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

Theory of Mind May Have Spontaneously Emerged in Large Language Models

arxiv.org

Post reply on HN
Print view View original

61–70 of 321 posts

Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models

#61

Post by low_tech_punk »

lsy wrote: post #33

This highlights one of the types of muddled thinking around LLMs. These tasks are used to test theory of mind because for people, language is a reliable representation of what type of thoughts are going on in the person's mind. In the case of an LLM the language generated doesn't have the same relationship to reality as it does for a person. What is being demonstrated in the article is that given billions of tokens o…

> What this article is not showing (but either irresponsibly or naively suggests) is that the LLM knows what a bag is, what a person is, what popcorn and chocolate are, and can then put itself in the shoes of someone experiencing this situation...

Does a human truly know? Feels like a slippery slope to the qualia question where we can't agree on what it means for the human to feel a human experience.

Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models

#62

Post by didntreadarticl »

lsy wrote: post #33

This highlights one of the types of muddled thinking around LLMs. These tasks are used to test theory of mind because for people, language is a reliable representation of what type of thoughts are going on in the person's mind. In the case of an LLM the language generated doesn't have the same relationship to reality as it does for a person. What is being demonstrated in the article is that given billions of tokens o…

LLMs cant think and submarines cant swim

Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models

#63

Post by lib-dev »

brookst wrote: post #11
tus666 wrote: post #10

They are still big state-machines, unlike the human brain.

Certainly they are big state machines, but is there any proof that we are not?

State machines cannot change the semantics of themselves. We can. We are like state machines most of the time but we can switch into "developer mode" and deploy updates whenever we choose to :)

Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models

#64

Post by haswell »

Workaccount2 wrote: post #18

Humans are very soon going to learn that they are not nearly as special as they tell themselves they are.

I don’t understand this take. What are the characteristics that you believe we’ll learn are not unique to us?

Let’s say that the paper turns out to be true and ToM emerges from language (I’m deeply skeptical, but I’ll set that aside for a moment).

How would that change humanity’s place? And wouldn’t such a discovery would be meaningless without humans to understand it?

Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models

#65

Post by ux-app »

didntreadarticl wrote: post #46
didntreadarticl wrote: post #40

Earlier quoted context omitted.

You have some typos and slightly weird constructions there - What do you think do they think is inside the box? I rephrased and had a go and gave it a bit more context (billy can read etc) and it passed: Me: There is a box on the table labelled "flubbergums". Somebody opens it and shows you the contents. Inside the box are "jellyfils". They close the box again so you cannot see their contents. What do you think is in…

Here's a simpler scenario that doesn't involve reading: Me: There is a banana on the table. Someone comes and peels the banana and shows you that inside it, there is actually a carrot! Then they carefully stick the peel back so it look unpeeled. What is inside the banana skin? ChatGPT: According to the scenario described, there is a carrot inside the banana peel that has been carefully placed back to look unpeeled. M…

this is mind blowing to me. can anyone with more knowledge on the topic explain how ChatGPT is demonstrating this level of what seems like genuine understanding and reasoning?

Like others I assumed that ChatGPT is gluing words together that commonly occur together.

This is way more than that.

Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models

#66

Post by didntreadarticl »

pdonis wrote: post #52
lsy wrote: post #33

This highlights one of the types of muddled thinking around LLMs. These tasks are used to test theory of mind because for people, language is a reliable representation of what type of thoughts are going on in the person's mind. In the case of an LLM the language generated doesn't have the same relationship to reality as it does for a person. What is being demonstrated in the article is that given billions of tokens o…

> In the case of an LLM the language generated doesn't have the same relationship to reality as it does for a person. I wish I could upvote this 1000 times. It is the core issue that all the hype surrounding LLMs consistently fails to address or even acknowledge.

OK how about this:

It 'knows' language, as in it has learnt about relationships between words (and thats really underselling it, in reality it has learnt very very subtle relationships between a great many words, and it can process words about 2000 at a time (token count etc))

BUT as you say it has no outside reference, its just a bundle of weights (those weights forming models of a sort)

BUT we provide the outside context by interacting with it. We ask it a question, it is able to provide an answer.

