Hacker News new | ask | show | jobs
by corethree 1034 days ago
The parlor tricks are getting better. In terms of practicality you just need to look at AI art. That stuff is good enough to replace the real thing.

In terms of actual sentience, understanding

I had chatGPT answer questions in the following order:

   1. Describe to me what happens when you throw sugar in coffee
   2. Describe the same thing in terms of atoms. 
   3. Is this an example of entropy decreasing? 
   4. What if the arrow of time was reversed. Describe what happens again at the atomic level. 
   5. What if there were two regions in space one with increasing entropy and another with decreasing entropy. I place the coffee cup such that one half is in one region the other half is in the other region. What happens?
Each answer displayed astonishing understanding of what occurs. This was the final answer to the fifth question:

   -----------------------------------------------

   The scenario you've proposed is purely hypothetical and quite speculative because it defies our current understanding of the laws of physics, particularly the Second Law of Thermodynamics, which stipulates that entropy in an isolated system tends to increase. Nevertheless, it's a fascinating thought experiment. Here's what might happen if you had a cup of coffee straddling two such regions:
   
   The Increasing Entropy Region:

    Dissolution and Distribution: On this side, sugar would behave as it does in our observable universe. It would dissolve in the coffee and disperse randomly throughout the half of the liquid.

    Mixing and Thermal Energy: Molecules in this region would continue to collide and interact based on thermal motion, contributing to faster dissolution and dispersion of sugar.

    Sweetening: The coffee in this half would become sweet as the sugar molecules interact with the liquid and dissolve.

   The Decreasing Entropy Region:

    Reforming Crystals: On this side, dissolved sugar would spontaneously start forming sugar crystals, leading to a decreasing level of entropy.

    Unmixing: The sugar would start to separate from the coffee and move to form a distinct layer or solid chunks, further decreasing entropy in that half.

    Unsweetening: Any sweetness initially imparted to this side would disappear as sugar molecules revert to a more ordered state.

   Challenges:

    Interface: The most mysterious part would be at the interface where the two regions meet. Would a sugar molecule crossing from the increasing to the decreasing entropy region suddenly reverse its course? Would there be some form of "entropy gradient" or "entropy tension" at the boundary? This part is extremely speculative and likely paradoxical.

    Energy Conservation: Energy conservation laws might become complicated here. The energy required for sugar to crystallize in the decreasing entropy zone would have to come from somewhere, and how this balances with the increasing entropy side would pose a significant scientific puzzle.

    Thermodynamic Anomalies: The coffee cup itself would be under very peculiar thermodynamic conditions, subject to two entirely different sets of rules. The temperature might behave inconsistently across the boundary, and heat exchange would likely be disrupted in perplexing ways.

    Taste Experience: If you were to taste the coffee, each half of the cup would offer a radically different experience, one sweet and the other likely reverting back to its original unsweet state.

    Perceptual Paradox: From a human perception standpoint, witnessing sugar both dissolve and crystallize in the same cup of coffee would be a profound and likely disorienting experience.

    Time's Arrow: This set-up implicitly questions the nature of time itself. Time seems to behave differently on each side, challenging our deepest notions about causality, sequence, and even reality.

   Again, it's worth noting that this scenario conflicts with our current understanding of physics, but it's a fascinating avenue for speculative thought. Such a universe, if it could exist, would fundamentally challenge our understanding of physical laws and reality as we know it.

   -------------------------------------------------

This answer here is anything but a magic trick. It shows deep understanding of conceptual reality by answering complex questions that are unlikely to exist anywhere else on the internet. The AI literally talked about the mysterious interface without me prompting it at all. It knows the conceptual consequence of two regions of space side by side with differing levels of entropy. The answer is not simply a trick of the next best language token.

Is it a practical answer? No. Because the question itself isn't practical. But a non-practical answer does not make this answer a parlor trick.

The entire internet is dismissing this thing as a parlor trick because LLMs fail to add large numbers. I mean come on man. You don't need to be able to do math like a calculator in order to "understand" things.

