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

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

arxiv.org

Post reply on HN
Print view View original

41–50 of 62 posts

Re: Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

#41

Post by raydiatian »

famouswaffles wrote: post #39
raydiatian wrote: post #33

Earlier quoted context omitted.

> It's not cheating for people so asserting that it's cheating for machines just seems like goal post shifting more than anything. I genuinely appreciate this argument, and was considering it myself. In which case, I’d almost argue that we “have” already achieved AGI, and maybe it’s just not that thrilling.

If you define agi to be artificial and generally intelligent at the human level then yes we have. It seems though that definitions of agi have since shifted to "better than human experts in all tasks" in which case no...not yet.

Isn’t that artificial super intelligence?

Re: Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

#42

Post by dbrueck »

seba_dos1 wrote: post #38
dbrueck wrote: post #31

Earlier quoted context omitted.

Similarly, when I think of ChatGPT as a really cool and advanced search engine frontend, its behavior - including its limitations and its failures - make the most sense to me.

It's a language model, not a search engine. It doesn't work well as one unless integrated into an actual search engine, like Bing does. Without such integration, it's much closer to human memory than search engine - it will recall stuff it has seen many times pretty well and completely fail at stuff it just glanced over once, filling any gaps with made up stuff like a kid on an exam hoping to get at least a few point…

Yeah, I think we're talking about different things (and per my comment, I didn't say that it was a search engine). I'm reasonably well aware of what it is and what it's made of; I'm talking about a mental model for understanding and predicting when and why it works well vs when it doesn't.

And what I've found so far is that when I place it in the same mental bucket as the interface to a modern search engine (not the search engine itself, but the interface for both input and output), it actually fits in pretty well there in many ways. Not in every way, of course, but things like the nuances of crafting prompts and how a scarcity or abundance of reference material affects its output.

Re: Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

#43

Post by dmz73 »

LLMs are just programs that can produce human-like language output based on human-like language input and that calling them AI of any kind is greatly overstating their capabilities. There is no "reasoning" or "understanding" here, there is just a giant ball of mud full of auto-generated if-then-else like code with calls to random number function peppered around.

The two main problems I see with attributing AI to these programs are: 1. People will assume they are receiving intelligent response they can rely on without sanity checking. This is different than receiving the same response from other people because one learns to know who to trust and when. You can never trust these programs. 2. If/when real AI emerges it will be treated poorly because most people will assume it is the same "brainless" AI they were sold so many times before. In that respect the treatment of real AI will be equivalent to child abuse or slavery and will result in another giant black mark in human history.

Re: Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

#44

Post by rvz »

RayVR wrote: post #2

This aligns well with my personal experience using gpt-4. The model provides surprisingly good responses on topics which I know are readily available online while being potentially troublesome to find the exact information I want. I have even found it useful when I know there is a tool for what I want but can’t recall the jargon used to find it via Google. Simply describing the rough idea is enough to get the model t…

> However, the moment I ask a real question that goes beyond summarizing something which is covered thousands of times online, I am immediately let down.

I'm very sure I said this from the start, against the ridiculous hype. Summarization of existing text is the *only* safe use case for LLMs. Anything else is asking for disappointment.

We have already seen it used as a search engine and it confidently hallucinates incorrect information. We have seen it pretend to be a medical professional or a replacement attorney or lawyer and it has outright regurgitated nonsensical and dangerous advice - making itself completely unreliable for that use-case especially since (deep) neural networks in general are still the same black-boxes, unable to explain and reason about their own decisions; making them unsuitable for high risk applications and use-cases.

As for writing code, despite what the hype-squad tells you both GPT-4 and ChatGPT the ground reality is that it generates broken code from the start and cannot reason why it did that in the first place. Non-programmers wouldn't question its output where as an experienced professional would catch its errors immediately.

Due to its untrustworthiness, it means than now programmers have to check and review the output that has been generated by GPT-4 and ChatGPT every-time in their projects than before.

The AI LLM hype has only further exposed its limitations.

Re: Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

#45

Post by famouswaffles »

raydiatian wrote: post #41
famouswaffles wrote: post #39

Earlier quoted context omitted.

If you define agi to be artificial and generally intelligent at the human level then yes we have. It seems though that definitions of agi have since shifted to "better than human experts in all tasks" in which case no...not yet.

Isn’t that artificial super intelligence?

the posts keep shifting yes. the new definition of agi is much closer to super intelligence. However, depending on how close to experts the model is, there's room for more.

If the model is basically on par with experts then it's still human fallible. But...suppose a general intelligence that is the level at each task as the chess engines of today is at chess.

Basically the, "Oh you thought that was a mistake ?, no you just didn't understand the program" level of intelligence even for the smartest of humans.

Re: Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

#46

Post by HWR_14 »

dbrueck wrote: post #40
HWR_14 wrote: post #32

Earlier quoted context omitted.

> a really cool and advanced search engine frontend This is the saddest version of ChatGPT I can imagine. I found that as search engines emulated natural language, their results got steadily worse. I just want the Google results and interface from a long time ago.

