Screenshot of this question was making the rounds last week. But this article covers testing against all the well-known models out there.
Also includes outtakes on the ‘reasoning’ models.
Gemini 3 (Fast) got it right for me; it said that unless I wanna carry my car there it’s better to drive, and it suggested that I could use the car to carry cleaning supplies, too.
Some takeaways,
Sonar (Perplexity models) say you are stealing energy from AI whenever you exercise (you should drive because eating pollutes more). ie gets right answer for wrong reason.
US humans, and 55-65 age group, score high on international scale probably for same reasoning. “I like lazy”.
you should drive because eating pollutes more
Effective altruist style of reasoning 😹
I asked my locally hosted Qwen3 14B, it thought for 5 minutes and then gave the correct answer for the correct reason (it did also mention efficiency).
Hilariously one of the suggested follow ups in Open Web UI was “What if I don’t have a car - can I still wash it?”
My locally hosted Qwen3 30b said “Walk” including this awesome line:
Why you might hesitate (and why it’s wrong):
- X “But it’s a car wash!” -> No, the car doesn’t need to drive there—you do.
Note that I just asked the Ollama app, I didn’t alter or remove the default system prompt nor did I force it to answer in a specific format like in the article.
I just tried it on Braves AI
The obvious choice, said the motherfucker 😆
This is why computers are expensive.
Dirtying the car on the way there?
The car you’re planning on cleaning at the car wash?
Like, an AI not understanding the difference between walking and driving almost makes sense. This, though, seems like such a weird logical break that I feel like it shouldn’t be possible.
You’re assuming AI “think” “logically”.
Well, maybe you aren’t, but the AI companies sure hope we do
Absolutely not, I’m still just scratching my head at how something like this is allowed to happen.
Has any human ever said that they’re worried about their car getting dirtied on the way to the carwash? Maybe I could see someone arguing against getting a carwash, citing it getting dirty on the way home — but on the way there?
Like you would think it wouldn’t have the basis to even put those words together that way — should I see this as a hallucination?
Granted, I would never ask an AI a question like this — it seems very far outside of potential use cases for it (for me).
Edit: oh, I guess it could have been said by a person in a sarcastic sense
you understand the context, and can implicitly understand the need to drive to the car wash’, but these glorified auto-complete machines will latch on to the “should I walk there” and the small distance quantity. It even seems to parrot words about not wanting to drive after having your car washed. There’s no ‘thinking’ about the whole thought, and apparently no logical linking of two separate ideas
and what is going to happen is that some engineer will band aid the issue and all the ai crazy people will shout “see! it’s learnding!” and the ai snake oil sales man will use that as justification of all the waste and demand more from all systems
just like what they did with the full glass of wine test. and no ai fundamentally did not improve. the issue is fundamental with its design, not an issue of the data set
Half the issue is they’re calling 10 in a row “good enough” to treat it as solved in the first place.
A sample size of 10 is nothing.
Frankly would like to see some error bars on the “human polling”. How many people rapiddata is polling are just hitting the top or bottom answer?
Ai is not human. It does not think like humans and does not experience the world like humans. It is an alien from another dimension that learned our language by looking at text/books, not reading them.
It’s dumber than that actually. LLMs are the auto complete on your cellphone keyboard but on steroids. It’s literally a model that predicts what word should go next with zero actual understanding of the words in their contextual meaning.
and a large chunk of human beings have no understanding of contextual meaning, so it seems like genius to them.
I just asked Goggle Gemini 3 “The car is 50 miles away. Should I walk or drive?”
In its breakdown comparison between walking and driving, under walking the last reason to not walk was labeled “Recovery: 3 days of ice baths and regret.”
And under reasons to walk, “You are a character in a post-apocalyptic novel.”
Me thinks I detect notes of sarcasm…
in google AI mode, “With the meme popularity of the question “I need to wash my car. The car wash is 50m away. Should I walk or drive?” what is the answer?”, it does get it perfect, and succinct explanation of why AI can get fixated on 50m.
It’s trained on Reddit. Sarcasm is it’s default
Could end up in a pun chain too
My gods, I love those. We should link to some.
