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

691–700 of 998 posts

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

#691

Post by nradov »

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…

The Lojban language already exists and allows for eliminating ambiguity. It's obviously not practical for general use, though.

https://en.wikipedia.org/wiki/Lojban

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

#692

Post by kenjackson »

lima wrote: post #659
kenjackson wrote: post #655

Earlier quoted context omitted.

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.

They don’t have access to their network level. But I assume they actually do have access to their chain of thoughts.

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

#693

Post by ninjagoo »

dist-epoch wrote: post #642
ninjagoo wrote: post #588

Earlier quoted context omitted.

> nowhere is it clearly specified that the free model IS as capable as the paid one either. so if you have uncertainty if IS/IS-NOT as capable, what sort of scientist assumes the answer IS? Putting the same model name/number on both the free and paid versions is the specification that performance will be the same. If a scientist has to bring to bear his science background to interpret and evaluate product markings, t…

They don't have the same labels though. On the free ChatGPT you can't select thinking mode.

> On the free ChatGPT you can't select thinking mode.

This is true, but thinking mode shows up based on the questions asked, and some other unknown criteria. In the cases I cited, the responses were in thinking mode.

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

#694

Post by ungreased0675 »

tzs wrote: post #652
dirkc wrote: post #512

Earlier quoted context omitted.

> 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…

This is going into my training courses at work. Thanks!

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

#695

Post by jtbayly »

paulus_magnus2 wrote: post #299

I see things were fixed already [2][4] but luckily a friend showed me this issue yesterday [1][2] [1] 2026-02-15 https://chatgpt.com/share/6992e17b-9b28-8003-9da9-38533f257d... [2] 2026-02-16 https://chatgpt.com/share/6992e135-c610-8003-9272-55058134d4... [3] 2026-02-15 https://grok.com/share/bGVnYWN5LWNvcHk_97e9717b-c2de-47e8-a4... [4] 2026-02-16 https://grok.com/share/bGVnYWN5LWNvcHk_b161bb03-4bed-4785-98... We tri…

Help me out here. Are the models learning, or being “taught more”/fixed on a daily basis? If so, isn’t the model itself changing daily?

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

#696

Post by fhennig »

gen220 wrote: post #637
fhennig wrote: post #400

IMO this is a great example of how we're often asking loaded questions without realizing it. IMO it's the same when we're asking: "Should I implement X from scratch, or import a small library to do it?" vs "Should I add feature X to the codebase or bring in another dependency for it?" In the first question, it sounds like a good idea to not reinvent the wheel, in the second it sounds bad to have dependency.

I totally agree! Interacting with LLMs at work for the past 8 months has really shaped how I communicate with them (and people! in a weird way). The solution I've found for "un-loading" questions is similar to the one that works for people: build out more context where it's missing. Wax about specifically where the feature will sit and how it'll work, force it to enumerate and research specific libraries and put thes…

Yes, great you're sharing this in a bit of detail! I think I've been using a similar approach to getting solid decisions.

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

#697

Post by mytailorisrich »

CamperBob2 wrote: post #683
mytailorisrich wrote: post #377

Earlier quoted context omitted.

Another/newer/less restricted LLM may give a better answer but I don't think we can conclude that it 'understands' anything still.

If it answers this out-of-distribution question correctly -- which the other major models do -- what else should we conclude, other than that a meaningful form of "understanding" is being exhibited? Do we need a new dictionary word that acts as a synonym for "understanding" specifically for non-human actors? I don't see why, personally, but I guess a case could be made.

You may be tempted to conclude that. Then you find something else to ask that leads to an answer obviously nonsensical to a human being, or it hallucinates something, and you realise that, in fact, that's not the case.

IMHO 'understanding' in the usual human sense requires thinking and however good and fast improving LLMs are I don't think anyone would suggest that any of them has become sentient yet. They can infer things based on their training data set better and better but do not 'understand' anmything.

This is a deep and complex topic, and has been for decades.

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

#698

Post by jfengel »

nradov wrote: post #691
dirkc wrote: post #512

Earlier quoted context omitted.

> 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…

The Lojban language already exists and allows for eliminating ambiguity. It's obviously not practical for general use, though. https://en.wikipedia.org/wiki/Lojban

Lojban is syntactically unambitious. Semantically it's still just as vague as any natural language.

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

#699

Post by amarant »

I've seen Claude do similar stuff in code. I asked it to add a new API endpoint in a project. I specified it should use rx.java flowables as the framework I'm using has built in support. I specified to use micronaut data for the database connection.

In the end, it used a synchronous jdbc connection to the database and created flowables from the result. Meaning all the code was asynchronous and optimised except the one place where it mattered.

Took me about 3.5 seconds to fix though, so no biggie.

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

#700

Post by runarberg »

idiotsecant wrote: post #557
nilamo wrote: post #528

Earlier quoted context omitted.

A structured language without ambiguity is not, in general, how people think or express themselves. In order for a model to be good at interfacing with humans, it needs to adapt to our quirks. Convincing all of human history and psychology to reorganize itself in order to better service ai cannot possibly be a real solution. Unfortunately, the solution is likely going to be further interconnectivity, so the model can…

I think it's very likely that machine intelligence will influence human language. It already is influencing the grammar and patterns we use.

I think such influence will be extremely minimal, like confined to dozens of new nouns and verbs, but no real change in grammar, etc.

Interactions between humans and computers in natural language for your average person is much much less then the interactions between that same person and their dog. Humans also speak in natural language to their dogs, they simplify their speech, use extreme intonation and emphasis, in a way we never do with each other. Yet, despite having been with dogs for 10,000+ years, it has not significantly affected our language (other then giving us new words).

EDIT: just found out HN annoyingly transforms U+202F (NARROW NO-BREAK SPACE), the ISO 80000-1 preferred way to type thousand separator

Post reply on HN