AI is not yet completely practical. That much is true. However, it is clearly No longer a parlor trick and it is getting closer and closer to transitioning into practical. When that day comes.... Good luck to us all.

4 comments

It sounds like understanding, but not sure because it already doesn't consider if sugar (or water) molecules could form/exist in the alternate universe (also ignores trading off energy vs entropy changes) or should the water just crystalize in one half of the cup (why isng that considered)?. I don't think one can say it has really though about the problem. To be fair, language is probably not the tool to analyse the problem but mathematics are.

It is a bit like technobabble.

You make a claim here with "Each answer displayed astonishing understanding of what occurs." and the question you fail to ask is: Whose understanding?

The responses are based on the accumulated knowledge of humans and not machines. The systems have not thought through anything and understand nothing. A process of analysing or pattern matching the input question with the data stored retrieves an answer. But that data stored is human knowledge and human effort not machine.

If you look very carefully at the results obtained, it either contains "interesting errors" (for which an intelligent human would pick up) or it is a summation of human knowledge.

The answers still have to be tested and confirmed for rationality and applicability by humans. In other words, this is a tool like all tools created by humans.

I have seen too many examples of what are supposed to be correct answers that contained subtle and not so subtle errors.

Like every system we have ever made, Garbage in gets us Garbage out. We are the ones responsible to checking those answers and making sure that they make sense in the real world.

> A process of analysing or pattern matching the input question with the data stored retrieves an answer.

They're not just retrieving stored text like pulling the most relevant passage from a database. If they were they'd not be able to deal with things outside the training set. They couldn't write code for a custom library that was created after the cutoff (they can with a description), and they couldn't write about terms made up in the question.

I don't see why not. It's not taking a single answer from a database no, it's taking several based on probability and merging them into what it thinks we're looking for. If you learn to multiply with code to perform one task, you can then apply that knowledge for a completely different task. It may look like solving a completely new problem but the LLM doesn't even see the difference.

When you use the term "custom library" that might be you over-complicating the task. It's still just looking up function to do x, function to do y and applying it to the output. Don't get me wrong it's impressive where we're at but there's no need to exaggerate it as magic.

> . It's still just looking up function to do x, function to do y and applying it to the output.

I mean no, no it isn't.

I'm giving it info on how to construct data models with a custom library, so interacting with that is not using anything previously stored, and then giving it businesses/tasks to model as simple human descriptions.

If you tell me that something which

* Takes a human description of a problem

* Describes back to me the overall structure and components required to solve it with a hierarchy

* Converts that into code, correctly identifying where it makes sense for an address to be contained within a model or distinct and referenced

* Correctly reuses previously created classes that are obviously not in its original dataset

has no understanding or reasoning and it just regurgitating things it's seen before simply mashed together, I don't know what to say.

Frankly

> it's taking several based on probability and merging them into what it thinks we're looking for. I

Sounds pretty much like understanding and reasoning to me.

> but there's no need to exaggerate it as magic.

I'm absolutely not saying there's magic. Humans aren't magic and they can do reasoning. I'm saying it's not just looking up text and regurgitating it.

I think this is supported by things like othello-gpt, which builds an internal world model and outputs based on that.

It's difficult for me to assess how original your library is without examples, maybe I could find the exact implementation on github within 30 minutes. But I've yet to see anything that isn't just mashing together stackoverflow and git repositories to save time. I get the same answers with less wordy fluff from a simple search, but I also know where to look.

It's impressive that it knows the difference between "how many are 5 more apples than 10" compared to "how many percent are 5 apples of 10" (I don't know if it does, just assuming). But the first release also tried to reason why the weight of 1 pound of nails depends with the simple prompt "how much do 1 pound of nails weigh". That's most likely a perfect example of it mashing the classic "what weighs more, 1 pound of nails or 1 pound of feathers".

It IS just looking in a database, and mashing it with some fluff. I'm happy to be proven wrong but I need more than your word for it. My experience is that as the topic gets more niche (less data in the training set) the worse the answers I get and it starts making things up based on probability. It doesn't reason in the sense I assume you're expecting.

