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

241–250 of 321 posts

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

#241

Post by pegasus »

d1sxeyes wrote: post #238
abeppu wrote: post #213

Earlier quoted context omitted.

The whole point of this conversation is whether talking like an agent that has a theory of mind and actually having a theory of mind are the same thing. I responded to a thread about what "knowing" is, and the same distinction can apply. You're responding with "if it talks like it knows what a cat is, it must know what a cat is", and that's totally begging the question.

While I agree with your point, how would you test that? How could you determine whether an LLM “knows” what a cat is. And what is “knowing”? If I know that a Mæw tends to nạ̀ng bn a S̄eụ̄̀x, isn’t that the first thing I’ve learned? And couldn’t I continue to learn other properties of Mæws? How many do I need to learn to “know” what a Mæw is?

Like GP said, the LLM has no chance at knowing what a cat is, regardless of how much data it ingests, because a cat is not made of data. It's not like you're getting closer and closer to knowing what a "Mæw" is. You were at the same remote distance all the time. This is called the "grounding problem" in AI.

As for how you would test it, I think one-shot learning would get one closer to proving understanding.

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

#242

Post by didntreadarticl »

abeppu wrote: post #206
didntreadarticl wrote: post #130

Earlier quoted context omitted.

Ok I like your thought experiment. Lets change it a bit. Instead of it being an unknown language, its English (a language you know), but every single Noun, Verb, Adjective or Preposition has been changed to Thai (a language you dont know). The Mæw Nạ̀ng Bn the S̄eụ̄̀x. If you had sufficient opportunity to study this pile of text, you'd begin to pick out patterns of which words appear together, and what order words of…

If you're constructing this to rely on my prior knowledge both of the world and of English, then I must remind you that those are things the LLM does not have. We have to be careful to not allow our human inferential biases from distorting our thinking about that the models are doing.

I know that. its a metaphor to adjust the 'Thai Language' intuition-pump that was presented. I'm making it easier to imagine how a Large Language Model might make a Model of the Language

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

#243

Post by selfmodruntime »

kabdib wrote: post #169

From Neuromancer (William Gibson): He coughed. "Dix? McCoy? That you man?" His throat was tight. "Hey, bro," said a directionless voice. "It's Case, man. Remember?" "Miami, joeboy, quick study." "What's the last thing you remember before I spoke to you, Dix?" "Nothin'." "Hang on." He disconnected the construct. The presence was gone. He reconnected it. "Dix? Who am I?" "You got me hung, Jack. Who the fuck are you?" "…

Sometimes I feel like Gibbson first wrote dozens of paragraphs about the backstory between two characters, only to condense it into a one page conversation filled with inside jokes and references to a common past.

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

#244

Post by Tv9m »

toss1 wrote: post #190

What this shows is flaws in the test, not that ChatGPT3 has a theory of mind. ChatGPT3 does not even have a theory of physical objects and their relations, nevermind a theory of mind. This merely shows that an often useful synthesis of phrases statistically likely to occur in a given context and grammar-checked, will fool people some of the time, and a better statistical model will fool more people more of the time.…

What would be evidence that a prediction machine had developed a theory of mind?

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

#245

Post by unnah »

arrow7000 wrote: post #216
p0pcult wrote: post #143

Earlier quoted context omitted.

Have you ever read any Julian Jaynes? Check out "The Origin of Consciousness in the Breakdown of the Bicameral Mind"

Any specific part of it?

You can just read this review instead of the book: https://slatestarcodex.com/2020/06/01/book-review-origin-of-...

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

#246

Post by d1sxeyes »

pegasus wrote: post #241
d1sxeyes wrote: post #238

Earlier quoted context omitted.

While I agree with your point, how would you test that? How could you determine whether an LLM “knows” what a cat is. And what is “knowing”? If I know that a Mæw tends to nạ̀ng bn a S̄eụ̄̀x, isn’t that the first thing I’ve learned? And couldn’t I continue to learn other properties of Mæws? How many do I need to learn to “know” what a Mæw is?

