[mholt]

The common sentiment around AI in the 90s and early 2000s was that it didn't work; it had its hype, it had its heyday, but it seemed like a dead-end for the most part. The Perceptron was merely a linear function approximator. And the Multi-layer Perceptron was a little more capable, but the many orders of magnitude it would have to scale up in order to be convincing just wasn't feasible back then (it finally was in the 2010s).

Simple statistical models that aren't "AI" so much as just generic ML were and are quite useful: like recommendation and newsfeed engines ("the Algorithm" as we call it so often today). Love 'em or hate 'em, they can be quite good at predicting interest/engagement.

The resurgence in deep learning in the 2010s has shown us new magic tricks, but they're still just that: parlor tricks. At least they're more convincing tricks than what we had 40 years ago!

That's what ultimately depresses me about AI. It's still just a parlor trick. We haven't actually taught computers to think, to reason, to be innovative. Deep learning is definitely having its day, but I suppose this too will pass unless we can unlock certain ways to make AI reliable and responsible. Or... to just start understanding it in general.

[BoiledCabbage]

> That's what ultimately depresses me about AI. It's still just a parlor trick. We haven't actually taught computers to think, to reason, to be innovative.

And what do you feel when we make these parlor tricks more capable than us at the majority of tasks?

And what do you feel when we understand it well enough to realize we're the same type of parlor tricks?

To me it seems like you're most interested in a magic 'aha' moment and will miss or not be prepared for how the road in front of us likely unfolds.

[keiferski]

And what do you feel when we understand it well enough to realize we’re the same type of parlor tricks?

That’s called positivism and it has a lot of philosophical issues. I wouldn’t be so quick to assume that sensory appearance is equivalent to reality.

https://en.wikipedia.org/wiki/Positivism

[bondarchuk]

Sensory appearance not being equivalent to reality does not have any relevance to the question of AI and humans ultimately being the same kind of information-processing system. Just handwaving "that's X philosophical position and it has problems" does not strike me as a good argument either unless you manage to explain how these problems pertain to the question at hand.

[keiferski]

Unless AI becomes indistinguishable from human beings on a cellular level, yes, it’s entirely relevant and is the single most relevant thing. A lot of people seem to think that if an AI can simulate the appearance of a human being, that makes them equivalent to one. It might introduce some problems WRT to determining if an entity is human or not, but this doesn’t somehow prove they humans are just a “parlor trick.”

This is a positivistic argument and as I pointed out, positivism has a lot of issues. The best counter argument IMO being that it’s needlessly reductive. This is all covered pretty clearly in the link.

[ben_w]

> Unless AI becomes indistinguishable from human beings on a cellular level, yes, it’s entirely relevant and is the single most relevant thing.

I disagree.

Thought experiment: design a circuit which has as many inputs and outputs as a biological neurone, such that it always maps inputs to outputs in the same way (including the observation that this isn't a static map but one which changes over time), then connect them as neurons are in one of us.

While clearly nothing like an natural brain on a cellular level, I believe this is a sufficient similarity to be "the same parlour tricks".

The question then is: how close does the design actually need to be, while not losing anything of importance?

Perceptrons were only ever a toy model, so they may well be insufficient; but on the other hand, for a sense of scale, GPT-3 is about the complexity of a rodent brain rather than a human brain — and that suggests that humans could learn to be simultaneous experts in many dozens of fields and languages with a mere tenth of a percentage point of our brains if only we lived long enough to read the entire internet.

Which matters most — neurons, connective structure, learning environment, or something else — is, I think, still an open question. But even between all the differences, AI collectively are general purpose enough to at least suspect these things have got a lot of similarities where it matters.

[bondarchuk]

>A lot of people seem to think that if an AI can simulate the appearance of a human being, that makes them equivalent to one.

That is not what BoiledCabbage was saying. He was saying: "And what do you feel when we understand it well enough to realize we're the same type of parlor tricks?"

>This is a positivistic argument and as I pointed out, positivism has a lot of issues. The best counter argument IMO being that it’s needlessly reductive. This is all covered pretty clearly in the link.

You're not really making any specific claim about what is wrong with BoiledCabbage's speculation, and why this specific thing is wrong. "That's wrong because positivism, it's all in this 5k word wikipedia article!" just doesn't prove anything.