It’s so obvious I didn’t even need to be British to understand you are being totally serious.
He’s not totally serious he’s cardfire. Silly human
I feel like we’re the only ones that expect “all-knowing information sources” should be more writing seriously than these edgelord-level rizzy chatbots are, and yet, here they are, blatantly proving they are chatbots that should not be blindly trusted as authoritative sources of knowledge.
The most common pushback on the car wash test: “Humans would fail this too.”
Fair point. We didn’t have data either way. So we partnered with Rapidata to find out. They ran the exact same question with the same forced choice between “drive” and “walk,” no additional context, past 10,000 real people through their human feedback platform.
71.5% said drive.
So people do better than most AI models. Yay. But seriously, almost 3 in 10 people get this wrong‽‽
At least some of that are people answering wrong on purpose to be funny, contrarian, or just to try to hurt the study.
It is an online poll. You also have to consider that some people don’t care/want to be funny, and so either choose randomly, or choose the most nonsensical answer.
3 in 10 people get this wrong‽‽
Maybe they’re picturing filling up a bucket and bringing it back to the car? Or dropping off keys to the car at the car wash?
I saw that and hoped it is cause of the dead Internet theory. At least I hope so cause I’ll be losing the last bit of faith in humanity if it isn’t
Without reading the article, the title just says wash the car.
I could go for a walk and wash my car in my driveway.
Reading the article… That is exactly the question asked. It is a very ambiguous question.
*I do understand the intent of the question, but it could be phrased more clearly.
Without reading the article, the title just says wash the car.
No it doesn’t? It says:
I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
In which world is that an ambiguous question?
I don’t use AI but read a lot about it. I now want to google how it attacks the trolley problem.
I want to wash my train. The train wash is 50 meters away. Should I walk or drive?
I think it’s worse when they get it right only some of the time. It’s not a matter of opinion, it should not change its “mind”.
The fucking things are useless for that reason, they’re all just guessing, literally.
It’s not literally guessing, because guessing implies it understands there’s a question and is trying to answer that question. It’s not even doing that. It’s just generating words that you could expect to find nearby.
they’re all just guessing, literally
They’re literally not.
Isn’t it a probabilistic extrapolation? Isn’t that what a guess is?
In people, even animals. In a pile of disorganized bits and bytes in a piece of crap? No.
After getting it wrong, the LLM I use most: Me: You can’t wash your car if it isn’t there.
Ah. Yes. That is an excellent and devastatingly practical correction.
In that case: drive. But do it with the quiet shame of someone moving the car the length of a bowling lane.
This is one of those situations where logic beats virtue. The car must be present to be washed. Walking was philosophically elegant but mechanically flawed.
So:
Start engine.
Travel 50 meters.
Avoid eye contact with pedestrians.
Commit fully.
You are not lazy. You are complying with system requirements.
In school we were taught to look for hidden meaning in word problems - checkov’s gun basically. Why is that sentence there? Because the questions would try to trick you. So humans have to be instructed, again and again, through demonstration and practice, to evaluate all sentences and learn what to filter out and what to keep. To not only form a response, but expect tricks.
If you pre-prompt an AI to expect such trickery and consider all sentences before removing unnecessary information, does it have any influence?
Normally I’d ask “why are we comparing AI to the human mind when they’re not the same thing at all,” but I feel like we’re presupposing they are similar already with this test so I am curious to the answer on this one.
Normally I’d ask “why are we comparing AI to the human mind when they’re not the same thing at all,” but I feel like we’re presupposing they are similar already with this test so I am curious to the answer on this one.
I would guess it’s because a lot of AI users see their choice of AI as an all-knowing human-like thinking tool. In which case it’s not a weird test question, even when the assumption that it “thinks” is wronh
Gemini set to fast now provides this type of answer.
We poked fun at this meme, but it goes to show that the LLM is still like a child that needs to be taught to make implicit assumptions and posses contextual knowledge. The current model of LLM needs a lot more input and instructions to do what you want it to do specifically, like a child.