Have you had a look at othello gpt? https://thegradient.pub/othello/

It's a nice constrained example of a transformer learning a world model, not just looking up responses.

> It's impressive that it knows the difference between "how many are 5 more apples than 10" compared to "how many percent are 5 apples of 10" (I don't know if it does, just assuming). But the first release also tried to reason why the weight of 1 pound of nails depends with the simple prompt "how much do 1 pound of nails weigh". That's most likely a perfect example of it mashing the classic "what weighs more, 1 pound of nails or 1 pound of feathers".

Is there a formulation here that would get to a point where you'd think it's not just mashing things together? Are there elements of a simple question that would be required?

Here's a slightly trickier one for it "Which weighs more, a pound of feathers or balloons made from one pound of rubber then filled with 100g of helium?"

https://chat.openai.com/share/b841c96f-e46c-4adf-8ec3-8778ff...

> You make a claim here with "Each answer displayed astonishing understanding of what occurs." and the question you fail to ask is: Whose understanding?

The answer is obvious. The LLM is understanding the concepts. The last question was unique. The resulting answer was also unique.

It was not a "retrieved" answer. It was a unique answer. A correct composition of several underlying concepts. A correct composition can only be formulated if the machine had correct understanding of each concept and how they relate to one another.

This thing understands you. It wholly owns this understanding. It is not regurgitating knowledge. It is inventing new answers.

Wake up man. I had the LLM invent 6 regions and heat the cup of coffee to plasma levels of heat. The answer and composition of concepts was remarkable.

You're calling it a parlor trick because of subtle errors? Bro. Come on.

> The answer is obvious. The LLM is understanding the concepts

Who created the LLM? Whose understanding underpins the LLM?

Certainly not the LLM.

> This thing understands you.

Does it? Or is this a result of the intelligence of the human beings involved in building the LLM?

> I had the LLM invent 6 regions and heat the cup of coffee to plasma levels of heat.

Did the LLM actually invent anything? Or was this result directly based on you and your intelligence with the recorded knowledge of all the human sources involved in the solution?

> You're calling it a parlor trick because of subtle errors?

I haven't called it a parlour trick. All I am saying is that there is no intelligence in these systems. Human intelligence built them, but these systems in and of themselves have no intelligence.

We do of course build many intelligent systems all the time, they are called children.

>Who created the LLM? Whose understanding underpins the LLM?

Who created you? Whose understanding underpins you? Asking these questions about you is as irrelevant as asking it about the LLM.

Just because books, educations your teachers, the internet and your parents and the environment shaped everything you know doesn't preclude your membership into the category of things that are capable of understanding.

>Does it? Or is this a result of the intelligence of the human beings involved in building the LLM?

It does understand you. The intelligence of human beings who built it aren't directly involved as it was trained on external data.

>Did the LLM actually invent anything? Or was this result directly based on you and your intelligence with the recorded knowledge of all the human sources involved in the solution?

Does a human actually invent something or is it directly based on recorded knowledge?

You're asking irrelevant questions. Humans do not create things out of thin air either. Humans also invent things by composing existing knowledge to form concepts. The inventing that LLMs can do is equivalent in totality to our understanding of the word "invent"

>I haven't called it a parlour trick. All I am saying is that there is no intelligence in these systems. Human intelligence built them, but these systems in and of themselves have no intelligence.

Totally false. Not only are you wrong but experts in AI including the father of modern AI disagree with you completely and utterly.

If I copied your brain and replicated exactly that brain is "from human intelligence" but that copy of your brain is still an intelligence independent of it's origins and where it got it's knowledge.

>We do of course build many intelligent systems all the time, they are called children.

It's like you're eating your own logic. We also build intelligent systems called LLMs. Same concept.

You miss the point of the questions in relation to the LLM. However, your questions are important in relation to the fundamental difference between humans and what they create.