[keiferski]

If you haven’t done the reading, I can’t explain it to you in a HN comment. I’m not trying to be snarky about it, but I genuinely don’t know what else to tell you. This is a pretty foundational ideal in the philosophy of science.

What’s wrong with the speculation is that it’s a positivistic argument that is needlessly reductive. It’s reductive because it assumes that appearing human-like is equivalent to being human.

The fact that we can understand how “AI” works as a parlor trick yet appears human-like in no way implies that human beings are nothing more than the same parlor trick processes. To argue that it does is to make a positivistic argument that doesn't take in account a whole host of other things. As noted in the Criticism section of the article (which is hardly 5,000 words) there are many issues with this approach.

[__loam]

That statement also has no basis in neuroscience.

[jmopp]

Computers are already better than humans at a wide variety of tasks. Text generation just happens to now be one of those tasks. But if you look at the prompt -> output -> prompt feedback loop, it's clear that the human submitting the prompts is still doing all the thinking. We're not yet at the point where the AI can prompt itself and improve its output in a logical manner.

[ben_w]

> We're not yet at the point where the AI can prompt itself and improve its output in a logical manner.

Self-play is widely used to train game AI, and is the "A" in "GAN"; is there any point doing it on an LLM? Especially on the ones being sold as services where people get upset if they change over time?

[tessellated]

You really should take a look at Code Interpretor:

https://www.latent.space/p/code-interpreter#details

[emodendroket]

> And what do you feel when we make these parlor tricks more capable than us at the majority of tasks?

This seems like the logical fallacy of "begging the question" since it is far from apparent to me that they are "more capable than us at the majority of tasks."

[ben_w]

It's certainly difficult to enumerate all the things we humans actually do.

There's a lot of stuff we consider to be "common sense", sometimes those things are used to criticise AI and sometimes they're used to criticise other humans for not knowing them, but that is a category that we don't even think about until we notice the absence.

For the things not considered common sense, like playing chess (beats all humans) or speaking/reading foreign languages (more than I can name to a higher standard than my second language), to creating art (even if it regularly makes the common sense mistake of getting the number of fingers and limbs wrong it's still better and not just faster than most humans), to arithmetic (a Raspberry Pi Zero can do it faster than all humans combined), to symbolic maths, to flying planes…

A dev conference I was at recently had someone demonstrate how they hooked up their whatsapp voice calls to speech recognition, speech synthesis trained on their own voice, and an LLM, and the criticism of the people who got the AI replies was not "you're using an AI" (he had to actively demonstrate his use of AI to conversation partners who didn't believe him) but "you can't have listed to my message, you replied too quickly to have even played it all back."

[oldandtired]

It is impossible to enumerate all the things that we humans do. However, we can enumerate all the things that we create can do. Every system we create has its limitation due to the limitations that we create in them. All systems we create cannot exceed those limitations.

We make machines that are stronger, faster, and can have much finer motor control than we have as individual abilities. No machine we have created has the dexterity that we have.

Every computational system can be analysed in fine detail to determine the limits that we have built into them. It may take an enormous amount of time and effort to do so, but we can do it. No computational system that we have built is able to exceed the limited programming we place in it.

There is an enormous amount of hype that goes on about the current generation (and future generations) of these systems, but all of them are in the abilities that we have programmed into them. They are in all essentials completely stupid (in the worst possible way - non-sentient, non-intelligent).

Every logic error that we have made in building these systems is hidden in that code. One day, those errors will come back and bite us, but there is nothing intelligent or sentient in these systems. It is our errors, for which we are responsible, that will cause those problems.

We can use them as adjuncts to our sentience and intelligence - but all they are are tools, never anything more.

However, if we cede control to these systems, we are ceding control to something that is no better than fire (a good servant - a horrendous master). After forty years, I have seen far too often, hype by humans convince other humans to cede control to the systems that humans have made and the result has been various levels of chaos.

If anything, what we need to be careful of is how humans use these systems against other humans. This is the perennial problem that we face as we build new technology.

[ben_w]

Mostly I agree with you, but

> However, we can enumerate all the things that we create can do.

Not really, no. Even before AI, "Turing Complete" makes things extremely hard to enumerate; see Busy Beaver numbers for how small a system can be and still outside our ability to fully comprehend — needing to use up-arrow notation because exponentials aren't big enough is always good for a laugh.