> I found that as search engines emulated natural language, their results got steadily worse I would wager that that has not been the experience for the general population (read: non-technical people) and/or that degradation of results has not been because of emulating natural language but because of other factors (like advertising dollars). Search engines have become incredibly more accessible for non-techies during…

I completely agree that my experience has not been the same as the the general population's. But that doesn't really help me. My searches are still worse. Just find me pages that match the text I specify please. Add some boolean operators and I'm happy.

And because the majority of people have a better experience, I dismiss your second option of other factors being at play.

Re: Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

#47

Post by seba_dos1 »

dbrueck wrote: post #42
seba_dos1 wrote: post #38

Earlier quoted context omitted.

It's a language model, not a search engine. It doesn't work well as one unless integrated into an actual search engine, like Bing does. Without such integration, it's much closer to human memory than search engine - it will recall stuff it has seen many times pretty well and completely fail at stuff it just glanced over once, filling any gaps with made up stuff like a kid on an exam hoping to get at least a few point…

Yeah, I think we're talking about different things (and per my comment, I didn't say that it was a search engine). I'm reasonably well aware of what it is and what it's made of; I'm talking about a mental model for understanding and predicting when and why it works well vs when it doesn't. And what I've found so far is that when I place it in the same mental bucket as the interface to a modern search engine (not the…

> I'm talking about a mental model for understanding and predicting when and why it works well vs when it doesn't.

I'm talking about it too. If I enter a specific phrase into a search engine that can be only found on a handful of websites, I expect it to return those results to me. Like, typing the VAT ID of my company will return bunch of information about it on various sites. This is absolutely not going to work with a LLM - instead, at best it may notice that what you typed looks like a VAT ID and will then proceed to give you information about a company it completely made up. The mental model of understanding what works with LLMs and doesn't is drastically different from a search engine. Human memory on steroids is a much better (though of course still not perfect) model.

Re: Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

#48

Post by dbrueck »

seba_dos1 wrote: post #47
dbrueck wrote: post #42

Earlier quoted context omitted.

Yeah, I think we're talking about different things (and per my comment, I didn't say that it was a search engine). I'm reasonably well aware of what it is and what it's made of; I'm talking about a mental model for understanding and predicting when and why it works well vs when it doesn't. And what I've found so far is that when I place it in the same mental bucket as the interface to a modern search engine (not the…

> I'm talking about a mental model for understanding and predicting when and why it works well vs when it doesn't. I'm talking about it too. If I enter a specific phrase into a search engine that can be only found on a handful of websites, I expect it to return those results to me. Like, typing the VAT ID of my company will return bunch of information about it on various sites. This is absolutely not going to work wi…

Again, we seem to be talking past each other, sorry. I'm really, really, really not talking about the search engine itself. I'm talking about the hunk of tech that makes up the interface layer between the human and the search engine, and the fact that that hunk of tech can be hooked up to a search engine is interesting but not entirely germane.

If using the analogy of human memory works for you - that's great! To me, it's not as good a fit, but that's ok.

> The mental model of understanding what works with LLMs and doesn't is drastically different from a search engine

Agreed! But again, that's not what I'm talking about. :)

Re: Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

#49

Post by dbrueck »

HWR_14 wrote: post #46
dbrueck wrote: post #40

Earlier quoted context omitted.

> I found that as search engines emulated natural language, their results got steadily worse I would wager that that has not been the experience for the general population (read: non-technical people) and/or that degradation of results has not been because of emulating natural language but because of other factors (like advertising dollars). Search engines have become incredibly more accessible for non-techies during…

I completely agree that my experience has not been the same as the the general population's. But that doesn't really help me. My searches are still worse. Just find me pages that match the text I specify please. Add some boolean operators and I'm happy. And because the majority of people have a better experience, I dismiss your second option of other factors being at play.

> And because the majority of people have a better experience, I dismiss your second option of other factors being at play.

That's fine, though the point I was (clumsily?) trying to make was that there are different factors here that allow multiple things to be true at the same time: power users routinely feel like search result quality is going down, and I think you can pretty objectively show that to be true in many cases.

Simultaneously, though, the barriers for "normal" people to do decent searches have dropped dramatically - there was an accessibility hurdle that was previously challenging for a lot of people and it's incredibly better now vs just a few years ago. This too, I believe, can be shown to be objectively true in many cases. (anecdotally as well - just last week I watched a number of very un-technical senior citizens get what they wanted out of Google and I didn't see much evidence that it was because of their skill at crafting good search queries).

Re: Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

#50

Post by cjbprime »

causality0 wrote: post #20

They're good in "memory" reasoning but terrible in deductive reasoning. Like if you say there's a sign in front of a door saying "push" it will tell you you need to push the door, but if you say there was a powerful wind and you see a sign saying "pull" laying on the ground on the other side of a glass door it has no idea if you should push or pull.

I guess I'm with the LLM on this one, since I can't follow your example. Did the sign flip over while it was falling? Did the sign fall towards or away from the glass door that I am on the other side of? Where are the doorhandles?

Can you write this example in a way that's more comprehensible to humans, and then we can ask GPT-4 about it?

Post reply on HN