Let me put it this way: Humans are started with a single cell that eventually grows into an extraordinarily complex entity. If you look at new born babies, they have a capability of learning and exploring that we do not see in any artificial construct that we make.

Our artificial constructs have to be essential fully developed physically before we can then start the process of programming them. Humans have a capability to learn as they develop. We see this occur in all living things.

There is a fundamental insurmountable category difference here between living things and artificial constructs that we make.

Any appearance of understanding is based on the logic that we program into these artificial constructs. They cannot exceed what is programmed into them. Interestingly, living organisms can often exceed that. I think that all programmers should undertake a study of living things to gain a greater appreciation of what we do and just how simplistic are the things we do. That is a particular philosophical point of view that I hold.

I think that your appreciation of what we do and the constructs we create is not in accordance with reality. Not that this is particularly strange as far too many people have a much higher view of our technological prowess, especially when comparing to what has gone before. Starting from my undergraduate engineering days and the ongoing study of engineering and technological history, it has become quite clear that we are often today, quite ignorant of just how technologically advanced previous eras were in all sorts of different areas. There are plenty of research groups that are researching how previous generations were able to do things that we do not know how to do today.

> Does a human actually invent something or is it directly based on recorded knowledge?

Here, we do know that there is at least three ways that invention can arise. Logical progression on recorded knowledge, imagination as to how to solve a problem (thinking outside of the box), observation of the natural world around us.

> You're asking irrelevant questions.

For you to say that the questions I asked were irrelevant shows that you have limited yourself in your pursuit of knowledge and understanding.

> Humans do not create things out of thin air either.

When thinking outside of the box, they do. But I suspect that you may not appreciate this particular point.

> Humans also invent things by composing existing knowledge to form concepts.

As pointed out above, this is one mode of invention.

> The inventing that LLMs can do is equivalent in totality to our understanding of the word "invent"

Here, I disagree with you. But that is very likely to be a philosophical/metaphysical difference between us.

> Totally false. Not only are you wrong but experts in AI including the father of modern AI disagree with you completely and utterly.

Do you understand that you have devolved into a fallacious argument here? This is a seriously flawed fallacious argument on your part. The problem here is that your argument assumes that these [experts] you are referring to are correct, when you have not demonstrated that. Nor have they. There are many experts and others (all highly intelligent and talented people) who for all their intelligence and talent are just wrong. This has been shown to be the case many many times throughout the last century (let alone before that) when our understanding has changed because some little known person has come up with anew idea. One of the best examples here would be someone you would know of - Albert Einstein.

Now when you say

> If I copied your brain and replicated exactly that brain is "from human intelligence" but that copy of your brain is still an intelligence independent of it's origins and where it got it's knowledge.

Here, you have a problem. What is the difference between a living brain and a dead brain? In a single instant, we go from life to death and yet we don't know at this point in time what that difference is. There are lots of experiments being done today which are trying to study if there is a non-physical aspect to intelligence and free-will. Different experimenters in the same team have quite different interpretations of what the data means.

Do be so quick to assume that you know, when the researchers who study this can't agree.

> It's like you're eating your own logic. We also build intelligent systems called LLMs. Same concept.

Not at all. Intrinsically different and there is a vast categorical difference between children and our artificial constructs. From your comment, is it a valid assumption that you do not have children of your own or grandchildren of your own or even pets?

Let me ask a question, what is your background in building systems that augment human capability? If you have been involved in building LLM's, let me know.

It's generating code for a brand new library based on explanations from me, it can write poems about the current news headlines and it can answer hypotheticals with words I've made up. I agree it cannot be just looking up stored answers.

Gpt Othello is a good discussion about this that's more constrained too.

Talking about mixing coffee with sugar/milk and reversing the arrow of time (ie. entropy) is a widely talked about example.

That said, I agree with your arguments and conclusions. Humans are not able to do this kind of reasoning until they have had some education on the topic - and when they reason they get feedback to reinforce their conclusions if others agree or they get a more rigorous proof. We could do the exact same thing with an LLM. Would that potentially make a reasoning AI? For me the jury is still out, albeit I think we need better algorithms for it to be feasible.

