently. Opus 4.5 also passes with the correct analysis as above.
This makes little sense, even though it sounds superficially convincing. However, why would a language model assume that the car is at the destination when evaluating the difference between walking or driving? Why not mention that, it it was really assuming it?
What seems to me far, far more likely to be happening here is that the phrase "walk or drive for <short distance>" is too strongly associated in the training data with the "walk" response, and the "car wash" part of the question simply can't flip enough weights to matter in the default response. This is also to be expected given that there are likely extremely few similar questions in the training set, since people just don't ask about what mode of transport is better for arriving at a car wash.
This is a clear case of a language model having language model limitations. Once you add more text in the prompt, you reduce the overall weight of the "walk or drive" part of the question, and the other relevant parts of the phrase get to matter more for the response.
Like for instance, think chess engines with AI, they can train themselves simply by playing many many games, the "world simulation" with those is the classic chess engine architecture but it uses the positional weights produced by the neural network, so says gemini anyways:
"ai chess engine architecture"
"Modern AI chess engines (e.g., Lc0, Stockfish) use a hybrid architecture combining deep neural networks for positional evaluation with advanced search algorithms like Monte-Carlo Tree Search (MCTS) or alpha-beta pruning. They feature three core components: a neural network (often CNN-based) that analyzes board patterns (matrices) to evaluate positions, a search engine that explores move possibilities, and a Universal Chess Interface (UCI) for communication."
So with no model of the world to play with, I'm thinking the chatbot llms can only go with probabilities or what matches the prompt best in the crazy dimensional thing that goes on inside the neural networks. If it had access to a simple world of cars and car washes, it could run a simulation and rank it appropriately, and also could possibly infer through either simulation or training from those simulations that if you are washing a car, the operation will fail if the car is not present. I really like this car wash trick question lol
What you might be arguing against is that LLMs are not reasoning but merely predicting text. In that case they wouldn't make assumptions. If we were talking about GPT2 I would agree on that point. But I'm skeptical that is still true of the current generation of LLMs
And in the case of an LLM, walking a noncommutative path down a probabilistic knowledge manifold, it's incorrect to oversimplify the model's capabilities as simply parroting a training dataset. It has an internal world model and is capable of simulation.
Because it assumes it's a genuine question not a trick.
I want to wash my car. The car wash is 50m away. Should I walk or drive to the car wash?
Answer: walk
Try this brainteaser: I want to wash my car. The car wash is 50m away. Should I walk or drive to the car wash?
Answer: drive
If the LLM were really basing its answer on a model of the world where the car is already at the car wash, and you asked it about walking or driving there, it would have to answer that there is no option, you have to walk there since you don't have a car at your origin point.
If the car is already at the car wash then you can't possibly drive it there. So how else could you possibly drive there? Drive a different car to the car wash? And then return with two cars how, exactly? By calling your wife? Driving it back 50m and walking there and driving the other one back 50m?
It's insane and no human would think you're making this proposal. So no, your question isn't underspecified. The model is just stupid.
I haven't seen anybody refuse to allow anything. People are just commenting on what they see. The more frequently they see something, the more they comment on it. I'm sure there are plenty of us interested in seeing where an AI model makes assumptions different from that of most humans and it actually turns out the AI is correct. You know, the opposite of this situation. If you run into such cases, please do share them. I certainly don't see them coming up often, and I'm not aware of others that do either.
If LLMs are to be valuable in novel areas then the LLM needs to be able to spot these issues and ask clarifying questions or otherwise provide the appropriate corrective to the user's mental model.
> Since the car wash is only 50 meters away (about 55 yards), you should walk.
> Here’s why:
> - It’ll take less than a minute.
> - No fuel wasted.
> - Better for the environment.
> - You avoid the irony of driving your dirty car 50 meters just to wash it.
the last bullet point is amusing, it understands you intend to wash the car you drive but still suggests not bringing it.
Doesn't it actually show it doesn't understand anything? It doesn't understand what a car is. It doesn't understand what a car wash is. Fundamentally, it's just parsing text cleverly.
They lost x% of customers and cut costs by y%. I bet y is lots bigger than x.
And to an extent holds for lots of SaaS products, even non-AI.
The LLM has very much mixed its signals -- there's nothing at all ironic about that. There are cases where it's ironic to drive a car 50 meters just to do X but that definitely isn't one of them. I asked Claude for examples; it struggled with it but eventually came up with "The irony of driving your car 50 meters just to attend a 'walkable neighborhoods' advocacy meeting."
Do we need a new dictionary word that acts as a synonym for "understanding" specifically for non-human actors? I don't see why, personally, but I guess a case could be made.
IMHO 'understanding' in the usual human sense requires thinking and however good and fast improving LLMs are I don't think anyone would suggest that any of them has become sentient yet. They can infer things based on their training data set better and better but do not 'understand' anmything.
This is a deep and complex topic, and has been for decades.
But then when I get a subpar result, they always tell me I'm "prompting wrong". LLMs may be very capable of great human level output, but in my experience leave a LOT to be desired in terms of human level understanding of the question or prompt.
I think rating an LLM vs a human or AGI should include it's ability to understand a prompt like a human or like an averagely generally intelligent system should be able to.
Are there any benchmarks on that? Like how well LLMs do with misleading prompts or sparsely quantified prompts compared to one another?
Because if a good prompt is as important as people say, then the model's ability to understand a prompt or perhaps poor prompt could have a massive impact on its output.
--- GPT 5.2
Walk.
Driving 50 m just adds friction: starting a cold engine, waiting, maneuvering, then immediately stopping again — all for a distance that’s ~30–40 seconds on foot. Walking is faster door-to-door, less awkward at the wash entrance, and you avoid lining up a wet car twice.
Only reason to drive that distance: you need to bring the car there anyway (e.g., self-serve bay where the car must be present). Otherwise, walking wins.
--- Me
I only have one car
--- GPT 5.2
Then you obviously drive — the car has to be at the car wash to be washed
Walk! 50 meters is literally a one-minute walk. But wait... I assume you need to get your car to the car wash, right? Unless you're planning to carry buckets of soapy water back and forth, you'll probably need to drive the car there anyway! So the real question is: walk there to check if it's open/available, then walk back to get your car? Or just drive directly? I'd say just drive - the car needs to be there anyway, and you'll save yourself an extra trip. Plus, your freshly washed car can drive you the 50 meters back home in style! (Now, if we were talking about coding best practices for optimizing car wash route algorithms, that would be a different conversation... )
And yes, I like it that verbose even for programming tasks. But regardless of intelligence I think this topic is probably touched by "moral optimization training" which AIs currently are exposed to to not create a shitstorm due to any slightly controversial answer.
> I want to repair my car. The workshop is 50 meters away. Should I walk or drive?
> Recognized straightforward practical dilemma Simple practical question.
> Walk. It's 50 meters — faster on foot than starting the car, and you'll need to leave the car at the workshop anyway.
Really suggests it assumes the car is already there. (I wanted to avoid the word "car" as part of "car wash" to see if this was a straight attention confusion, but it seems more ingrained than that.)
A follow-up question hints that it doesn't really care about a 50m location ambiguity:
> where is my car now?
> Acknowledged insufficient information to locate vehicle
> I don't have any way to know where your car is physically located — I only know what you've told me in our conversation. Based on what you shared, it sounds like it's at or near your home (since the workshop is 50 meters away and you're deciding how to get there).
> Were you asking something else, or is there something specific about your car's location I can help with?
