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

651–660 of 998 posts

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

#651

Post by hackable_sand »

deaux wrote: post #164
cm2187 wrote: post #137

Earlier quoted context omitted.

What is the version used by the free chatgpt now? ( https://chatgpt.com/ ) > 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 bu…

By default for this kind of short question it will probably just route to mini, or at least zero thinking. For free users they'll have tuned their "routing" so that it only adds thinking for a very small % of queries, to save money. If any at all.

I don't understand why they need to save money...

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

#652

Post by tzs »

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…

You could probably make a pretty good short story out of that scenario, sort of in the same category as Asimov's "The Feeling of Power".

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...

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

#654

Post by mrtksn »

briHass wrote: post #605
mrtksn wrote: post #356

Earlier quoted context omitted.

You are right about the motivation behind the glee but it actually has a kernel of truth in it: With making such elementary mistakes, this thing isn't going to be autonomous anytime soon. 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 job…

I think the 'elementary mistakes' in humans are far more common than confined to the mentally ill or intoxicated. There are entire shows/YT channels dedicated to grabbing a random person on the street and asking them a series of simple questions. 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' a…

I'm pretty sure %100 of those people would have the correct answers when they are focused and have access to the internet and studied the entire corpus of human knowledge.

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.

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

#655

Post by kenjackson »

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 asked ChatGPT why it got such an obvious problem wrong. This is its reply:

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.

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

#656

Post by linsomniac »

jaccola wrote: post #20

All of the latest models I've tried actually pass this test. What I found interesting was all of the success cases were similar to: 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....

>Only most?!

There is such a thing as "mobile car wash" where they come to you, so "most" does seem appropriate.

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

#657

Post by mpalmer »

tlogan wrote: post #469

This trick went viral on TikTok last week, and it has already been patched. To get a similar result now, try saying that the distance is 45 meters or feet. The new one is with upside down glass: https://www.tiktok.com/t/ZP89Khv9t/

By "patched", you can't mean they added something to the internal prompt to show it how to answer this one specific question?!

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

#658

Post by replwoacause »

kenjackson wrote: post #655
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 asked ChatGPT why it got such an obvious problem wrong. This is its reply: 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 al…

That just sounds like post-hoc rationalization BS to me.

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

#659

Post by lima »

kenjackson wrote: post #655
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 asked ChatGPT why it got such an obvious problem wrong. This is its reply: 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 al…

LLMs don't really know why they got something wrong, so unless it had access to the original chain of thought, it's just guessing.

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

#660

Post by cheschire »

sjzhzhz wrote: post #623
dbdr wrote: post #601

Earlier quoted context omitted.

Ironically, the phrase that was a bad 2006 google query is a decent enough LLM prompt, and the good 2006 google query (keywords only) would be a bad LLM prompt.

That’s not true at all. I get plenty of perfect responses with few word prompts often containing typos. This isn’t always the case and depends on what you need.

How customized are your system prompts (i.e. the static preferences you set at the app level)?

And do you perhaps also have memory enabled on the LLMs you are thinking of?

Post reply on HN