[oldandtired]

With your example of "Turing Complete", we know what cannot be done and in this way, we have enumerated the things that can be done, if you like. You appreciate the humour required for the up-arrow notation - a very human quality.

You example of the Busy Beaver numbers, which was a recent interesting read, is a good example of what I was trying to point out. We have a definition and even if we cannot enumerate each number, we discuss and think about these in a rational way. At the moment, I am quite interested in Computer Algebra Systems (of which there are a variety) and I find it interesting just how limited these systems are and just how difficult it is to program into them the capabilities that humans use to solves various problems. The various discussions have been quite enlightening.

Mathematics is an interesting subject and I think shows up the intractability of ever getting that highly feared singularity.

All artificial computing systems are limited in ways we are not. Your "Turing Machine" example is one such case. The Halting Problem being a class example.

I think that far too often, we fail to recognise that what we create is not that great. We often stand in awe of the things we make without comprehending that these things are a very poor reflection of what is around us and what we ourselves are.

Every time some hype comes about these artificial stupidity systems, I look at my youngest granddaughter and see in her, capabilities that far exceed anything that we have created. Even my old buck of a goat demonstrates capabilities far, far in excess of anything we have created in all of our computational systems.

As I have said elsewhere here, we have to be careful that we do not cede control of our lives to systems that we think are more than they really are - systems that are limited, fragile and prone to failure.

[adastra22]

AI systems are vastly better than humans at a wide variety of tasks. Better at handwriting recognition, better at scheduling, better at playing games, better at speech recognition and transcription, etc.

[cypress66]

I am skeptical on many of those. Speech recognition is not even close to human level. Whisper, and whatever Google uses will make a lot of mistakes on audio files that are trivial to any native speaker.

[adastra22]

In actual tests it is beyond human level. Humans actually mishear about 1 in 20 words during transcription tests; whisper does better.

[emodendroket]

But we don’t solely rely on how well we hear since we have knowledge that allows us to correct for poor hearing based on what is being said rather than forging ahead with a nonsense transcription. Machine transcription is definitely faster and cheaper but the end product isn’t “better,” and anyone who has read it can attest to that.

[cypress66]

Well, those "actual tests" clearly don't reflect reality. This is obvious if you actually use whisper.

[oldandtired]

The question to ask is why?

The answer is that we have programmed these systems to do what we require. They cannot exceed but they fail becasue of errors that we have placed in these systems.

All of the tasks that you have mentioned have been programmed that way. It has taken human ingenuity to work out how to do this programming. The end result is a machine (non-sentient, non-intelligent) that is doing what we require.

If you look at game playing, a system was created to play Go and won and yet that same system fails to win against humans under many circumstances. The literature is there, yet not publicised for all the world to see. A result of keeping the hype in play.

If you look at speech recognition, these systems still fail when we humans work against them and yet, we humans still recognise what the machines fail at.

Just keep in mind that a tractor can move a greater amount of material than a human can, but it is still only a tool. A plane can travel faster and fly higher that a human can, but it is still only a tool.

We use these systems to augment our abilities and yet they are all limited in so many ways that we are not.

The upshot is that we can do amazing things with the things we create, but none of those things exist without us and all those things fail without us.

[ben_w]

> All of the tasks that you have mentioned have been programmed that way. It has taken human ingenuity to work out how to do this programming.

The successful Go AI were programmed to learn; we still can't program a decent Go AI with rules humans come up with.

> The literature is there

Do you have a link? Two Minute Papers just had a video about an AI systematic finding ways to confound other AI, but I thought we'd passed the point where the best Go AI could be so manipulated by humans…

[oldandtired]

Your example of the Go AI being programmed to learn is not all that accurate for what has been achieved here. I didn't keep the link for the discussion on the confounding of the Go AI system. What the discussion covered though was that there were simple Go configurations that the GO AI failed abysmally on when playing a human - it didn't learn here.

I have spent forty years dealing with all sorts of computer systems - designing, building, maintaining, repairing, redesigning and rebuilding. One thing I have learnt over that time is that none of the systems ever built has been error free in terms of the logic entailed within them. All to often, I have seen systems that were used to make decisions with and those using them assuming that the outputs were correct or reasonable. Yet on investigation, the logic entailed in them was completely rubbish.

We make assumptions and often we do not carefully check that those assumptions are actually real. I don't trust anything I write until I have gone over it with a fine tooth comb and then I will try to document all my assumptions and this usually shows up various logic errors or conditions that I didn't think about. I don't see this happening much out in the real world.