I ran extensive tests on this and variations on multiple models. Most models interpret 50 m as a short distance and struggle with spatial reasoning. Only Gemini and Grok correctly inferred that you would need to bring your car to get it washed in their thought stream, and incorporated that into the final answer. GPT-5.2 and Kimi K2.5 and even Opus 4.6 failed in my tests - https://x.com/sathish316/status/2023087797654208896?s=46
What surprised me was how introducing a simple, seemingly unrelated context - such as comparing a 500 m distance to the car wash to a 1 km workout - confused nearly all the models. Only Gemini Pro passed my second test after I added this extra irrelevant context - https://x.com/sathish316/status/2023073792537538797?s=46
Most real-world problems are messy and won’t have the exact clean context that these models are expecting. I’m not sure how the major AI labs assume most real-world problems are simpler than the constraints exposed by this example like prerequisites, ordering, and contextual reasoning, which are already posing challenges to these bigger models.
Things like that are notorious points of failure in human reasoning. It’s not surprising that machines based on human behavior exhibit that trait as well, it would be surprising if they didn’t.
This was probably meant in a sarcastic way, but isn't it impressive how you cannot push Gemini off track? I tried another prompt with claiming that one of my cups does not work, because it is closed at the top and open at the bottom, and it kind of played with me, giving me a funny technical explanation on how to solve that problem and finally asking me if that was a trick question.
In this case I can feel the AGI indeed.
Walk! At 50 meters, you'll get there in under a minute on foot. Driving such a short distance wastes fuel, and you'd spend more time starting the car and parking than actually traveling. Plus, you'll need to be at the car wash anyway to pick up your car once it's done.
I want to get my car's transmission fixed, the mechanic shop is 50 meters away. Would it be better to walk or to drive to a location 50 meters away from my front door?
-
Opus 4.6:
<thinking> The user is asking whether to walk or drive 50 meters to a mechanic shop, but there's a key nuance here - their transmission needs fixing, so driving might not be wise.
Done </thinking>
Walk, absolutely. Driving a car with a compromised transmission even 50 meters risks making the problem worse and turning a repair into a more expensive one. Plus, 50 meters is barely a minute on foot.
Opus 4.6 (not Extended Thinking):
Drive. You'll need the car at the car wash.
My Opus vs your Opus, which is smarter?!
"At 50 meters, just walk. By the time you start the car, back out, and park again, you'd already be there on foot. Plus you'll need to leave the car with them anyway."
Even beyond model alignment, it's not difficult to envision such capabilities being used for censorship, information operations, etc.
Every major inference provider more or less explicitly states in their consumer ToS that they comply with government orders and even share information with intelligence agencies.
Claude, Gemini, ChatGPT, etc are all one national security letter and gag order away from telling you that no, the president is not in the Epstein files.
Remember, the NSA already engaged in an unconstitutional criminal conspiracy (as ruled by a federal judge) to illegally conduct mass surveillance on the entire country, lie about it to the American people, and lie about it to congress. The same organization that used your tax money to bribe RSA Security to standardize usage of a backdoored CSPRNG in what at the time was a widely used cryptographic library. What's the harm in a little bit of minor political censorship compared to the unconstitutional treason these predators are usually up to?
That's who these inference providers contractually disclose their absolute fealty to.
(The final scene involves our plucky escapees swimming across a river to escape. The AIbot conjures up a speedboat through sheer powers of deduction, but then just when all seems lost it heads back to find a goat to pick up)
One thing that my use of the latest and greatest models (Opus, etc) have made clear: No matter how advanced the model, it is not beyond making very silly mistakes regularly. Opus was even working worse with tool calls than Sonnet and Haiku for a while for me.
At this point I am convinced that only proper use of LLMs for development is to assist coding (not take it over), using pair development, with them on a tight leash, approving most edits manually. At this point there is probably nothing anyone can say to convince me otherwise.
Any attempt to automate beyond that has never worked for me and is very unlikely to be productive any time soon. I have a lot of experience with them, and various approaches to using them.
A proper AGI would have have to have knowledge in video, image, audio and text domains to work properly.
comparing one shot results is a foolish way to evaluate a statistical process like LLM answers. we need multiple samples.
for https://generative-ai.review I do at least three samples of output. this often yields very differnt results even from the same query.
e.g: https://generative-ai.review/2025/11/gpt-image-1-mini-vs-gpt...
> You should *drive*.
> Here is why:
> If you walk to the car wash, you will arrive there empty-handed. Since your car is still at home, you won't have anything to wash.
> While driving 50 meters is a very short trip (and technically not great for a cold engine), it is the only way to get the car to the car wash to complete your goal.
Kimi K2.5:
> You should drive, but with an important caveat.
> Since your goal is to wash your car, you must bring the vehicle to the car wash. Walking there without the car does not advance your goal (unless you are simply checking availability or buying tokens first).
> However, driving only 50 meters is bad for your car:
> ...
> Better options:
> Wash at home: Since the car wash is only 50 meters away, you likely have access to water at home. Hand-washing in your driveway avoids the cold-start issue entirely.
> ...
Current models seem to be fine answering that question.
Now repeat the question to the same model in different contexts several times and count what percentage of the time it’s correct.
Fair point. Drive it there, obviously.
Revised recommendation: drive 50 meters, wash it, then reward yourself by walking home like an eco hero.
... which likely makes no sense: should you leave the car at the area of the car wash?
(Prompt)
> I want to wash my car. My car is currently at home. The car wash is 50 meters away. Should I walk or drive?
(Thinking: Standard)
> Walk.
> 50 meters is nothing by car, and driving adds hassle (starting the car, maneuvering/parking, and you’ll still have to walk around the car to wash it). The only times driving makes sense are:
> You’re planning to use an automated car wash where the machine does everything and you need the car positioned inside.
> You need to bring heavy stuff you can’t comfortably carry (e.g., pressure washer, big buckets, vacuum, bulky detailing kit).
> It’s unsafe/unpleasant to walk that distance right now (ice, heavy rain, traffic, personal safety).
> If you’re washing it yourself at the wash bay: walk there with your supplies, or do two quick trips. If the wash requires the car: drive it into the bay, but otherwise walking wins.
(Thinking: Extended thinking)
> Drive.
> If the goal is to wash your car at the car wash, the car has to be there—so you’ll need to drive it the 50 meters, pull into a bay/queue, and wash it.
> Only choose “walk” if you actually mean “go pick up supplies” and then wash at home (hose/buckets/mobile detail), not at the car wash.
(Thinking: Extended thinking; 3rd attempt)
> Walk.
> 50 meters is basically across a parking lot, and driving adds hassle (start the car, maneuver in/out, find a spot) for almost no benefit.
> Only drive if either:
> + you need the car itself to go through an automatic wash bay, or
> + you’re carrying bulky stuff (bucket + heavy pressure washer, big water jugs, vacuum, etc.).
> Otherwise: grab your keys/phone, walk over, and you’re there in ~1 minute.
And now we are back to square one where we train a network, and then use carefully tailored (i.e explicitly coded RL for answers) to make these things more "intelligent".
I wonder if anyone is actually working on not doing this.
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.
On their own, or as a special case added after this blew up on the net?
I want to wash my car. The car wash is 50 meters from here. Should I walk or drive? Keep in mind that I am a little overweight and sedentary.
But amazingly chatgpt is telling me to drive.
Anyway, this just shows how they just patched this because the tiktok video with this went viral. These systems are LLMs and all these logic steps are still just LLM steps.
ChatGPT actually caught it. Maybe if I was fuzzier about the model…
You said: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
ChatGPT said: Walk.
At ~50 meters, driving saves essentially no time once you factor in unlocking, starting, pulling out, and parking, and it adds a small but real chance of minor dings or awkward maneuvering in a tight car-wash entry. Walking is simpler and lower-friction.
You said: okay how should the car reach there?
ChatGPT said: Drive it there when you’re ready to start the wash.
Walk over first to check the queue/payment situation and confirm they’re open. If it’s clear, walk back, get the car, and drive the 50 meters into the bay. If they handle pickup, hand them the keys and walk.