Like GP said, the LLM has no chance at knowing what a cat is, regardless of how much data it ingests, because a cat is not made of data. It's not like you're getting closer and closer to knowing what a "Mæw" is. You were at the same remote distance all the time. This is called the "grounding problem" in AI. As for how you would test it, I think one-shot learning would get one closer to proving understanding.

The grounding problem is an intelligence problem, not an artificial intelligence problem.

How would you envision a test based on one-shot learning working?

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

#247

Post by mensetmanusman »

frogperson wrote: post #220
mensetmanusman wrote: post #21

Earlier quoted context omitted.

“ My belief, based on experiences with domestic and wild animals is that there is nothing uniquely human about "theory of mind". “ This belief might simply arise from the human ability to try to understand events through pattern matching. Certainly humans are very different than any other animals when it comes to thinking and problem solving.

What does it mean that my cats 100% understand what container their treats are kept in? I can not leave the container on the counter or they will knock it onto the floor and tear the lid off to get inside. I am conviced they understand something is hidden in a box. Object permanence is something humans and cats both learn and understand.

I’m talking about the ability to write down thoughts.

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

#248

Post by didntreadarticl »

quonn wrote: post #179
letmevoteplease wrote: post #122

Earlier quoted context omitted.

There's a good chance a human would respond in the same way, because they would assume you were asking a good-faith question instead of nonsense. Try asking it an original question that has some kind of deducible answer. Its abilities are more impressive than you would expect from an algorithm that just predicts the next word. I doubt there is anything quite like this situation in the training data: https://i.imgur.c…

> than you would expect from an algorithm that just predicts the next word. I think there is common mistake in this concept of just predicting the next word. While it is true that just the next word is predicted, a good way to do that is to internally imagine more than the next word and then just spit out the next word. Of course with the word after that the process repeats with a new imagination. One may say that th…

It predicts the next word based on the preceding 2000 words or so, thats the thing. And to do that takes serious modelling.

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

#249

Post by didntreadarticl »

kilgnad wrote: post #153
didntreadarticl wrote: post #150

Earlier quoted context omitted.

I think about its 4000 token length. For the brief amount of time that it absorbs and processes those 4000 tokens, is there a glimmer of a hint of sentience? Like it is microscopically sentient for very short bursts and then resets back to zero.

Does sentience need memory? I would say it's orthogonal. There are examples of people in the real world who only remember things for about 3 minutes before they lose it. They can't form any real memories. These people are still sentient despite lack of memory. See: https://www.damninteresting.com/living-in-the-moment/ If chatGPT was sentient, I would say it has nothing to do with the 4000 character limit. The 4000 ch…

I dont think of the 4000 tokens as its memory as such. Its more like the size of its thinking workspace

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

#250

Post by toss1 »

Tv9m wrote: post #244
toss1 wrote: post #190

What this shows is flaws in the test, not that ChatGPT3 has a theory of mind. ChatGPT3 does not even have a theory of physical objects and their relations, nevermind a theory of mind. This merely shows that an often useful synthesis of phrases statistically likely to occur in a given context and grammar-checked, will fool people some of the time, and a better statistical model will fool more people more of the time.…

What would be evidence that a prediction machine had developed a theory of mind?

well, I'd first need to see that it had a Theory of Feet... ;-)

More seriously, that it can actually understand and wield abstract concepts. Can it accurately and repeatedly understand that "the foot attaches to the shin bone, which attaches to the thigh bone, which attaches to the hip bone...", and that these have certain degrees of freedom, but not others, and that one foot goes in front of the other, and to easily and reliably distinguish a normal walk from a silly walk . . .

Yes, these are different levels of abstraction, especially the last one, and they need to be very accurate to even reach a young child's level of understanding, and this is just one branch of a branch of a branch in the entire fractal pattern of understanding that is necessary for a more general intelligence.

Once that is in place, and it can show evidence that it can model it's own mind, then it might be able to model someone else's mind.

While the statistical 'abstraction' and remixing seen in these "AI" systems is sometimes impressive and useful, it is frequently revealed that there is utterly no conceptual understanding beneath it. It is merely a statistical re-mixer abstracting patterns of words that occur near other words, remixing them and filtering for grammatical output.

It hasn't got a theory of anything, nevermind a theory of mind.

Post reply on HN