> Talking about mixing coffee with sugar/milk and reversing the arrow of time (ie. entropy) is a widely talked about example.

But the interface is unique. That is not a topic widely talked about at all.

Question:

   Instead of two regions add a third region where entropy of the particles entering the region will always stays the same no matter what. Place the coffee cup such that it is in all 3 regions equally. Describe atomically what happens. 
Answer:

   --------------------------------------

   In this fictional universe where regions have varying entropy behavior, the coffee cup sits at a tri-junction: a third of it is in a region of increasing entropy (Region A), another third in a region of decreasing entropy (Region B), and the last third in a region where entropy remains constant (Region C).
In the Atomic Realm:

    Region A (Increasing Entropy):

    Sugar molecules randomly move throughout the coffee, driven by thermal motion. They strike water molecules and dissolve over time, eventually reaching a state of homogeneous distribution. The entropy of the system in this portion of the cup increases as expected.

    Region B (Decreasing Entropy):

    Astonishingly, sugar crystals spontaneously form in the coffee. Sugar molecules collide with water molecules and join an ever-growing crystalline lattice. Over time, the sugar becomes a distinct entity in the coffee, and the entropy of this system decreases.

    Region C (Constant Entropy):

    The sugar neither dissolves nor crystallizes. Instead, sugar molecules and water molecules co-exist in a dynamic but unchanging equilibrium. At the atomic level, every dissolution event is perfectly balanced by a crystallization event, maintaining constant entropy.
The Tri-Junction:

    Molecular Exchange:

    Some molecules, through Brownian motion, will wander across the boundary lines dividing the three regions. Entropic currents from Region A and B cross into Region C and are balanced out, maintaining a zero net change in entropy in that region. Special quantum-entangled pairs straddle the boundaries, existing in superpositions of increased, decreased, and unchanged entropy states.

    Entropic Flux and Balance:

    A constant entropic flux is established between the three regions. The entropic gradient tensor now has a third component, and the entropic flux density vector also adjusts to a tri-vector to balance out the exchange between the three regions.

    Localized Time Anomalies:

    At the atomic level, it's as if time runs forward in Region A, backward in Region B, and is somehow "static" or cyclical in Region C. Particles appear to remember both their past and future states in Region C, generating a unique form of atomic "temporal coherence."

    Causality and Quantum Superposition:

    Despite these anomalies, causality is preserved. Particles that cross into different regions adapt to the local entropy behavior and exhibit quantum behaviors that align with the local direction of time.

   In essence, the tri-junction becomes a hotbed of bizarre but mathematically consistent phenomena, a place where the fabric of spacetime and the fundamental laws of thermodynamics seem to negotiate a delicate truce.

   As for the cup of coffee, one-third of it will end up well-mixed, one-third will have sugar crystals, and the last third will remain an intriguing paradox of thermodynamics. You might call it the most scientifically fascinating cup of coffee ever brewed.

   -------------------------------------------------
This isn't a parlor trick regurgitation. It's displaying understanding of the concepts by speculating on new concepts via composition of several other concepts.
Of course it's not regurgitation. But it is combining related concepts and I'm sure that somewhere in its training input, there is plenty of talk about increasing, decreasing, and constant entropy.

However, it does not really say much. In particular the "Localized Time Anomalies" section for region C seems to be a hallucination and from there on, it really sounds like something a science writer, without the proper education, could have written.

It sounds good, but from an experts view, it is at best a popsci introduction to the subject.

>it really sounds like something a science writer, without the proper education, could have written.

It just flew past your head didn't it? You remarked on the similarities between an AI and a human in order to prove the triviality of AI.

Getting AI to the ability of a science fiction writer was an impossible feat just 3 or 4 years ago.

That's a fun example. Here's one I posted elsewhere about filling a balloon with a gas made of 1 proton and 100 neutrons at a kids party.

https://chat.openai.com/share/71224df4-5c6c-45f7-88fd-eec316...