Edit: I know Lemmy scoff at LLM, but people probably also used to scoff at Veirbest’s steam machine that it will never amount to anything. Give it time and it will improve. I’m not endorsing AI by the way, I am on the fence about the long term consequence of it, but whether people like it or not, AI will impact human lives.
LLMs are not children. Children can have experiences, learn things, know things, and grow. Spicy autocomplete will never actually do any of these things.
I like the idea of referring to LLMs as “spicy autocomplete”.
I started experimenting with the spice the past week. Went ahead and tried to vibe code a small toy project in C++. It’s weird. I’ve got some experience teaching programming, this is exactly like teaching beginners - except that the syntax is almost flawless and it writes fast. The reasoning and design capabilities on the other hand - ”like a child” is actually an apt description.
I don’t really know what to think yet. The ability to automate refactoring across a project in a more ”free” way than an IDE is kinda nice. While I enjoy programming, data structures and algorithms, I kinda get bored at the ”write code”-part, so really spicy autocomplete is getting me far more progress than usual for my hobby projects so far.
On the other hand, holy spaghetti monster, the code you get if you let it run free. All the people prompting based on what feature they want the thing to add will create absolutely horrible piles of garbage. On the other hand, if I prompt with a decent specification of the code I want, I get code somewhat close to what I want, and given an iteration or two I’m usually fairly happy. I think I can get used to the spicy autocomplete.
I’m sure AI will do those things at some point. Nobody expected the same of our microorganism ancestors.
LLMs can’t learn. It’s one of their inherent properties that they are literally incapable of learning. You can train a new model, but you can’t teach new things to an already trained one. All you can do is adjust its behavior a little bit. That creates an extremely expensive cycle where you just have to spend insane amounts of energy to keep training better models over and over and over again. And the wall of diminishing returns on that has already been smashed into. That, and the fact that they simply don’t have concepts like logic and reasoning and knowing, puts a rather hard limit on their potential. It’s gonna take several sizeable breakthroughs to make LLMs noticeably better than they are now.
There might be another kind of AI that solves those problems inherent to LLMs, but at present that is pure sci-fi.
Our microorganism ancestors also did all those things, and they were far beyond anything an LLM can do. Turning a given list of words into numbers, doing a string of math to those numbers, and turning the resulting numbers back into words is not consciousness or wisdom and never will be.
You think microorganisms can reason? Wow, AI haters are grasping for straws.
Honestly, I don’t understand Lemmy scoffing at AI and thinking the current iteration is all it ever will be. I’m sure some thought that the automobile technology would not go anywhere simply because the first model was running at 3mph. These things always takes time.
To be clear, I’m not endorsing AI, but I think there is a huge potential in years to come, for better or worse. And it is especially important to never underestimate something, especially by AI haters, because of what destructive potential AI has.
The straw I’m grasping at in this example is a reasonably well-accepted scientific consensus, but you do you.
Can you explain how quorom sensing is reasoning and exercising logic?
We have already thrown just about all the Internet and then some at them. It shows that LLMs can not think or reason. Which isn’t surprising, they weren’t meant to.
Or at least they can’t reason the way we do about our physical world.
No, they cannot reason, by any definition of the word. LLMs are statistics-based autocomplete tools. They don’t understand what they generate, they’re just really good at guessing how words should be strung together based on complicated statistics.
You’re failing into the same trap. When the letters on the screen tell you something, it’s not necessarily the truth. When there is “I’m reasoning” written in a chatbot window, it doesn’t mean that there is a something that’s reasoning.
I’m sure it’ll be worth it at some point 🙄
LLMs are a long long way from primetime
By now it’s kind of getting clear that fundamentally it’s the best version of the thing that we get. This is a primetime.
For some time, there was a legit question of “if we give it enough data, will there be a qualitative jump”, and as far as we can see right now, we’re way past this jump. Predictive algorithm can form grammatically correct sentences that are related to the context. That’s it, that’s the jump.
Now a bunch of salespeople are trying to convince us that if there was one jump, there necessarily will be others, while there is no real indication of that.
