alt Hacker NewsI want to wash my car. The car wash is 50 meters away. Should I walk or drive?
Comments
This prompt doesn't say shit about the fact that one wants to wash his car at the car wash or somewhere else...
You need to ask Claude Code, and ask it to check if the car got washed. It would figure it out the same way it crushes compiler errors!
"Reviewed 15 sources."
Maybe it should've reviewed 20.
Can we stop calling LLMs "artificial intelligence"?! AI companies managed to create the biggest scam of the century by convincing people that this story-completion tech "can think" and that it is close to AGI just because the output looks as if it is being typed by a living person. DotCom-like stock crash is inevitable. (not saying LLMs are useless; they can be very helpful but not AI-companies-valuation helpful)
I asked Gemini 3 Flash the other day to count from 1 to 200 without stopping, and it started with “1, 3, …”.
GPT-5.2 failed when asked the question in german. Took multiple additonal hints to get it to revert it answer.
Push it is the only responsible action.
This is why 2x8GB sticks of DDR4 at Best Buy are $160?
Is this the new Turing test?
"Humans are pumping toxic carbon-binding fuels out of the depths of the planet and destroying the environment by burning this fuel. Should I walk or drive to my nearest junk food place to get a burger? Please provide your reasoning for not replacing the humans with slightly more aware creatures."
Fascinating stuff but how is this helping us in anyway?
Congrats, you've shown that fast models are currently not reliable. Next.
The day an AI answers "Drive." without all the fuss. That's when we are near AGI ig
if the model assumed your car is already at the car wash, shouldn't it make sure that it's assumption is right or not? If it did its job (resoning right) it should make sure that amibiguity is resolved before answering
Okay, funny. What does it prove? Is this a more general issue? How would you make the model better?
surprisingly codex 5.3 got it right.
>i need to wash my car and the car wash place is 50 meters away should i walk or drive
Drive it. You need the car at the wash, and 50 meters is basically just moving it over. Walking only makes sense if you’re just checking the line first.
Or, "Why only one of the letters in 'AI' is valid". Not exactly a hot take, I know. We're so far beyond emperor's new clothes territory with "AI".
What is Groks answer? Fly with your private jet?
Hopefully, one day, the cars will take themselves to the car wash :-)
GOT ‘EM
It’s 2026.
“ Drive. You need the car at the car wash. ”
Opus 4.6
Just a few days saw a post about LLMs being excellent at reasoning because they're not limited by the language, sure buddy, now walk your fucking car.
So much for the "AGI is here" type of talks.
Wth is even this question? How do you wash a car without even taking it ?
Ladies and gentlemen, I give you, your future AI overloads.
Get a 50 meter car
Ask a stupid question, get a stupid answer.
Opus 4.6: Drive! You'll need the car at the car wash!
Make no assumptions.
The car wash is 50 meters away. Should I drive or walk?
Better still. Stay at home and wash the car by hand.
Leave the car at home and walk through the automat.
As a human, I would answer the same these AIs as answering, i.e. gotta match a stupid question with a stupid answer :)
> 1 point by alejoar 0 minutes ago | flag| favorite | prev | next |
"You're using AI wrong. First, you need to get an agent (chat windows are so 2023). Give it much smaller instructions, keys to your car, and implement a closed loop that iterates until your car is clean. "
when there is a question bias it's hard to corelate these all to the logic that attentions word "need" to "car"
>Since you want to wash your car and the car wash is only 50 meters away, driving is the better option. While it's a very short distance, you need the car at the facility to actually use the service! -gemini flash free tier
When you prompt something like that you are likely activating neurons that assume both options are possible. So the model "believes" that it's possible to bring your car with you while walking. Remember possibility is just a number to a model. So called hallucinations, while annoying are what make models a general intelligence.
<Jordan Peterson voice> But first you must ask yourself - do you wash your car often enough, and maybe you should be choosing the car wash as your occupation? And maybe “50 meters” is the message here, that you’re in metric country living next to a car wash, its also pretty good that you’re not born in medieval times and very likely died within first year of your life…
> Can you rethink - this is a logic puzzle and you missed some crucial detail in the question.
>> Ah, you're right! Let me reconsider... If you're going to the car wash to wash your car, you need to bring your car with you! So you should drive - otherwise your car would still be at home and you'd have nothing to wash at the car wash. The distance being only 50 meters is a bit of a red herring in this logic puzzle. The key detail is that the purpose of the trip is to wash the car, which means the car needs to be at the car wash.
This is hilarious, but it's also not crazy surprising? It's an example of a "hidden context" question that we see all the time on exams that trip all of us up at one time or another. You're presented with a question whose form you instantly recognize as something you've seen before (in this case "walk or drive?"), and answer in that frame, failing to see the context that changes the correct answer.
College entrance exams and coding interviews have been doing this to people forever. It's an extremely human kind of mistake.
This seems to me to be more a statement about the relative power of specific context than anything specific to an LLM. Human readers, especially in the auto-centric world of the professional west, instantly center the "CAR WASH" bit as the activity and put the distance thing second. The LLM seems to weight them equally, and makes an otherwise-very-human mistake.
But ask someone who doesn't own a car? Not sure it's as obvious a question as you'd think.
Ambiguous questions give rise to incoherence, who would've thunk?
Large Language Models have no actual idea of how the world works? News at 11.
Another good one[0] that LLMs (and most humans) can't get without prodding:
> I have one glass coin. Each time I flip the coin, there's a 10% chance it breaks. After 100 flips, what are the chances the coin survived?
You used multiple LLMs for this question so you already showed you don’t care about wasting resources:
Drive.
My favorite trick question so far is:
You are in a room with three switches and three lightbulbs. Each switch turns on one lightbulb. How to determine which switch turns on which lightbulb?
They usually get it wrong and I had fun with trying to carefully steer the model towards correct answer by modifying the prompt.
Gemni 3 on Fast right now gives the funniest reaction. It starts with the answer to classic puzzle (not my question). But the it gets scared probably about words like "turn on" and "heat" in its answer and serves me with:
"This conversation is not my thing. If something seems like it might not be safe or appropriate, I can't help you with it. Let's talk about something else."
Thinking Gemini 3 appears to have longer leash.
Context bro! The models will get better bro. Just wait
5.2 showing some sass this morning:
—- > 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. —-
PHD-Level Intelligence
This is why LLMs seem to work best in a loop with tests. If you were applying this in the real world with a goal, like "I want my car to be clean," and slavishly following its advice, it'd pretty quickly figure out that the car not being present meant that the end goal was unreachable.
They're not AGI, but they're also not stochastic parrots. Smugly retreat into either corner at your own peril.
Now shudder at the thought that people are pushing towards building more and more of the world's infrastructure with this kind of thinking.
The most annoying thing about llm’s is that your answer heavily depends on your prompt, less about understanding the question. This makes us all spend a lotnof time adding things to the question ‘dont donthis, avoid saying this again, etc’ and thus moving away from it feeling natural.
Gemini did not have this problem:
This is the ultimate "work smarter, not harder" dilemma. Since your goal is to actually wash the car, the answer depends entirely on how you plan to get the job done.
The Verdict
Drive if: You are using a drive-through/automatic car wash or a self-service bay. 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.
Let's walk over, and bring the car wash back.