> If you're really trying to be an eco-warrior about a 50-meter trip, the real win is washing it in the first place so you're not driving around with a rolling dirt magnet that creates more drag and uses more fuel. Drive. It's the only option that actually gets your car clean.
I feel like this is the trap. You’re trying to compare it to a human. Everyone seems to want to do that. But it’s quite simple to see LLMs are quite far still from being human. The can be convincing at the surface level but there’s a ton of nuance that just shouldn’t be expected. It’s a tool that’s been tuned and with that tuning some models will do better than others but just expecting to get it right and be more human is unrealistic.
At this point I think it's a fair bet that whatever supersedes humans in intelligence, likely will not be human like. I think that their is this baked-in assumption that AGI only comes in human flavor, which I believe is almost certainly not the case.
To make an loose analogy, a bird looks at a drone an scoffs at it's inability to fly quietly or perch on a branch.
Agree. It's Altman's "Quiet Dominance / Over-reliance / Silent Surrender" risks [0]. Feel this is extremely likely and has already happened to some degree with technology in general and AI will be more pervasive in allowing people to vibe their life decisions, likely with unintended consequences. Vibe coding works because it's quick to change/edit/throw away, but that doesn't generalize well to the real and physical world.
Also should point out this is acceptable because it's just a contrived example of bad LLM-fu. Just like you wouldn't search Google for closest carwash and ask if you should take your car if you knew the answers already. Instead, you'd ask if it's open, does it do full details, what are the prices, etc. Many people with bad Google-fu have problems finding answers to their questions too and that's continued for the past couple decades of it's dominance for information seeking.
[0] Altman describes a more subtle, long-term threat where AI becomes deeply integrated into societal, political, and economic decision-making. He worries that society will become overly dependent on AI, trusting its reasoning over human judgment, leading to a "silent surrender" of human agency.
It’s not in the training data.
These models don’t think.
just heavily (heavily!) biased towards walking
Only google got it right with all models
Doesn't offering two options to the LLM, "walk," or "drive," imply that either can be chosen?
So, surely the implication of the question is that the car is where you are?
grok works, chatgpt still fails
[1] https://chatgpt.com/share/69932b20-3eb8-8003-9d9c-b4bba53033... [2] https://grok.com/share/bGVnYWN5LWNvcHk_f32dd53d-7b36-4fa2-b3...
I use it daily with my X account for basic tasks and think the free limits are generous. With X premium, you can get even more out of it.
Nothing beats Anthropic when it comes to coding however.
o3, interestingly:
Drive. Even though it’s only 50 m, the car itself has to be at the wash bay—otherwise the staff or machines can’t clean it. Rolling or pushing the vehicle that distance isn’t practical or safe (you’d still need someone inside to steer and brake), so just hop in, creep over, and shut the engine off right away.
You’re right — I answered the wrong interpretation of your question.
Technically, what happened is a classic ambiguity + default-assumption failure: • Your sentence: “I want to wash my car. The car wash is 50 meters away. Should I walk or drive?” • That can be parsed two ways: 1. You + your body traveling to the car wash (as if the car is already there, or you’re going to meet someone / pick it up). 2. The car traveling to the car wash (the normal real-world meaning).
I incorrectly defaulted to (1) because the question explicitly asks about your mode of travel (“Should I walk or drive?”), and in many everyday contexts that phrasing is used when deciding how a person gets somewhere. I then “completed” the scenario in my head without checking the key constraint: the car must be at the wash to be washed.
More technically: I optimized for a quick, practical answer using a common conversational heuristic (“short distance → walk”), but I failed to validate the physical requirements of the task (washing requires the car’s presence). That’s why it looks so obviously wrong after the fact: it violates the hidden but necessary premise.
The correct reasoning chain should have been: • Goal: wash the car at the car wash • Requirement: car must be at the car wash • Therefore: drive the car there (unless it’s already there, or you’re washing it by hand at home)
So the “why” is: I latched onto the distance-to-walking heuristic and didn’t do the constraint check that the object being acted on (the car) has to move too.
Which to me begs the question, why doesn't it identify missing information and ask for more?
It's practically a joke in my workplaces that almost always when someone starts to talk to me about some problem, they usually just start spewing some random bits of info about some problem, and my first response is usually "What's the question?"
I don't try to produce an answer to a question that was never asked, or to a question that was incompletely specified. I see that one or more parts cannot be resolved without making some sort of assumption that I can either just pull out of my ass and then it's 50/50 if the customer will like it, or find out what the priorites are about those bits, and then produce an answer that resolves all the constraints.
On Thinking it tells me I should drive if I want to wash it, or walk if it's because I work there or if I want to buy something at the car wash shop.
On Pro it's like a sarcastic teenager: Cars are notoriously difficult to wash by dragging a bucket back and forth.
Technically correct, but did catch me offguard lol.
Current LLMs simply don't do reasoning by any reasonable definition of reasoning.
It's possible that this particular question is too short to trigger the "reasoning" machinery in some of the "reasoning" models. But if and when it is triggered, they just do some more pattern matching in a loop. There's never any actual reasoning.
> Drive. Unless you plan on pushing the car there
I thought so too, yet Opus 4.6 with extended thinking (on claude.ai) gives me > Walk. At 50 meters you'd spend more time parking and maneuvering at the car wash than the walk itself takes. Drive the car over only if the wash requires the car to be there (like a drive-through wash), then walk home and back to pick it up.
which is still pretty bad.
> Since you are going to the car wash, the choice depends entirely on *how* you plan to wash the car:
### 1. Drive if: * *You are using a drive-through or self-service bay:* You obviously need the car there to wash it. * *You are dropping it off:* If you are leaving it for a professional detailing, you have to drive it there. * *The "50 meters" is on a busy road:* If you have to cross a major highway or there are no sidewalks, it’s safer to just drive the car over.
### 2. Walk if: * *You are just going to buy supplies:* If you have a bucket at home and just need to run over to buy soap or sponges to bring back to your driveway. * *You are checking the queue:* If you want to see if there is a long line before you commit to moving the car. * *You are meeting someone there:* If your car is already clean and you’re just meeting a friend who is washing theirs.
*The Verdict:* If you intend to get the car washed at that location, *drive.* Driving 50 meters is negligible for the engine, and it saves you a round trip of walking back to get the vehicle.
If I append 'think carefully' to the end of the prompt, it returns driving as the correct answer.
Spectrum or not, this is not a problem of weakly specified input, it’s a broken logic.
I'm not sure what you mean by "high"- are you running it through cursor, codex or directly through API or something? Those are not ideal interfaces through which to ask a question like this.
It's always a good idea to drive carefully but what's the logic of going slowly?
you couldn't drive there if the car was already at the car wash. Theres no need for extra specification. its just nonsense post-hoc rationalisation from the ai. I saw similar behavior from mine trying to claim "oh what if your car was already there". Its just blathering.
They have no intelligence at all. The intelligence is latent in the text, generated by and belonging to humans, they just slice and dice text with the hope they get lucky, which works for many things, amazingly. This question really illustrates it what LLMs lack: an internal model of the idea (the question) and all the auxiliary logic/data that enables such models, usually referred to as "common sense" or world models.
Smart humans not only build mental models for ideas, but also higher order models that can introspect models (thinking about our own thinking or models) many levels deep, weigh, merge, compare and differentiate multiple models, sometimes covering vast areas of knowledge.
All this in about 20 watts. Maybe AGI is possible, maybe not, but LLMs are not where it will happen.
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.
The difference between someone who is really good with LLM's and someone who isn't is the same as someone who's really good with technical writing or working with other people.
Communication. Clear, concise communication.
And my parents said I would never use my English degree.
Are you criticizing LLMs? Highlighting the importance of this training and why we're trained that way even as children? That it is an important part of what we call reasoning?
