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

731–740 of 998 posts

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

#731

Post by brightball »

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…

Grok also said to drive. Also made an eco case for washing your car.

> If you're really trying to be an eco-warrior about a 50-meter trip, the real win is washing it in the first place so you're not driving around with a rolling dirt magnet that creates more drag and uses more fuel. Drive. It's the only option that actually gets your car clean.

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

#732

Post by PlatoIsADisease »

Aerroon wrote: post #663
PlatoIsADisease wrote: post #597

Earlier quoted context omitted.

I put this into Grok and it got the right answer on quick mode. I did not give multiple choice though. The real solution is to have 4 AI answer and let the human decide. If all 4 say the same thing, easy. If there is disagreement, further analysis is needed.

Shouldn't it be 3 or 5? https://news.ycombinator.com/item?id=46603111 Are two heads better than one? The post explains why an even number doesn't improve decision-making. Would that still be relevant here?

That was a binary situation and more evidence wasnt helping improve anything.

You could change the standards. If any of the 4 fail, then reject the data.

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

#734

Post by nutjob2 »

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 have a good sense of their _edges_ of intelligence

They have no intelligence at all. The intelligence is latent in the text, generated by and belonging to humans, they just slice and dice text with the hope they get lucky, which works for many things, amazingly. This question really illustrates it what LLMs lack: an internal model of the idea (the question) and all the auxiliary logic/data that enables such models, usually referred to as "common sense" or world models.

Smart humans not only build mental models for ideas, but also higher order models that can introspect models (thinking about our own thinking or models) many levels deep, weigh, merge, compare and differentiate multiple models, sometimes covering vast areas of knowledge.

All this in about 20 watts. Maybe AGI is possible, maybe not, but LLMs are not where it will happen.

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

#735

Post by spogbiper »

datsci_est_2015 wrote: post #690
YeGoblynQueenne wrote: post #629

Earlier quoted context omitted.

That's because it doesn't really have any questions until you ask it whether it does.

This is the most important comment in this entire thread IMO, and it’s a bit buried. This is the fundamental limitation with generative AI. It only generates, it does not ponder.

what is the difference between "ponder" and "generate"? the number of iterations?

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

#736

Post by zeroonetwothree »

linsomniac wrote: post #656
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.

Right, I use it all the time.

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

#737

Post by visarga »

Never ask an important question just once. Ask it in many ways, and on multiple models. If they don't agree at least you know you can't rely on these answers. For important questions I run 3-4 Deep Research reports (Claude, ChatGPT, Gemini, Perplexity) and then comparative analysis at the end.

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

#738

Post by schnable »

datsci_est_2015 wrote: post #690
YeGoblynQueenne wrote: post #629

Earlier quoted context omitted.

That's because it doesn't really have any questions until you ask it whether it does.

This is the most important comment in this entire thread IMO, and it’s a bit buried. This is the fundamental limitation with generative AI. It only generates, it does not ponder.

You can define "ponder" in multiple ways, but really this is why thinking models exist - they turn over the prompt multiple times and iterate on responses to get to a better end result.

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

#739

Post by kshacker »

tlogan wrote: post #482
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…

It has been patched. I tried it last week and it definitely suggested walking. It seems like all the models have been updated, which is not surprising given that the TikTok video has got 3.5 million views.

I tried ChatGPT today. Same results as others.

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

#740

Post by geraneum »

falcor84 wrote: post #674
geraneum wrote: post #632

Earlier quoted context omitted.

These failure modes are not AI’s edge cases at the limit of its capabilities. Rather they demonstrate a certain category of issues with generalization (and “common sense”) as evidenced by the models’ failure upon slight irrelevant changes in the input. In fact this is nothing new, and has been one of LLMs fundamental characteristics since their inception. As for your suggestion on learning from simulations, it sounds…

Interesting - why wouldn't learning from simulations address the problem? To the best of my knowledge, it has helped in essentially every other domain.

Because the problem at display here is inherent in LLMs design and architecture and learning philosophy. As long as you have this architecture you’ll have this issues. Now, we’re talking about the theoretical limits and the failure modes people should be cautious about, not the usefulness, which is improving, as you pointed out.
Post reply on HN