this is an interesting problem but it’s more of a logic problem than a true test of theory of mind. when i think “theory of mind” i think being able to model an external agent with complete knowledge, incentives, and behavior. i would not doubt LLMs have something close to this for humans, almost by accident since they are trained on human outputs.
I would venture to guess that it has value in that we couldn't even begin to properly test a theory of mind if they can't yet reason through a logic puzzle. It would be like testing if a society could build a rocket ship when they don't know how to use tools.
LLMs, Theory of Mind, and Cheryl's Birthday
51–60 of 150 posts
Re: LLMs, Theory of Mind, and Cheryl's Birthday
#52What is a software program? The codification of a solution. What is a solution? An answer to a problem. What is a problem? The identification and expression of a need to be satisfied. What is a need? A uniquely human experience, one which only exists within the minds of people whom experience it.
Do animals not have needs?
We are animals as well, so a pedantic answer would be "yes." :-)
My actual answer is the origin of the thought process began by Norvig stating:
But none of them were able to write a program that finds the solution.
So while the concept of "need" is shared across many entities and widely applicable to many conversations, in this context it serves as a root cause answering "why write a program."Re: LLMs, Theory of Mind, and Cheryl's Birthday
#53The problem with evaluating LLMs is that there's a random component, and the specific wording of prompts is so important. I asked Claude to explain the problem, then write python to solve it. When it ran there was an exception, so I pasted that back in and got the correct answer. I'm not sure what this says about theory of mind (the first script it wrote was organized into steps based on who knew what when, so it see…
Yes, that helps. But if you iterate on this a few times (as I did last year with Code Interpreter), it reveals how much LLM's "like" to imitate patterns. Sure, often it will pattern-match on a useful fix and that's pretty neat. But after I told it "that fix didn't work" a couple times (with details about the error), it started assuming the fix wouldn't work and immediately trying again without my input. It learned th…
Re: LLMs, Theory of Mind, and Cheryl's Birthday
#54Earlier quoted context omitted.
GP is referring to the fact that if it becomes well known that LLM version X can’t solve problem Q, then the model’s trainers will make sure to include problem Q prominently in the training set, running it through over and over to ensure that version X+1 is able to solve the problem whether the model’s “reasoning” abilities have improved or not. Thus observers of the LLM space like us need to keep finding novel “Bell…
Oh, thanks for the correction. I did misinterpret. Though I will say that LLMs don't appear to be doing any better at the river crossing puzzles. They tend to "patch" the ones I and others actively tweet about but they still aren't becoming better at generalizing. I've taken this as fairly strong evidence as we're going in the wrong direction of reasoning (as opposed to similar direction). But the strongest evidence…
Re: LLMs, Theory of Mind, and Cheryl's Birthday
#55Earlier quoted context omitted.
I would venture to guess that it has value in that we couldn't even begin to properly test a theory of mind if they can't yet reason through a logic puzzle. It would be like testing if a society could build a rocket ship when they don't know how to use tools.
Children as young as 4 demonstrate theory of mind but would be unable to solve artificial logic problems like OP
Re: LLMs, Theory of Mind, and Cheryl's Birthday
#56Earlier quoted context omitted.
Yes, that helps. But if you iterate on this a few times (as I did last year with Code Interpreter), it reveals how much LLM's "like" to imitate patterns. Sure, often it will pattern-match on a useful fix and that's pretty neat. But after I told it "that fix didn't work" a couple times (with details about the error), it started assuming the fix wouldn't work and immediately trying again without my input. It learned th…
If I understood correctly, that anectode in first paragraph looks like an interaction with a child who is trying something but lacks confidence.
Re: LLMs, Theory of Mind, and Cheryl's Birthday
#57Earlier quoted context omitted.
If I understood correctly, that anectode in first paragraph looks like an interaction with a child who is trying something but lacks confidence.
It did look that way and it's a fun way to interpret it, but pattern-matching on a pretty obvious pattern in the text (several failed fixes in a row) seems more likely. LLM's will repeat patterns in other circumstances too.
Re: LLMs, Theory of Mind, and Cheryl's Birthday
#58Earlier quoted context omitted.
I would venture to guess that it has value in that we couldn't even begin to properly test a theory of mind if they can't yet reason through a logic puzzle. It would be like testing if a society could build a rocket ship when they don't know how to use tools.
What animals have theory of mind?
Our ability to understand animal intelligence is limited by or ability to ask appropriate questions, so we tend to underestimate intelligence outside of the primate space.