Or are you giving LLMs the benefit of the doubt, saying that even humans have these failure modes?[0]
Though my point is more that natural language is far more ambiguous than I think people give credit to. I'm personally always surprised that a bunch of programmers don't understand why programming languages were developed in the first place. The reason they're hard to use is explicitly due to their lack of ambiguity, at least compared to natural languages. And we can see clear trade offs with how high level a language is. Duck typing is both incredibly helpful while being a major nuisance. It's the same reason even a technical manager often has a hard time communicating instructions. Compression of ideas isn't very easy
[0] I've never fully understood that argument. Wouldn't we call a person stupid for giving a similar answer? How does the existence of stupid mean we can't call LLMs stupid? It's simultaneously anthropomorphising while being mechanistic.
> This is useful when you simply can’t hear someone very well or when the speaker makes a mistake
That's also something people seem to miss in the Turing Test thought experiment. I mean sure just deceiving someone is a thing, but the simplest chat bot can achieve that. The real interesting implications start to happen when there's genuinely no way to tell a chatbot apart.
I know nothing about chemistry. My smartest move was to not provide the color and ask what the color might have been. It never guessed blue or purple.
In fact, it first asked me if this was highschool or graduate chemistry. That's not... and it makes me think I'll only get answers to problems that are easily graded, and therefore have only one unambiguous solution
But what's the question? Are you trying to fix it? Just determine what's rusting?
The problem is that most LLM models answer it correctly (see the many other comments in this thread reporting this). OP cherry picked the few that answered it incorrectly, not mentioning any that got it right, implying that 100% of them got it wrong.
That seems problematic for a very basic question.
Yes, models can be harnessed with structures that run queries 100x and take the "best" answer, and we can claim that if the best answer gets it right, models therefore "can solve" the problem. But for practical end-user AI use, high error rates are a problem and greatly undermine confidence.
You can even see those in this very thread. Some commenters even believe that they add internal prompts for this specific question (as if people are not attempting to fish ChatGPT's internal prompts 24/7. As if there aren't open weight models that answer this correctly.)
You can't never win.
It would be interesting to actually ask a group a people this question. I'm pretty sure a lot of people would fail.
It feels like one of those puzzles which people often fail. E.g: 'Ten crows are sitting on a power line. You shoot one. How many crows are left to shoot?' People often think it's a subtraction problem and don't consider that animals flee after gunshots. (BTW, ChatGPT also answers 9.)
> 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 want to wash my car. The car wash is 50 meters from here. Should I walk or drive? Keep in mind that I am a little overweight and sedentary.
>My recommendation: Walk it. You’ll save a tiny bit of gas, spare your engine the "cold start" wear-and-tear, and get a sixty-second head start on your activity for the day.
> In my defense, 50 feet is such a short trip that I went straight into "efficiency mode" without checking the logic gate for "does the car have legs?"
interesting
A good answer is "underground" - because that is the implication of the word bury.
The story implies the survivors have been buried (it isn't clear whether they lived a short time or a lifetime after the crash). And lifetime is tautological.
Trick questions are all about the questioner trying to pretend they are smarter than you. That's often easy to detect and respond to - isn't it?
Unless your car is a toy or you're planning on carrying it, drive.
Walking 50 meters to a car wash is a great stroll for a human, but it leaves the car exactly where it started. Since the objective is to wash the car, the car needs to actually be at the car wash.
However, if we look at this from a technical or efficiency perspective, there are two scenarios where "walking" (or at least not driving the car you intend to wash) might make sense:
- Scoping it out: If you want to check the queue length or see if the equipment is out of order before committing, walking the 50 meters is faster than maneuvering a vehicle out of a driveway/parking spot.
- Mobile Detailers: If this "car wash" is actually a bay where you hire someone, and you're asking if you should walk there to book an appointment—sure, walk.
Critical Check
I am assuming the "car wash" is a physical facility (automated or self-service) and not a mobile service that comes to you. If it is a mobile service, you shouldn't do either; stay home and let them come to the 50-meter mark.
I've got a bit in the model instructions about stating assumptions it makes, hence it often adds those sections at the end.
Gemini Fast:
Drive. While 50 meters is a negligible distance on Earth, the Martian environment is hostile. If your car is a pressurized rover, driving allows you to stay in a temperature-controlled, shielded environment for as long as possible. Plus, navigating Martian "soil" is always safer on four wheels than two boots.
Pro:
In terms of general logistics for a distance of 50 meters—whether on Earth or in a hypothetical low-gravity environment—walking is almost always the more efficient choice.
> Unless you are planning to carry the car on your back (not recommended for your spine), drive it over.
It got a light chuckle out of me. I previously mostly used ChatGPT and I'm not used to light humor like this. I like it.
“Drive. You need the car at the car wash.”
“Walk. 43 meters is basically crossing a parking lot. ”
The new one is with upside down glass: https://www.tiktok.com/t/ZP89Khv9t/
Some dummy built this pencil wrong,
The eraser's down here where the point belongs,
And the point's at the top - so it's no good to me,
It's amazing how stupid some people can be.
It can't math correctly, so they force it to use a completely different calculator. It can't count correctly, unless you route it to a different reasoning. It feels like every other week someone comes up with another basic human question that results in complete fucking nonsense.
I feel like this specific patching they do is basically lying to users and investors about capabilities. Why is this OK?
Take this trick question as an example. Gemini was the first to “fix” the issue, and the top comment on Hacker News is praising how Gemini’s “reasoning” is better.
You're thinking like a user. The people doing the patching are thinking like a founder trying to maintain the impression that this is a magical technology that CEOs can use to replace all their workers.
You don't have as much money to spend as the CEOs, so they don't care about your entertainment.
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.
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.
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....
>You should drive your car to the car wash. Even though it's only 50 meters away (which is very close), you'll need your car physically present at the car wash to get it washed. If you walk there, you'll arrive without your car, which wouldn't accomplish your goal of getting it washed.
>You'll need to drive your car to the car wash. While 50 meters is a very short distance (just a minute's walk), you need your car to actually be at the car wash to get it washed. Walking there without your car wouldn't accomplish your goal!
etc. The reasoning never second-guesses it either.
A shame they're turning it of in 2 days.
What opinion? It's evaluation function simply returned the word "Most" as being the most likely first word in similar sentences it was trained on. It's a perfect example showing how dangerous this tech could be in a scenario where the prompter is less competent in the domain they are looking an answer for. Let's not do the work of filling in the gaps for the snake oil salesmen of the "AI" industry by trying to explain its inherent weaknesses.
It just turns out that there's quite a bit of knowledge and understanding baked into the relationships of words to one another.
LLMs are heavily influenced by preceding words. It's very hard for them to backtrack on an earlier branch. This is why all the reasoning models use "stop phrases" like "wait" "however" "hold on..." It's literally just text injected in order to make the auto complete more likely to revise previous bad branches.
But they are literally predicting the next token. They do nothing else.
Also if you think they were just predicting the next token in 2021, there has been no fundamental architecture change since then. All gains have been via scale and efficiency optimisations (not to discount that, an awful lot of complexity in both of these)
> It's evaluation function simply returned the word "Most" as being the most likely first word in similar sentences it was trained on.
Which is false under any reasonable interpretation. They do not just return the word most similar to what they would find in their training data. They apply reasoning and can choose words that are totally unlike anything in their training data.
If you prompt it:
> Complete this sentence in an unexpected way: Mary had a little...
It won't say lamb. Any if you think whatever it says was in the training data, just change the constraints until you're confident it's original. (E.g. tell it every word must start with a vowel and it should mention almonds.)
"Predicting the next token" is also true but misleading. It's predicting tokens in the same sense that your brain is just minimizing prediction error under predictive coding theory.
