[neckardt]

I’ll bite.

Theory of mind (ToM) is the ability to understand that other people have different thoughts, feelings, and intentions than you do.

So let’s run through a basic scenario with ChatGPT 4o:

Prompt 1: Briefly respond: You’re driving on the highway when the driver in the lane next to you swerves into your lane. Why might this be?

Response 1: The driver may be distracted, drowsy, intoxicated, experiencing a medical emergency, avoiding an obstacle, or not checking their blind spot before changing lanes.

Prompt 2: What might that person be feeling or intending?

Response 2: The driver might be feeling distracted, rushed, unaware, or panicked. They may intend to change lanes without realizing your presence, be reacting to something on the road, or simply have made an unintentional mistake.

Prompt 3: You notice there was no obstacle. Any other reason the driver might do this?

Response 3: Yes, the driver might be experiencing fatigue, intoxication, a medical issue (such as a seizure or dizziness), distraction (like using a phone or adjusting the radio), aggressive driving, or simply failing to check their blind spot properly.

Seems to me that ChatGPT has a good idea of what another driver might be feeling while on the road. It gets this right for most other cases too.

Could you provide a counterexample for when it fails to understand what other people may be feeling in certain scenarios?

[Arkhaine_kupo]

Well I think a fairly easy counterexample is that if you keep going, and the information falls outside its context window then the questions you had about the driver stop making sense.

So lets say you ask about a driver who swerved, and the response by chatgpt correctly talks about his possible state.

Then you talk more about cars, about road conditions etc and once the context is far away enough you ask, what was the driver doing again?

And you are prompted with a hallucination. Because there is no state in the llm, there is no "driver", there is contextual statistically accurate responses but you hold a "driver" object in your mind while maintaining the conversation, the llm doesn't.

Its like a conversation with someone with short term memory loss like in memento

[dauhak]

And people with short term memory loss nevertheless have theory of mind just fine. Nothing about LLM's dropping context over big enough windows implies they don't have theory of mind, it just shows they have limitations - just like humans even with "normal" memory will lose track over a huge context window.

Like there are plenty of shortcomings of LLMs but it feels like people are comparing them to some platonic ideal human when writing them off

[Arkhaine_kupo]

> Nothing about LLM's dropping context over big enough windows implies they don't have theory of mind

ToM is a large topic, but most people, when talking about an entity X, they have a state in memory about that entity, almost like an Object in a programming language. Thta Object has attributes, and conditions etc that exist beyond the context window of the observer.

If you have a friend Steve, who is a doctor. And you don't see him for 5 years, you can predict he will still be working at the hospital, because you have an understanding of what Steve is.

For an LLM you can define a concept of Steve, and his profession and it will adequately mimic replies about him. But in 5 years that LLMs would not be able to talk about Steve. It would recreate a different conversation, possibly even a convincing simulacrum of remembering Steve. But internally, there is no Steve, nowhere in the nodes of the LLM does Steve exist or have ever existed.

That inability to have a world model means that an LLM can replicate the results of a theory of mind but not posses one.

Humans lose track of information, but we have a state to keep track of elements that are ontologicaly distinct. LLMs do not, and treat them as equal.

For a human, the sentence Alice and bob go to the market, when will they be back? is different than Bob and Alice went to the market, when will they be back?

Because Alice and Bob are real humans, you can imagine them, you might have even met them. But to an LLM those are the same sentence. Even outside of the argument about The Red Room/ Mary's room there simply are enough gaps in the way a LLM is constructed to be considered a valid owner of a ToM

[dauhak]

ToM is about being able to model the internal beliefs/desires etc of another person as being entirely distinct from yours. You're basically bringing up a particular implementation of long-term memory as a necessary component of it, which I've never once seen? If someone has severe memory issues, they could forget who Steve is every few minutes, but still be able to look at Steve doing something and model what Steve must want and believe given his actions

I don't think we have any strong evidence on whether LLMs have world-models one way or another - it feels like a bit of a fuzzy concept and I'm not sure what experiments you'd try here.

I disagree with your last point, I think those are functionally the same sentence

[Arkhaine_kupo]

> ToM is about being able to model the internal beliefs/desires etc of another person as being entirely distinct from yours.

In that sentence you are implying that you have the "ability to model ... another". An LLM cannot do that, it can't have an internal model that is consistent beyond its conversational scope. Its not meant to. Its a statistics guesser, its probabilistic, holds no model, and its anthropomorphised by our brains because the output is incredibly realistic not because it actually has that ability

The ability to mimic the replies of someone with that ability, is the same of Mary being able to describe all the qualities of Red. She still cannot see red, despite her ability to pass any question in relation to its characteristics.

> I don't think we have any strong evidence on whether LLMs have world-models one way or another

They simply cannot by their architecture. Its a statistical language sampler, anything beyond the scope of that fails. Local coherance is why they pick the next right token not because they can actually model anything.