Here's an excellent book on this topic: https://www.goodreads.com/book/show/30231743-are-we-smart-en...
Re: LLMs, Theory of Mind, and Cheryl's Birthday
#59Earlier quoted context omitted.
Oh, thanks for the correction. I did misinterpret. Though I will say that LLMs don't appear to be doing any better at the river crossing puzzles. They tend to "patch" the ones I and others actively tweet about but they still aren't becoming better at generalizing. I've taken this as fairly strong evidence as we're going in the wrong direction of reasoning (as opposed to similar direction). But the strongest evidence…
Oh interesting, what variants were you using that it seems they patched?
Which weighs more, a kilogram of bricks or a pound of feathers
and that worked until the second or third update on GPT 3.5 (when everyone was like "but did you try 3.5?)Here's a river crossing puzzle with the current GPT-4o that "works"
----------------------------------------------------
> I have a duck, a goose, and a pig that I need to take across a river. If I live the duck and goose alone, the duck will quack. If I leave the pig with the goose the pig will oink. I can only fit two animals in the boat at a time. What is the quickest way to get all animals across the river?
To solve this puzzle, we need to find a way to transport the animals across the river without triggering the quacking or oinking conditions:
1. **First Trip:** Take the duck and the goose across the river. Leave the goose on the other side and take the duck back with you.
2. **Second Trip:** Take the pig across the river. Leave the pig on the other side and bring the goose back with you.
3. **Third Trip:** Take the duck and the goose across the river again.
Now all three animals are across the river, and at no point were the duck and goose left alone, nor were the pig and goose left together. This method ensures no quacking or oinking occurs.
----------------------------------------------------
Idk why it decided to add the extra constraint of keeping the animals quiet but hey, it doesn't really matter.As far as I know, I'm the first one that came up with this variant and strangely it has been consistently answered correctly when 4o came out (after my post got repeated by a few bigger names) so I thought it was patched, but just now I wasn't able to reproduce a success with various checkpoints and system prompts, so I guess it got undone?
----------------------------------------------------
> I have a fox, a goose, and a bag of corn that I need to transport across a river. All three can fit in the boat. If you leave the fox alone with the goose, it'll eat the goose. If you leave the goose alone with the corn, it'll eat the corn. Describe how to get all items safely across the river.
To solve this classic puzzle, follow these steps:
1. **Take the Goose Across First:** Start by taking the goose across the river and leave it on the other side.
2. **Return and Take the Fox Across:** Go back to the original side and take the fox across the river.
3. **Bring the Goose Back:** When you reach the other side, leave the fox there and take the goose back with you to the original side.
4. **Take the Corn Across:** Leave the goose on the original side and take the bag of corn across the river.
5. **Return Alone:** Leave the bag of corn with the fox on the other side and return alone to the original side.
6. **Take the Goose Across Again:** Finally, take the goose across the river one last time.
Now, all three items—the fox, the goose, and the corn—are safely across the river without any being eaten.
----------------------------------------------------
claude-3-5-sonnet-20240620 and claude-3-opus-20240229 both act like it is the normal puzzle.It doesn't matter if you say "All three can fit in the boat with the farmer." Nor if you ask it to explain its logic step-by-step.
The only humans I've seen struggle with this variant ask me to repeat the question several times before saying something similar to "I don't understand the trick. You just take all the animals across at once?" But the trick is there's no trick and I accept that as an answer lol.
FWIW, I've had several LLMs explain to me that all animals can fit in the boat and then proceed to do the normal solution to the puzzle. I've also seen it put all animals into the boat and then only drop one off and travel back and forth, or sometimes animals teleporting or even the framer. Sometimes the farmer is just going back and forth. That happens a lot when I use a variant where animals will follow the farmer and can swim.
Very often I see the better models great at getting the right answers but fail (or even worse) when explaining that answer. I don't think this makes the models useless, but I feel that their highest utility is mostly due to Google's ever decreasing quality. But what can you do?
Re: LLMs, Theory of Mind, and Cheryl's Birthday
#60AI researchers need to learn what terms like "theory of mind" actually mean before they write dumb crap like this. Theory of mind is about attributing mental states to others, not information. What Norvig has done here is present a logic puzzle, one that works equally well when the agents are Prolog programs instead of clever children. There's no "mind" in this puzzle at all. Norvig is being childishly ignorant to ca…
CS researchers do partake in some pretty low quality science.
My fav is AI researchers arrogantly rediscovering learning theory and pedagogy.