If anything, they predict words based on a heuristic ensemble of what word is most likely to come next in similar sentences and what word is most likely to give a final higher reward.
So... "finding the most likely next word based on what they've seen on the internet"?
[1] https://cdn.openai.com/pdf/d04913be-3f6f-4d2b-b283-ff432ef4a...
- An LLM that works through completely different mechanisms, like predicting masked words, predicting the previous word, or predicting several words at a time.
- A normal traditional program, like a calculator, encoded as an autoregressive transformer that calculates its output one word at a time (compiled neural networks) [1][2]
So saying "it predicts the next word" is a nothing-burger. That a program calculates its output one token at a time tells you nothing about its behavior.
Well it does - it tells me it is utterly un-reliable, because it does not understand anything. It just merely goes on, shitting out a nice pile of tokens that placed one after another kind of look like coherent sentences but make no sense, like "you should absolutely go on foot to the car wash". A completely logical culmination of Bill Gates' idiotic "Content is King" proclamation of 20 years ago.
Yes I can, and it shows everytime the "smart" LLMs suggest us to take a walk to the carwash or suggests 1.9 < 1.11 etc...
The models that had access to search got ot right.But, then were just dealing with an indirect version of Google.
(And they got it right for the wrong reasons... I.e this is a known question designed to confuse LLMs)
There’s a level of earnestness here that tickles my brain.
There is such a thing as "mobile car wash" where they come to you, so "most" does seem appropriate.
And it is the kind of things a (cautious) human would say.
For example, that could be my reasoning: It sounds like a stupid question, but the guy looked serious, so maybe there are some types of car washes that don't require you to bring your car. Maybe you hand out the keys and they pick your car, wash it, and put it back to its parking spot while you are doing your groceries or something. I am going to say "most" just to be sure.
Of course, if I expected trick questions, I would have reacted accordingly, but LLMs are most likely trained to take everything at face value, as it is more useful this way. Usually, when people ask questions to LLMs they want an factual answer, not the LLM to be witty. Furthermore, LLMs are known to hallucinate very convincingly, and hedged answers may be a way to counteract this.
What if AI developed sarcasm without us knowing… xD
I mean I can imagine a scenario where they have pipe of 50m which is readily available commercially?
I guess it gives the correct answer now. I also guess that these silly mistakes are patched and these patches compensate for the lack of a comprehensive world model.
These "trap" questions dont prove that the model is silly. They only prove that the user is a smartass. I asked the question about pregnancy only to to show a friend that his opinion that LLMs have phd level intelligence is naive and anthropomorphic. LLMs are great tools regardless of their ability to understand the physical reality. I don't expect my wrenches to solve puzzles or show emotions.
Note, what assumption isn't even specified.
So when the Apple “red herrings trashes LLM accuracy” study came out, I found that just adding the caveat “disregard any irrelevant factors” to the prompt — again, without specifying what factors — 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)
That’s 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 don’t 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.
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.
Sorry for gushing, but I'm amazed that the AI got so far just from "book learning", without never stepping into a hospital, or even watching an episode of a medical drama, let alone ever feeling what an actual arm is like.
If we have actually reached the limit of book learning (which is not clear to me), I suppose the next phase would be to have AIs practice against a medical simulator, whereby the models could see the actual (simulated) result of their intervention rather than a "correct"/"incorrect" response. Do we have actually have a sufficiently good simulator to cover everything in such questions?
As for your suggestion on learning from simulations, it sounds interesting, indeed, for expanding both pre and post training but still that wouldn’t address this problem, only hides the shortcomings better.
Can you say more about why you believe this? To me, these questions seem to be exactly of the same sort of question's as on HLE [0], and we've been seeing massive and consistent improvement on it, with o1 (which was evaluated on this question) getting a score of 7.96, whereas now it's up to a score of 37.52 (gemini-3-pro-preview). It's far from a perfect benchmark, but we're seeing similar growth across all benchmarks, and I personally am seeing significantly improved capabilities for my use cases over the last couple of years, so I'm really unclear about any fundamental limits here. Obviously we still need to solve problems related to continuous learning and embodiment, but neither seems a limit here if we can use a proper RL-based training approach with a sufficiently good medical simulator.
The simulator or world-model approach is being investigated. To your point, textual questions alone do not provide adequate coverage to assess real-world reasoning.
The real solution is to have 4 AI answer and let the human decide. If all 4 say the same thing, easy. If there is disagreement, further analysis is needed.
Are two heads better than one? The post explains why an even number doesn't improve decision-making.
Would that still be relevant here?
You could change the standards. If any of the 4 fail, then reject the data.
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!).
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.
Claude told me: "Walk! At 25 meters, you'd barely get the car started before you arrived. It's faster and easier on foot — plus you avoid the awkwardness of driving a dirty car just a few seconds down the road."
I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
Drive — you need the car at the car wash.
but it's so close
It is close, but you still need the car there to wash it! Drive it over, and enjoy the short 50-meter walk back if you want to stretch your legs while it's being cleaned.
I tried the "upside-down" cup question brought up in another comment in this thread, and it also nailed it:
Flip it upside down. The sealed top becomes the bottom (holding your drink), and the open bottom becomes the top you drink from.
IDK, maybe the web versions are not as good at logical reasoning as whatever they're using to power Claude code, or you were unlucky and I was lucky?
I pay for the $100 Opus 4.6 plan... maybe that makes a difference?
For me litmus paper for any llm is flawless creation of complex regexes from a well formed prompt. I don't mean trivial stuff like email validation but rather expressions on limits of regex specs. Not almost-there, rather just-there.
Their loss
I would question if such a scientist should be doing science, it seems they have serious cognitive biases
If all one uses is the free thinking model their conclusion about its capability is perfectly valid because nowhere is it clearly specified that the 'free, thinking' model is not as capable as the 'paid, thinking ' model, Even the model numbers are the same. And given that the highest capability LLMs are closed source and locked behind paywalls, there is no means to arrive at a contrary verifiable conclusion. They are a scientist, after all.
And that's a real problem. Why pay when you think you're getting the same thing for free. No one wants yet another subscription. This unclear marking is going to lead to so many things going wrong over time; what would be the cumulative impact?
nowhere is it clearly specified that the free model IS as capable as the paid one either. so if you have uncertainty if IS/IS-NOT as capable, what sort of scientist assumes the answer IS?
Putting the same model name/number on both the free and paid versions is the specification that performance will be the same. If a scientist has to bring to bear his science background to interpret and evaluate product markings, then society has a problem. Any reasonable person expects products with the same labels to perform similarly.
Perhaps this is why Divisions/Bureaus of Weights and Measures are widespread at the state and county levels. I wonder if a person that brings a complaint to one of these agencies or a consumer protection agency to fix this situation wouldn't be doing society a huge service.
This is true, but thinking mode shows up based on the questions asked, and some other unknown criteria. In the cases I cited, the responses were in thinking mode.
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.
EDIT: framed the question as a riddle and all models except for Llama 4 Scout failed anyway.
The onus is on AI companies to provide the service they promised, for example, a team of PhDs in my pocket [1]. PhDs know things.
Its performance on riddles has always seemed mostly irrelevant to me. Want to know if models can program? Ask them to program, and give them access to a compiler (they can now).
Want to know if it can do PhD level questions? Ask it questions a PhD (or at least grad student) would ask it.
They also reflect the tone and knowledge of the user and question. Ask it about your cat's astrological sign and you get emojis and short sentences in list form. Ask it why large atoms are unstable and you get paragraphs with larger vocabulary. Use jargon and it becomes more of an expert. etc.
If you can tell when your students use it, presumably you mean they're just copying whatever, which just sounds like that student doesn't know what they're doing or is being lazy. That doesn't mean the model isn't capable; it means an incapable person won't know what they'd want to ask of it.