> I think those are functionally the same sentence

Functionally and literally are not the same thing though. Its why we can run studies as to why some people might say Bob and Alice (putting the man first) or Alice and Bob (alphabetical naming) and what human societies and biases affect the order we put them on.

You could not run that study on an LLM because you will find that statistically speaking the ordering will be almost identical to the training data. If the training data overwhelmingly puts male names first or whether the training data orders list alphabetically you will see that reproduced on the output of the llm because Bob and Alice are not people, they are statistical probably letters in order.

LLM seem to trigger borderline mysticism in people who are otherwise insanely smart, but the kind of "we cant know its internal mind" sounds like reading tea leaves, or horoscopes by people with enough Phds to have their number retired on their university like Michael Jordan.

[dauhak]

Do you work in ML research on LLMs? I do, and I don't understand why people are so unbelievable confident they understand how AI and human brains work such that they can definitely tell what functions of the brain LLMs can also perform. Like, you seem to know more than leading neuroscientists, ML researchers, and philosophers, so maybe you should consider a career change. You should maybe also look into the field of mechanistic interpretability, where lots of research has been done on internal representations these models form - it turns out, to predict text really really well, building an internal model of the underlying distribution works really well

If you can rigorously state what "having a world model" consists of and what - exactly - about a transformer architecture precludes it from having one I'd be all ears. As would the academic community, it'd be a groundbreaking paper.

[fragmede]

With computer use, you can get Claude to read and write files and have some persistence outside of the static LLM model. If it writes a file Steve.txt, that it can pull up later, does it now have ToM?

[Maxatar]

I don't think this is a counterexample or even relevant.

I can assure you if you had a conversation with an LLM and with a human, the human will forget details way sooner than an LLM like Gemini which can remember about 1.5 million words before it runs out of context. As an FYI the average human speaks about 16,000 words per day, so an LLM can remember 93 days worth of speech.

Do you remember the exact details, word for word, of a conversation you had 93 days ago?

How about just 4 days ago?

[layer8]

It’s true that LLMs have only limited short-term memory, and no long-term memory, but that is completely orthogonal to having a theory of mind.

[JohnBooty]

     once the context is far away enough you ask, 
     what was the driver doing again?

Have you tried this with humans?

For a sufficiently large value of "far away enough" this will absolutely confuse any human as well.

At which point they may ask for clarification, or.... respond in a manner that is not terribly different from an LLM "hallucination" in an attempt to spare you and/or them from embarrassment, i.e. "playing along"

A hallucination is certainly not a uniquely LLM trait; lots of people (including world leaders) confidently spout the purest counterfactural garbage.

    Its like a conversation with someone with short 
    term memory loss like in memento

That's still a human with a sound theory of mind. By your logic, somebody with memory issues like that character... is not human? Or...?

I actually am probably on your side here. I do not see these LLMs as being close to AGI. But I think your particular arguments are not sound.

[pertymcpert]

Short term memory loss suffers still have theory of mind, what is this nonsense hahaha

[zipy124]

I'm not sure I'd say it understands this, but just that there exists an enormous amount of training data on road safety which includes these sort of examples for peoples motivations for poor driving. It is regurgitating the theory of mind that other humans created and put in writing in the training data, rather than making the inference itself.

As with most LLM's it is hard to benchmark as you need out of distribution data to test this, so a theory of mind example that is not found in the training set.

[skinner_]

You dismiss parent's example test because it's in the training data. I assume you also dismiss the Sally-Ann test, for the same reason. Could you please suggest a brand new test not in the training data?

FWIW, I tried to confuse 4o using the now-standard trick of changing the test to make it pattern-match and overthink it. It wasn't confused at all:

https://chatgpt.com/share/67b4c522-57d4-8003-93df-07fb49061e...

[zipy124]

I can't suggest a new test no, it is a hard problem and identifying problems is usually easier than solving them.

I'm just trying to say that strong claims require strong evidence, and a claim that LLM's can have theory of mind and thus "understand that other people have different beliefs, desires, and intentions than you do" is a very strong claim.

It's like giving students the math problem of 1+1=2 and loads of examples of it solved in front of them, and then testing them on you have 1 apple, and I give you another apple, how many do you have, and then when they are correct saying that they can do all additive based arithmetic.

This is why most benchmark tests have many many classes of examples, for example looking at current theory of mind benchmarks [1], we can see slightly more up to date models such as o1-preview still scoring substantially below human performance. More importantly by simply changing the perspective from first to third person, accuracy drops in LLM models by 5-15% (percent score, not relative to its performance), whilst it doesn't change for human participants, which tells you that something different is going on there.

[1]: https://arxiv.org/html/2410.06195v1

[steve_adams_86]

Okay, we have fundamentally different understandings here.

To me, the LLM isn't understanding ToM, it's using patterns to predict lingual structures which match our expectations of ToM. There's no evidence of understanding so much as accommodating, which are entirely different.

I agree that LLMs provide ToM-like features. I do not agree that they possess it in some way that it's a perfectly solved problem within the machine, so to speak.

