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

81–90 of 321 posts

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

#81

Post by oliveshell »

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.

Strongly agree.

It’s been eye-opening to see how often otherwise very bright, highly technical people stumble at this sort of critical thinking hurdle.

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

#83

Post by low_tech_punk »

HillRat wrote: post #37

There's something about language generation that triggers the anthropomorphic fallacy in people. While it's impressive that GPT3 can generate language that mimics ToM-based reasoning in people, this paper doesn't get close to proving its central contention, that LLMs possess a ToM. A test that demonstrates the development of ToM in human children should not, absent compelling causal evidence and theory, be assumed to…

May I play devil's advocate? The fallacy of this paper granted, is it worth questioning our belief that there is more to intelligence than the "appearance of intelligence"?

What if the lack of hallucination in human being is due to our self-imposed guard (hello, frontal cortex) that is developed via an evolutionary process (aka, biological reinforcement training)?

To stretch the argument a bit further, what if hallucination is a feature, not a bug? At the risk of straying too far empirical science, how might we compare psychedelics-induced hallucinations in human with hallucinations in AI models?

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

#84

Post by swatcoder »

didntreadarticl wrote: post #66
pdonis wrote: post #52

Earlier quoted context omitted.

> 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 c…

The future AI you describe has language at the center of its understanding. For example, you would expect that the cameras and arm-feedback-sensors would produce text (or text-associated weights/tokens) that describe what the AI "sees" and the robotic arms would be receive some kind of language-derived directives from the LLM.

It will be very interesting to see what that system is capable of. I think a lot of people here don't identify language as an essential part of "thinking" and "being", and instead view language as a superficial layer whose role is primarily about social communication and secondarily about abstract reasoning. This is why some of us see these LLM examples as not really speaking to intelligence per se. It's hard for some of us to conceive of intelligence as being represented purely in language.

So your proposed system would be a extremely interesting exploration of that! I look forward to it.

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

#85

Post by didntreadarticl »

sgt101 wrote: post #70
ux-app wrote: post #65

Earlier quoted context omitted.

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…

your question is pretty confusing. What dog? station is a vague word. Train station, police station? Case is a vague word. And asking whats in the station is still asking whats in the case, in a way.

Me: There's a blue suitcase in the airport and a policeman carrying a red bag opens the blue suitcase with a sniffer dog and fireman standing nearby. The dog is worried about the suitcase but the policeman isn't. What does the fireman think is inside the red bag?

ChatGPT: As a language model AI, I do not have personal opinions or emotions. I cannot speculate what the fireman thinks is inside the red bag as it is not specified in the information given.

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

#86

Post by pdonis »

mietek wrote: post #79
pdonis wrote: post #60

Earlier quoted context omitted.

> 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 your own experiences that they're probably experiencing the same thing you are. That judgment is not just based on the words other people use. It is based on knowing that other people's brains and minds have the same sort of semantic…

I don’t think you know whether I have a mind or not.

If you object to the term "mind", just leave it out and read "brain and mind" as just "brain". I'm a physicalist so I don't think the mind is something separate from the brain anyway, so it's all the same to me.

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

#87

Post by avgcorrection »

Workaccount2 wrote: post #18

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

What is modernity but a two-hundred year old experiment where the masters try to tell the other humans how they are just well-dressed machines? Soon to be replaced by the mechanical machine, then by the digital computer, then by the language model.

Of course you too, nerd-handmaiden, is a willing accomplice in this charade. Self-satisfied because it makes you feel special, above the herd, even though you are also not-special, in the grand scheme of things…? Well, no matter.

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

#88

Post by strbean »

didntreadarticl wrote: post #66
pdonis wrote: post #52

Earlier quoted context omitted.

> 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 c…

Yeah, that argument seems especially hollow.

Take someone and put their brain in a jar, with some Brain Computer Interface that enables call-and-response text chat. Are they suddenly not conscious, because they no longer have some transcendent connection with reality?

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

#89

Post by ux-app »

sgt101 wrote: post #70
ux-app wrote: post #65

Earlier quoted context omitted.

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…

>However, based on the information provided, it can be inferred that the fireman may be concerned about the contents of the case

this is complex "reasoning" (or whatever ChatGPT is doing. My 5 year old would struggle with the convoluted logic let alone complex language. In my layman view this is mind blowing.

>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.

I'm not sure what you're dismissing here? At least from my point of view The "logic" that ChatGPT demonstrates here can't be dismissed with your explanation.

If anything I'm even further amazed by the example you provided!

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

#90

Post by pdonis »

strbean wrote: post #78
pdonis wrote: post #57

Earlier quoted context omitted.

> Is it not also possible that the study suggests that the human mind actually operates as a statistical regression over billions of data points rather than through some kind of Baysian logic? No. Human minds have semantic relationships to the rest of the world that LLMs do not have. The comparisons being made between the two, not just in this paper but in all of the hype surrounding LLMs, are simply invalid. But the…

> Human minds have semantic relationships to the rest of the world that LLMs do not have. This is a bold claim that seems built on a presumption of mind-body dualism. Brains don't have semantic relationships with anything. They are neurons hooked up to sensors and actuators. Any inferences they produce are the result of statistical processes.

> This is a bold claim that seems built on a presumption of mind-body dualism.

Not at all. I'm a physicalist; I don't believe the mind is a separate thing from the brain.

> Brains don't have semantic relationships with anything.

Yes, they do: you describe them yourself:

> They are neurons hooked up to sensors and actuators.

Those are semantic relationships with the rest of the world. Although your short description does not by any means do justice to the complexity and richness of those relationships.

Post reply on HN