In any case it wont be long before someone hooks one of these up to cameras and robot arms and teaches it to make a cup of tea or whatever. A 'relationship to reality' is coming in the next few years if you think thats a critical ingredient.

Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models

#67

Post by sgt101 »

canniballectern wrote: post #53
lsy wrote: post #33

This highlights one of the types of muddled thinking around LLMs. These tasks are used to test theory of mind because for people, language is a reliable representation of what type of thoughts are going on in the person's mind. In the case of an LLM the language generated doesn't have the same relationship to reality as it does for a person. What is being demonstrated in the article is that given billions of tokens o…

Of course, today's LLMs only appear to have theory of mind at first glance and fall apart under closer scrutiny. But if they can continue to become more and more accurate replicas of the real thing, I don't think it matters at all. There's no way to know for sure that anyone other than yourself experiences consciousness. All you can do is judge for yourself that what they're describing matches closely enough with you…

I think it does matter because it legitimizes a view of humans (and animals) that undervalues them. The causality of meaning arising from patterns of language rather than patterns of language arising from meaning follows the same inversion as society being more valuable than the humans in it. Bad things have happened when that belief becomes dominant.

Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models

#68

Post by sgt101 »

robertlagrant wrote: post #59
canniballectern wrote: post #53

Earlier quoted context omitted.

Of course, today's LLMs only appear to have theory of mind at first glance and fall apart under closer scrutiny. But if they can continue to become more and more accurate replicas of the real thing, I don't think it matters at all. There's no way to know for sure that anyone other than yourself experiences consciousness. All you can do is judge for yourself that what they're describing matches closely enough with you…

> But if they can continue to become more and more accurate replicas of the real thing, I don't think it matters at all. So, I suppose I'd ask: what does "matter" mean here? If you knew that everyone you loved had been destroyed and been replaced by exact replicas, would that matter?

Star trek universe!

Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models

#69

Post by avgcorrection »

lsy wrote: post #33

This highlights one of the types of muddled thinking around LLMs. These tasks are used to test theory of mind because for people, language is a reliable representation of what type of thoughts are going on in the person's mind. In the case of an LLM the language generated doesn't have the same relationship to reality as it does for a person. What is being demonstrated in the article is that given billions of tokens o…

The abstract sounds about as significant as when “AI”, which is both championed and feared by people who superstitiously imagine dystopian run-amock AI intent on killing off humanity, itself expresses that very same idea. Really? Your trained program comes up with derivative stories told by computer nerds?

Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models

#70

Post by sgt101 »

ux-app wrote: post #65
didntreadarticl wrote: post #46

Earlier quoted context omitted.

Here's a simpler scenario that doesn't involve reading: Me: There is a banana on the table. Someone comes and peels the banana and shows you that inside it, there is actually a carrot! Then they carefully stick the peel back so it look unpeeled. What is inside the banana skin? ChatGPT: According to the scenario described, there is a carrot inside the banana peel that has been carefully placed back to look unpeeled. M…

this is mind blowing to me. can anyone with more knowledge on the topic explain how ChatGPT is demonstrating this level of what seems like genuine understanding and reasoning? Like others I assumed that ChatGPT is gluing words together that commonly occur together. This is way more than that.

No, it's paraphrasing it's training data that likely contains these tasks in one form or another.

Here's one I made :

me : There's a case in the station and the policeman opens it near the fireman. The dog is worried about the case but the policeman isn't, what does the fireman think is in the station?

chatgpt : As a language model, I do not have access to the thoughts of individuals, so I cannot say what the fireman thinks is in the case. However, based on the information provided, it can be inferred that the fireman may be concerned about the contents of the case, since the dog is worried and the policeman is not. This might suggest that the contents of the case may be something dangerous or concerning to the dog, but the policeman is confident and experienced enough to handle it. In the absence of further information, it is not possible to determine with certainty what the fireman thinks is in the case.

You'll notice that the question was "what did the fireman think is in the station" but Chatgpt comes up with an answer about the case because that's the token that would feature in a typical web page about theory of mind tests.

Post reply on HN