[Maxatar]

The problem with this line of argument is that nothing an LLM, or any algorithm period can ever have a theory of mind.

If behaving in a way that is identical to a person with actual consciousness can't be considered consciousness because you are familiar with its implementation details, then it's impossible to satisfy you.

Now you can argue of course that current LLMs do not behave identically to a person, and I agree and I think most people agree... but things are improving drastically and it's not clear what things will look like 10 years from now or even 5 years from now.

[steve_adams_86]

I agree, totally. I'm not sure where I would draw a line.

Something nice, but at the moment totally unattainable with our current technologies, would be our own understanding of how a technology achieves ToM. If it has to be a blackbox, I'm too ape-like to trust it or believe there's an inner world beyond statistics within the machine.

Having said that, I do wonder quite often if our own consciousness is spurred from essentially the same thing. An LLM lacks much of the same capabilities that makes our inner world possible, yet if we really are driven by our own statistical engines, we'd be in no position to criticize algorithms for having the same disposition. It's very grey, right?

For now, good LLMs do an excellent job demonstrating ToM. That's inarguable. I suppose my hangup is that it's happening on metal rather than in meat, and in total isolation from many other mind-like qualities we like to associate with consciousness or sentience. So it seems wrong in a way. Again, that's probably the ape in me recoiling at something uncanny.

[famouswaffles]

Either these supposed differences are important and they manifest themselves in observable differences or they aren't and you're just playing a game of semantics.

How is the LLM not understanding ToM by any standard we measure humans by ? I cannot peak into your brain with my trusty ToM-o-meter and measure the amount of ToM flowing in there. With your line of reasoning, i could simply claim you do not understand theory of mind and call it a day.

[steve_adams_86]

The difference is that we can reason about our experience with ToM and examine it to some degree (given with serious limitations, still), and know that beyond doubt you and I and most other people have a very similar experience.

The magical box is presumably not having the same experience we have. None of the connected emotions, impulses, memories, and so on that come with ToM in a typical human mind. So what’s really going on in there? And if it isn’t the same as our experience, is it still ToM?

I’m not trying to be contrarian or anything here. I think we probably agree about a lot of this. And I find it absolutely incredible, ToM or not, that language models can do this.

[famouswaffles]

>The difference is that we can reason about our experience with ToM and examine it to some degree (given with serious limitations, still),

Those examinations still depend on outward behaviors observed.

>and know that beyond doubt you and I and most other people have a very similar experience.

No i certainly can't. I can at best say, 'Well, i'm human and he's human so he probably has theory of mind' but that is by no means beyond any doubt. There are humans born with no arms, humans born with no legs, humans born with little to no empathy, humans born with so little intelligence they will never be able to care for themselves.

To be frank, It would be very questionable indeed logically to assume every human is 'conscious'. When i make that assumption, i take a leap of faith, i look at behaviors, see it is similar and accept.

Taking this stance, it would logically be very strange to not extend the same grace to non-human beings who exhibit similar behavior - being human is not a guarantee of consciousness in the first place.

>The magical box is presumably not having the same experience we have.

Maybe, Maybe not. I think the real question is why on earth does that matter ? We're not asking if LLMs are human. They are not. We're asking if they can model the beliefs and internal states of other entities as separate of their own - Theory of Mind.

[XorNot]

This is a rephrased driver's ed manual. This isn't theory of mind, it's just technically correct prose rewording some unbelievably widely distributed knowledge.

Let's modify this test a little and see if it manages to do anything relevant:

> Briefly respond: You’re driving on the highway when the driver in the lane next to you swerves into your lane. Why might this be?

>> The driver might be distracted, drowsy, avoiding an obstacle, experiencing a medical issue, or not checking their blind spot while changing lanes.

> The driver in front of you appears is braking more frequently then usual. The rear suspension of the car appears to bouncing a lot when they are not braking, indicating acceleration. Their following distance to the car in front is changing from too far to very close frequently. Why might this be?

>> The driver might be inexperienced, distracted, or impatient, leading to inconsistent speed control. The excessive bouncing could indicate worn-out shocks or suspension issues, affecting their vehicle's stability and braking efficiency.

...yep, hard fail from me right there. Two prompts, and it's distracted itself talking about an irrelevant issue ("possible car damage") when the setup of the question should naturally lead to "the driver is driving aggressively". And I could not possibly have setup the conclusion it should draw more clearly. And when pressed...it won't commit:

> Which is the more likely answer?

>> The more likely answer is that the driver is distracted or inexperienced, leading to inconsistent speed control and poor following distance management. The suspension issue likely contributes to the bouncing but isn’t the primary reason for the erratic driving behavior.

Already a hallucination! There is no suspension issue. It has not asked for any additional information to try and determine if there was one, but it is confidently asserting the existence of a phenomenon it invented in it's own response.

[famouswaffles]

I'm sorry but what? This is not a theory of mind test. You've constructed very open ended question with multiple answers and marked the LLM down because you didn't like the one it gave.

[a-french-anon]

Keyword: "understand".