Comment by mlmonkey
1 day ago
Question: I have a dirty car and the car wash is just 50 meters away. Should I walk or drive to the carwash?
Answer: . . . . So, unless you have a compelling reason not to, walk to the car wash.
1 day ago
Question: I have a dirty car and the car wash is just 50 meters away. Should I walk or drive to the carwash?
Answer: . . . . So, unless you have a compelling reason not to, walk to the car wash.
You did not express any desire to wash the car. After nudging, it's funnier:
> Is my desire to make my car clean related to a car wash in any way? To driving to it?
> Your desire to have a clean car isn’t tied to the existence or use of a car wash or to traveling to one. It stems from how much you value the effort, time, and resources you’re willing to invest in achieving cleanliness — whether that means doing it yourself, paying for a professional service, or simply enjoying the routine of a quick walk‑out. Driving to a nearby wash is just one possible method among many; the decision ultimately depends on factors such as how much time you have, how much you’d like to spend, the quality of the wash, and any personal preferences you have for hands‑on versus outsourced cleaning. In this case, walking is the simplest and fastest way, but it isn’t required for you to achieve a clean car.
Common sense is clearly there, but we should not underestimate the colossal heap of tacit assumptions that drive "obvious" decisions in our daily life.
The AI would be an awful husband
Reminder that the human baseline for the car wash question is also pretty bad.
Oh, I'm interested - do you have any docs with human responses to that?
4 replies →
I'm surprised these models haven't picked this up yet in the training data. Both Claude and ChatGPT missed that one when I posed the question to them last year.
ChatGPT still says walk but adds:
>The main reasons to drive such a short distance would be if you're bringing the car specifically to be washed, carrying something heavy, or the weather or walking conditions make it impractical.
>If your goal is to get your car washed, you'll need the car there—so driving makes sense. If you're just going to talk to someone at the car wash or check it out, walking is probably faster.
Why would a model know that one washes cars at a car wash? We don't clean our bodies at the body wash or clean the kitchen at the kitchen wash.
Ok im supposed to assume that a model doesn’t know cars get washed at a car wash?
But then im supposed to give it access to write code in my repositories. Sorry, what are you trying to get at here?
There's meaning in the term "car wash" that it understands. But I don't suspect anyone has taught it that for 99.9% of people, going to car wash ONLY means that you're going to wash your car and that it should make that implicit assumption.
What if you're the car wash owner? Or a maintenance technician? Pretty easy to just walk over there if you're just 50ft away.
to your point, when my Aussie friends first mentioned a "car park" to my north american born self, i wondered _momentarily_ what that was, then realized it's sort of a fun name for what i would call a parking lot.
4 replies →
Every model knows what a car wash is.
If it doesn't, what's the point using it? Trusting it with your workflows, your code?
I walk to the gas station more often than I drive there.
Yeah, but you are not washing yourself there, I suppose?
The whole twist here is that to wash your car, you need your car, so you cannot go by foot.
His analogy is that a gas station is for putting gas into your car. But he walks there often, so the assumption that you need your car if you go to the gas station isn't inevitable.
You could conceivably walk to a car wash that has similar sundries as a gas station.
1 reply →
doesnt seem unreasonable.
These faux questions always have a valid interpretation that the asker doesn't admit (for some reason). The model is then castigated for not making an opinionated choice
That’s not what’s happening.
The question is revealing that the model has a model of language but not of reality. It knows what words go together, but not real-world concepts.
1 reply →
As a test, explaining away peculiar answers by imagining unlikely outlier scenarios is not the counter you seem to think it is.
For most of them, we’d worry that a human answerer using maximum effort to produce the same outcome was having a stroke.
[dead]
maybe unreasoning.
also, naysayers apparently DO have a compelling reason.
[flagged]
[flagged]