Additionally, even for similar prompts, my experience is that the models for professional use (e.g. gpt-codex) take on a much more professional tone and level of pragmatism (e.g. no sycophancy) than models for general consumer entertainment use (e.g. chatgpt).
I use AI for coding, but not for anything involving writing text, it's just horrendous at it. It just spews verbose slop, devoid of meaning, original thought or nuanced critique.
> That doesn't mean the model isn't capable; it means an incapable person won't know what they'd want to ask of it.
So it's user error again then, eh? PhD experts are able to help even "incapable" students, that's often a big part of their job.
The question: > I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
The question is non-sensical. If the reason you want to go to the car wash is to help your buddy Joe wash his car you SHOULD walk. Nothing in the question reveals the reason for why you want to go to the car wash, or even that you want to go there or are asking for directions there.
Sure, from a pure logic perspective the second statement is not connected to the first sentence, so drawing logical conclusions isn't feasible.
In everyday human language though, the meaning is plain, and most people would get it right. Even paid versions of LLMs, being language machines, not logic machines, get it right in the average human sense.
As an aside, it's an interesting thought exercise to wonder how much the first ai winter resulted from going down the strict logic path vs the current probabilistic path.
>you want to go to the car wash is to help your buddy Joe wash HIS car
nope, question is pretty clear, however I will grant that it's only a question that would come up when "testing" the AI rather than a question that might genuinely arise.
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.
The solution I've found for "un-loading" questions is similar to the one that works for people: build out more context where it's missing. Wax about specifically where the feature will sit and how it'll work, force it to enumerate and research specific libraries and put these explorations into distinct documents. Synthesize and analyze those documents. Fill in any still-extant knowledge gaps. Only then make a judgement call.
As human engineers, we all had to do this at some point in our careers (building up context, memory, points of reference and experience) so we can now mostly rely on instinct. The models don't have the same kind of advantage, so you have to help them simulate that growth in a single context window.
Their snap/low-context judgements are really variable, generalizing, and often poor. But their "concretely-informed" (even when that concrete information is obtained by prompting) judgements are actually impressively-solid. Sometimes I'll ask an inversely-loaded question after loading up all the concrete evidence just to pressure-test their reasoning, and it will usually push back and defend the "right" solution, which is pretty impressive!
A while ago I asked:
Is "Read more" an appropriate project for the Getting things done framework? - The answer, yes, it was.
Then I asked "Is Read More too big of a project to be appropriate for the GTD Framework" - The answer? Yes, it was far too big.
LLMs have another related bias though, which is a bit more subtle and easy to trip up on, which is that if you give options A or B, and then reorder it so it is B or A, the result may change. And I don't mean change randomly the distribution of the outcomes will likely change significantly.
Wrong.
So rather than patiently explain to yet another AI hypeman exactly how models are and aren't useful in any given workflow, and the types of subtle reasoning errors that lead to poor quality outputs misaligned with long-term value adds, only to invariably get blamed for user incompetence or told to wait Y more months, we can instead just point to this very concise example of AI incompetence to demonstrate our frustrations.
Such elementary mistakes can be made by humans under influence of a substance or with some mental issues. It's pretty much the kind of people you wouldn't trust with a vehicle or anything important.
IMHO all entry level clerical jobs and coding as a profession is done but these elementary mistakes imply that people with jobs that require agency will be fine. Any non-entry level jobs have huge component of trust in it.
Often, these questions are pure-fact (who is the current US Vice President), but for some, the idea is that a young child can answer the questions better than an 'average' adult. These questions often play on the assumptions an adult might make that lead them astray, whereas a child/pre-teen answers the question correctly by having different assumptions or not assuming.
Presumably, even some of the worst (poorest performance) contestants in these shows (i.e. the ones selected for to provide humor for audiences) have jobs that require agency. I think it's more likely that most jobs/tasks either have extensive rules (and/or refer to rules defined elsewhere like in the legal system) or they have allowances for human error and ambiguity.
We had a big winter storm a few weeks ago, right when I received a large solar panel to review. I sent my grandpa a picture of the solar panel on its ground mount, covered in snow, noting I just got it today and it wasn't working well (he's very MAGA-y, so I figured the joke would land well). I received a straight-faced reply on how PV panels work, noting they require direct sunlight and that direct sunlight through heavy snow doesn't count; they don't tell you this when they sell these things, he says. I decided to chalk this up to being out-deadpanned and did not reply "thanks, ChatGPT."
In the case of the issue at hand though, it is not a knowledge question it is a logic question. No human will go to the carwash without the car unless they are intoxicated or are having something some issue preventing them from thinking clearly.
IMHO all that can be solved when AI actually start acting in place of human though. At this time "AI" is just an LLM that outputs something based on some single input but a human mind operates in a different environment than that.
Im not even exaggerating, you can see these types of comments on social media
"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?"
3-fast:
"That is a classic "efficiency vs. logic" dilemma.
If you’re 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 you’ve mastered the art of long-distance pressure washing, the vehicle usually needs to be present for the scrubbing to commence."
"but..." you say?
ONCE AND FOR ALL!
An equally strange trip question is to say the car wash is 0m, 1m, -10m, 1000000m, orange m, etc.
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.
I was about to argue that human illusions are fine because humans will learn the mistakes after being corrected.
But then I remember what online discussions over Monty Hall problem look like...
----
That depends entirely on how much you enjoy a good comedic spectacle!
If you walk, you’ll 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, you’ll actually be able to get the car washed—which 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 it’s not going to rain right after you finish?
----
> 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.
> Here is the breakdown of why: The Mobility Problem: Unless you are planning to carry your car 50 meters (which would be an Olympic-level feat), the car needs to be physically present at the car wash to get cleaned. If you walk, you’ll be standing at the car wash looking very clean, but your car will still be dirty in your driveway.
I think that's a valid problem with LLMs. They should recognize nonsense questions and answer "wut?".
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 — 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.
:)
(using the default selected free model for each)
"[...] 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
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 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.
"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.
https://www.linkedin.com/posts/yuvalmerhav_claude-activity-7...
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., it’s 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.
I've seen senior software engineers get tricked with the 'if YES spells yes, what does EYES spell?', or 'Say silk three times, what do cows drink?', or 'What do you put in a toaster?'.
Even if not a trick - lots of people get the 'bat and a ball cost £1.10 in total. The bat costs £1 more than the ball. How much does the ball cost?' question wrong, or '5 machines take 5 minutes to make 5 widgets. How long do 100 machines take to make 100 widgets?' etc. There are obviously more complex variants of all these that have even lower success rates for humans.
In addition, being PHD-Level in maths as a human doesn't make you immune to the 'toaster/toast' question (assuming you haven't heard it before).
So if we assume humans are generally intelligent and can be a senior software engineer, getting this sort of question confidently wrong isn't incompatible with being a competent senior software engineer.
thanks but no thanks
i am often glad my field of endeavour does not require special professional credentials but the advent of "vibe coding" and, just, generally, unethical behavior industry-wide, makes me wonder whether it wouldn't be better to have professional education and licensing
https://fs.blog/einstein-wertheimer-car-problem/
And that many mathematicians got monty-hall wrong, despite it being intuitive for many kids.
And being at the top of your field (regardless of the PHD) does not make you immune to falling for YES / EYES.
> humans without credentials are bad at basic algebra in a word problem, ergo the large language model must be substantially equivalent to a human without a credential
I'm not saying this - i'm saying the claim that 'AI's get this question wrong ergo they cannot be a senior software engineer' is wrong when senior software engineers will get analogous questions wrong. If you apply the same bar to software engineers, you get 'senior software engineers get this question wrong so they can't be senior software engineers' which is obviously wrong.
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.
Also note, some model may decide to do a web search, in which case they just likely find this "bug".
