Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

mastodon.world

Post reply on HN
Print view View original

701–710 of 998 posts

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#701

Post by operator_nil »

dirkc wrote: post #512
jstummbillig wrote: post #147

Earlier quoted context omitted.

> so you need to tell them the specifics 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 bu…

> That is the entire point, right? Us having to specify things that we would never specify when talking to a human. 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 pro…

[dead]

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#703

Post by aklein »

https://chatgpt.com/share/699346d3-fcc0-8008-8348-07a423a526...

interesting. if you probe it for its assumptions you get more clarity. I think this is much like those tricky “who is buried in grants tomb” phrasings that are not good faith interactions

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#704

Post by tlogan »

onionisafruit wrote: post #595
fireflash38 wrote: post #509

Earlier quoted context omitted.

To me, the "patching" that is happening anytime some finds an absolutely glaring hole in how AIs work is so intellectually dishonest. It's the digital equivalent of house flippers slapping millennial gray paint on structural issues. 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…

Counting and math makes sense to add special tools for because it’s handy. I agree with your point that patching individual questions like this is dishonest. Although I would say it’s pointless too. The only value from asking this question is to be entertained, and “fixing” this question makes the answer less entertaining.

From a technological standpoint, it is pointless. But from a marketing perspective, it is very important.

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.

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#705

Post by dezgeg »

rob74 wrote: post #140
vlovich123 wrote: post #120

Gemini fast > 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…

Wow... so not only does Gemini thinking not fall for it, but it also answers the trick question with humor? I'm impressed!

Yeah Gemini seems to be good at giving silly answers for silly questions. E.g. if you ask for "patch notes for Chess" Gemini gives a full on meme answer and the others give something dry like "Chess is a traditional board game that has had stable rules for centuries".

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#706

Post by gurjeet »

prasoonds wrote: post #46

I've used LLMs enough that I have a good sense of their _edges_ of intelligence. I had assumed that reasoning models should easily be able to answer this correctly. And indeed, Sonnet and Opus 4.5 (medium reasoning) say the following: Sonnet: Drive - you need to bring your car to the car wash to get it washed! Opus: You'll need to drive — you have to bring the car to the car wash to get it washed! Gemini 3 Pro (mediu…

I tried your exact prompt on my ChatGPT 5.2 Thinking. It gave me the opposite response. This proves that even an exact replication of the prompt is not a guarantee that the response will be on the right side of a binary chose. Then, in a new chat, I set the thinking mode to 'Extended thinking' (from the default 'Standard'). I got the expected response. But since the first conversation showed that the exact prompt is not a guarantee of the same answer, I tried again and on 3rd attempt I got the 'Extended thinking' mode to respond with the 'Walk' response.

(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.

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#707

Post by K0balt »

kenjackson wrote: post #649
K0balt wrote: post #625

Earlier quoted context omitted.

To be fair, we all have holes in our reasoning if we don’t carefully consider things and sometimes they are very surprising when they come to light. The dependency issue (need the car at the car wash) is an easy one that often trips up people at first glance too. (Left my phone at work, plan: take an uber to get to the office, walk to the couch and remember I don’t have my phone to call an uber) Things like that are…

Another simple example is using the flashlight on your phone to look for your phone.

Oh the cringe. Got me.

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#710

Post by Retric »

jmward01 wrote: post #680
FatherOfCurses wrote: post #666

All the people responding saying "You would never ask a human a question like this" - this question is obviously an extreme example. People regularly ask questions that are structured poorly or have a lot of ambiguity. The point of the poster is that we should expect that all LLM's parse the question correctly and respond with "You need to drive your car to the car wash." People are putting trust in LLM's to provide…

This reminds me of the old brain-teaser/joke that goes something like 'An airplane crashes on the boarder of x/y, where do they bury the survivors?' The point being that this exact style of question has real examples where actual people fail to correctly answer it. We mostly learn as kids through things like brain teasers to avoid these linguistic traps, but that doesn't mean we don't still fall for them every once i…

That’s less a brain teaser than running into the error correction people use with language. This is useful when you simply can’t hear someone very well or when the speaker makes a mistake, but fails when language is intentionally misused.
Post reply on HN