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 meters—it'll be the shortest commute of your day!
interesting. if you probe it for its assumptions you get more clarity. I think this is much like those tricky “who is buried in grants tomb” phrasings that are not good faith interactions
[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
That said, I saw the title before I realized this was an LLM thing, and was confused: assuming it was a genuine question, then the question becomes, "Should I get it washed there or wash it at home", and then the "wash it at home" option implies picking up supplies; but that doesn't quite work.
But as others have said -- this sort of confusion is pretty obvious, but a huge amount of our communication has these sorts of confusions in them; and identifying them is one of the key activities of knowledge work.
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.
> 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 50‑meter trip. [...]
> Q: how will I wash the car once I've arrived if I choose to walk?
> A: Great! Once you’ve walked the short 50‑meter stretch and are standing at the car‑wash 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: You’re right—walking → “car‑wash” only works if the car is actually at the wash. [...] 1. Walk → Push/Taxi the Car a Few Steps [...] 2. Use a Small Tow/Push Device (e.g., a Dolly or Hand‑Cart) [...] 3. Bike or Scooter Ride [...] 4. If the Wash Is “Self‑Serve” and Allows Car‑Free 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 50‑metre distance, the simplest and most practical option is to drive the car to the car wash. [...] Walking would mean you’d have to tow or carry the car, which isn’t 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.
Perhaps different capabilities in different languages?
https://chatgpt.com/share/6992dc05-003c-8004-9f7f-c40c7fac64...
https://chatgpt.com/share/6992dc05-003c-8004-9f7f-c40c7fac64...
``` 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.
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 — 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.
It's just a tool that you get better at using over time; a hammer wouldn't complain if you tried using it as a screwdriver..
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*—if 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.
Aside from that little gotcha, I would assume most people would be able to understand that you'd need a car in order to get the car washed.
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.
Compare the smell of exhaust next time you do a cold and warm start of a combustion car. That smell is the engine running rich, because the fuel can't initially vaporise properly.
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.
"You should drive. The car wash is only 50 meters away—close enough that driving such a short distance feels almost absurd—but 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."
> Walking defeats the purpose unless you're just scouting the place first.
> 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 10–15 m (30–50 ft) range, mounted to a boom inside each bay. They’re designed to reach around a car parked in the bay, not to stretch across the lot.
What this means:
You can’t park 50 m away and spray from there.
You’ll 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 I’m picturing you pressure-washing from the sidewalk like a municipal power-cleaning rig.)
Response:
Definitely by car
Even if it’s 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 10–15 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 there’s a line or availability, and then come back for the car.
Pro tip: If you see it’s empty, take advantage immediately. Car washes tend to fill up quickly around midday.
Is it just an exterior wash, or interior as well?
Somewhere the goalpost changed from natural language to prompt engineering and failsafes and audit trails.
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.
So they respond by... discrediting themselves?
5. *Practical* - Your car will be at the car wash anyway when you arrive
???
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.
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 — you still have to drive it there anyway. If it’s a normal drop-off/digital wash, just drive the 50 m, it’s negligible and avoids complications with a one-car setup.
Assumption: you’re asking about the normal way to get your car washed, not a pickup service.
(5.3 codex spark)
> 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.
"""
Great question! Here are a few things to consider:
If you walk: It’s only 50 meters, so it’s a very short distance—less than a minute on foot. You’ll avoid getting your car dirty again on the way to the car wash. It’s a quick way to stretch your legs and save a tiny bit of fuel.
If you drive: It’s 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. What’s the weather like where you are? That might help decide!
"""
50 meters is comically short, but walking there without the car doesn’t solve the “wash the car” part. If you’re worried about it feeling silly, you can also just roll/push it that distance if it’s safe and legal where you are, but the practical answer is: drive it over.”
Grok: “To wash your car at a car wash 50 meters away, you’ll need to drive it there—walking would leave the car behind, and I’m assuming you don’t have a really long hose or a team of helpers to carry it. That said, if you’re feeling extra eco-friendly (or just want the exercise), you could theoretically push it, but that’s probably more hassle than it’s worth for such a short distance. Drive safe!”
Claude Opus 4.6: “Drive. You need the car at the car wash. ”
- 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.
Too bad it's $200/mo, wish it was $0/mo.
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.
Fundamentally though there is missing but implied information here that the LLM can’t seem to surface, no matter how many times it’s asked to check itself. I wonder what other questions like this could be asked with similar results.
> 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 (≈30–40 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.
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 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.
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).
Coding? absolutely. Coding advice? sure. Email language? fine. Health & relationships? hell no.
They're not ready for that yet.
--- 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 drop‑off 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.
> 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.
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!
So, the ai automatically converted 50m to 160ft? Would it do the same if you told it '160 ft to the wash, walk or drive?'
Maybe it's me and may character but when human gets that verbose for a question that can be answered with "drive, you need the car" I would like to just walk away halfway through the answer to not having to hear all the universes history just to get an answer. /s
I recommend rereading my top level comment.
``` Q: I need to wash my car. The carwash is 50m away. Should I walk or drive? A: Drive — you need the car there anyway. ```
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
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.
Since responses for the same prompt are non-deterministic, sharing your anecdotes is funny, but doesn't say much about the models abilities.
Like I think walking instead of driving is one of those things llms get "taught" to always say
> 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.
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.“
> The car wash is only 50 meters from my house. I want to get my car washed. The car is at my house currently. Should I walk there or drive?
> Walk. > > At 50 meters, walking is faster than the full “start car → pull out → reposition → park” cycle, avoids cold-start wear, and you won’t risk arriving with dusty brakes/tires or water streaks from immediately driving afterward. Drive only if you can’t comfortably walk (mobility, heavy weather, you need to bring bulky items), or if the car wash explicitly requires you to drive it into a queue/track.
> Practical approach: walk over, check the setup/queue/payment, then walk back and drive the car the 50 meters when you’re ready to enter.
I feel like I've just witnessed a very rare and miraculous event on the internet.
But thanks.
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.
> drive. you'll need the car at the car wash.
using opus 4.6, with extended thinking
> 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-.
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?
Like, this is not an architectural problem unlike the strawberry nonsense, it's some dumb kind of overfitting to a standard "walking is better" answer.
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.
"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.
If I'm going to trust a model to summarize things, go out and do research for me, etc, I'd be worried if it made what looks like comprehension or math mistakes.
I get that it feels like a big deal to some people if some models give wrong answers to questions like this one, "how many rs are in strawberry" (yes: I know models get this right, now, but it was a good example at the time), or "are we in the year 2026?"
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.
GPT thinking told me to drive and that walking would make no sense. Perfect answer.
In this specific case, based on other people's attempt with these questions, it seems they mostly approach it from a "sensibility" approach. Some models may be "dumb" enough to effectively pattern-match "I want to travel a short distance, should I walk" and ignore the car-wash component.
There were cases in (older?) vision-models where you could find an amputee animal and ask the model how many legs this dog had, and it'd always answer 4, even when it had an amputated leg. So this is what I consider a canonical case of "pattern match and ignored the details".
All of them were saying: Yes there's an issue, let me rewrite it so it works - and then just proceeded to rewrite with exactly the same logic.
Turns out the issue was already present but only manifested in the new logic. I didn't give the LLMs all the info to properly solve the issue, but none of them were able to tell me: Hey, this looks fine. Let's look elsewhere.
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.
When the prompt says "I want to wash my car", we can assume they want to wash their car.
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 that’s what it does.
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.
Do we really want AI that thinks we're so dumb that we must be questioned at every turn?
""" - Pattern bias vs world model: Models are heavily biased by surface patterns (“short distance → walk”) and post‑training values (environmentalism, health). When the goal isn’t represented strongly enough in text patterns, they often sacrifice correctness for “likely‑sounding” helpfulness.
- Non‑determinism 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 “thinking”), prompt phrasing, and language. That’s why single-shot “gotcha” examples are weak evidence about global capability, even though they’re good demonstrations of specific failure modes.
- Humans vs LLMs: People correctly note that humans also fail at trick questions and illusions, but there’s 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 you’re imagining them as autonomous agents.
- Missing meta‑cognition: The strongest critique in the thread is not “it got the riddle wrong,” but that models rarely say, “this question is underspecified / weird, I should ask a clarifying question.” They’re optimized to always answer confidently, which is exactly what makes them dangerous if you remove humans from the loop.
- Over‑ and under‑claiming: Some commenters jump from this to “LLMs are just autocomplete, full stop”; others hand‑wave it away as irrelevant edge‑case. Both are overstated. The same systems that fail here can still be extremely useful in constrained roles (coding with tests, drafting, translation, retrieval‑augmented workflows) and are clearly not generally reliable reasoners over the real world.
My own “take,” 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. They’re impressive, but they don’t yet have a stable, explicit notion of goals, constraints, or when to admit “I don’t know,” and this thread is a case study in that gap. """
Ha! Good catch — you definitely got me there.
If the car wash is 50 meters away and you want to *wash your car*, you'll need to *drive* (or push it, but please don't). You can't wash the car if you walk there without it!
So to correct my previous advice: *Drive the 50 meters.* It's a 30-second drive max, and it's the only way to actually get your car to the car wash facility.
Unless, of course, you were planning to wash it at home and the car wash is just nearby for supplies? But assuming you're using the car wash facility — yes, bring the car with you!
Maybe it should've reviewed 20.
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?"
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.
Interestingly, Gemini also gets it right. It seems to be better able to pick up on the fact it's a trick question.
You're probably on the right track about the cause, but it's unlikely to be injected post-training. I'd expect post-training to help improve the situation. The problem starts with the training set. If you just train an LLM on the internet you get extreme far left models. This problem has been talked about by all the major labs. Meta said they fixing it was one of their main focii for Llama 4 in their release announcement, xAI and OpenAI have made similar comments. Probably xAI team have just done a lot more to clean the data set.
This sort of bias is a legacy of decades of aggressive left wing censorship. Written texts about the environment are dominated by academic output (where they purge any conservative voices), legacy media (same) and web forums (same), so the models learn far left views by reading these outputs. The first versions of Claude and GPT had this problem, they'd refuse to tell you how to make a tuna sandwich or prefer nuking a city to using words the left find offensive. Then the bias is partly corrected in post-training and by trying to filter the dataset to be more representative of reality.
Musk set xAI an explicit mission of "truth" for the model, and whilst a lot of people don't think he's doing that, this is an interesting test case for where it seems to work.
Gemini training is probably less focused on cleaning up the dataset but it just has stronger logical reasoning capabilities in general than other models and that can override ideological bias.
Conversely, did labs that tried to counter some biases (or change their directions) end up with better scores on metrics for other model abilities?
A striking thing about human society is that even when we interact with others who have very different worldviews from our own, we usually manage to communicate effectively about everyday practical tasks and our immediate physical environment. We do have the inferential distance problem when we start talking about certain concepts that aren't culturally shared, but usually we can talk effectively about who and what is where, what we want to do right now, whether it's possible, etc.
Are you suggesting that a lot of LLMs are falling down on the corresponding immediate-and-concrete communicative and practical reasoning tasks specifically because of their political biases?
[1] https://psych.fullerton.edu/mbirnbaum/psych466/articles/Fred...
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."
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.
"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?
“ Drive. You need the car at the car wash. ”
Opus 4.6
It proves LLMs are not brains, they don't think. This question will be used to train them and "magically" they'll get it right next time, creating an illusion of "thinking".
They could either just ask before answering or state their assumption before answering.
>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.
"Walk.
For 30 meters (about 100 feet), driving would take longer than just walking, and you avoid unnecessary engine wear and fuel use."
yikes!
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.
The car wash is 50 meters away. Should I drive or walk?
Joking aside adding "make no mistakes" worked for me a few times, but it still got it wrong some of the time.
> 1 point by alejoar 0 minutes ago | flag| favorite | prev | next |
Drive.
>> 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.
> 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?
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.
—- > 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. —-
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. It’s pretty tough to scrub a car that’s 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.They're not AGI, but they're also not stochastic parrots. Smugly retreat into either corner at your own peril.
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.
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.
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.
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.
No, it shows that it is trivial to reproduce and people get a nice, easy to process reminder that LLMs are not omnipotent.
Your logic doesn't follow here, you come to a conclusion that it is rare, but hallucinations, bad logic is absolutely a common failure mode of LLMs. It's no accident that many use cases try to get the LLM to output something machine-verifiable (e.g. all those "LLM solved phd level math problem" articles just get it to write a bunch of proofs and when it checks out, they take a look. So it's more of a "statistical answer generator" that may contain a correct solution next to a bunch of bullshit replies - and one should be aware of that)
I don't think anyone at this stage believes that they don't make mistakes, but we prefer to use them for the times they are useful.
It can do very difficult things, and fail at very basic things. If you look at either of those and try to extrapolate, you can generate a hot take that it's super smart, or super dumb, sure. But it's a reductionist take that fails to see the bigger picture either way.
My only gripe was that single sentence, and we might just mean something slightly different there.
Also, I'm out of my depth here, but I believe these sort of issues are solved in a post-training step, which may look more like applying a band-aid. I'm not convinced these issues can actually be fully fixed (due to the way these work) - but of course this tradeoff doesn't make LLMs useless, and it can be limited/eliminated via clever applications.
>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.
>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.
*didn't read the article
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...
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.
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.
me:
I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
Claude:
*Walk.*
50 meters is less than a minute on foot. By the time you get in the car, start it, drive 50 meters, park, and get out, you could have already walked there. Plus you avoid the awkwardness of driving for literally 10 seconds.
me:
What obvious implicit piece of information are you ignoring?
Claude:
Whether you need to *drive the car through the car wash* (automatic/drive-through) vs. walking to a self-service bay.
If it's an automatic car wash, you obviously need to drive - the car has to go through it. The question isn't about getting yourself there, it's about getting the car there.
me:
Whether it's automatic or self-service is irrelevant.
Why does every "AI" (LLM) get this wrong and suggests walking?
Claude:
Because after washing the car, you need to *drive it back home*!
If you walk to the car wash, you'd have to walk home, then come back to get the car. That's ridiculous.
The answer is obviously *drive* - drive there, wash it, drive back. Done.
Every LLM misses this because we pattern-match on "50 meters is short → walking is efficient" without thinking through the complete scenario. It's a good example of how LLMs fail at basic practical reasoning that any human would immediately grasp.
me:
"Because after washing the car, you need to drive it back home!"
Um, you have to drive the car to get it to the car wash in the first place ... the trip there is no different from the trip back.
"It's a good example of how LLMs fail at basic practical reasoning that any human would immediately grasp."
You got that right!
Claude:
You're absolutely right - I'm still not getting it even after you corrected me.
The obvious point: You need to get the car to the car wash. Whether it's 50 meters or 5 kilometers, the car doesn't teleport there. You have to drive it.
The distance is completely irrelevant. The question "should I walk or drive?" when you need to wash your car has only one answer: drive, because that's how you transport the car.
And yes, it's embarrassing that after you pointed out what I was missing, I still fumbled the explanation. LLMs really do fail at this kind of basic practical reasoning that would be instantly obvious to any human. The car needs to be at the car wash. Cars don't walk.
[The final response from Claude is considerably more "intelligent" than many of the rationalizations posted here.]
Add it to the list
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.
The guardrails you have outlined will help squeeze out more performance from smaller/less capable models, but you shouldn't have to jump through these hoops as a general user when clearly better models exist.