[tsunamifury]

He will go on saying it’s a trick. It’s a form of denial I’m seeing everywhere now when faced with something so genuinely terrifying or identity challenging you can’t process it.

[emodendroket]

Perhaps I can say you're motivated by an Oedipus complex and we can keep the chain going of ad hominem with a thin psychobabble veneer to make it appear serious.

[ibarearer]

I hate this sentiment. We might learn that human thought and reasoning are parlor tricks too once we understand them better. Anything we start to understand loses its mystery

[bentcorner]

"Any sufficiently advanced technology is indistinguishable from magic."

I know nothing about AI but it seems like we're approaching it from the other end - the human mind seems like magic and when we approximate it using technology it feels like we'll reach a moment of "that's all it is?" and refuse to believe we actually did it because we doubt ourselves.

Along the same lines, if achieving equal human rights for all humans were a trip to the corner store, the fight for AI rights is going to be like Mount Everest.

[Xcelerate]

> the fight for AI rights is going to be like Mount Everest.

I used to think this and worried that AI would never have rights (see, e.g., sibling comment to mine), but these days I tend to think the fight will be very brief and heavily in the favor of AI. It could be the first time in history that rights are achieved so quickly that there isn’t much of a struggle at all.

That said, I find it extremely depressing that the default human viewpoint is “it’s a machine and doesn’t deserve rights”. Hopefully AI will have a superior system of morality to ours as well.

[__loam]

It would certainly be neat if we approximated the mind using technology. It's a real shame we haven't done that. And no, computer programs don't have or deserve to have rights.

[Gigachad]

>That's what ultimately depresses me about AI. It's still just a parlor trick.

I find this to be quite comforting. It means we haven't completely uprooted all of society overnight and have time to stop and think about what this new technology can do for us and what it means for the future.

[nologic01]

AI is not a parlor trick.

AI is a branch of statistics. Nobody said that statistics must limit itself to quasi-linear models of numerical data. It was just a limitation of computational resources (initially "AI" was developed by human computers).

The trick is to get people not to associate the dictum "lies, damn lies and statistics" with "hallucinations, damn hallucinations and AI".

[sacado2]

AI is not only a branch of statistics. Symbolic AI has nothing to do with stats.

[Sparkyte]

AI he referred to was of that time.

[array-species]

statistics are based.

[prmoustache]

> , but they're still just that: parlor tricks

It isn't that much different than human behaviors.

People tend to repeat stuff they have seen done by our parents, sibling, friends, medias. Listen to people smalltalking in the streets, repeating the same things all over again every day. The easy success of marketing, politicians, dictators. The power of marketing and success of consumption society. Racism, bigotry, religions, addictions. All these are easily explained because people barely think. They just respond to internal and external stimulus with recipes they have been taught to follow without giving a second thought.

[JeremyNT]

> That's what ultimately depresses me about AI. It's still just a parlor trick. We haven't actually taught computers to think, to reason, to be innovative. Deep learning is definitely having its day, but I suppose this too will pass unless we can unlock certain ways to make AI reliable and responsible. Or... to just start understanding it in general.

Isn't this just semantics, and the expectations that go with them, really?

If the marketing language surrounding ML wasn't so hyperbolic and sci-fi-y ("artificial intelligence"? "neural network"? give me a break!) I think we all could agree that what we can achieve now is really interesting and impressive in its own right.

Even if these models aren't on a path to some kind of "thinking computer" as you envision it, their "parlor tricks" are doing things I would've relegated to the realm of sci-fi even a decade ago, much less 25 years ago.

[imiric]

The reason ML took off in the 2010s is because hardware finally became powerful enough to brute force classical solutions. If anything, this lends credence to the idea that these are more than just "parlor tricks", but that with sufficient hardware we can approximate the value of intelligence. We've certainly experienced the leaps in just the last few years when more hardware is thrown at the problem. Imagine what can be accomplished in the next decade or two based on this growth alone.

We don't necessarily have to replicate the way the human brain works, but as long as the machine is capable of performing quasi-cognitive tasks, there will be immense value (and disruption) to society.

[sacado2]

You seem to be conflating AI (in general) and strong AI. They are not the same thing at all. There have been industrial uses of AI techniques (I'm going by the definition from the 1956 Dartmouth workshop) for decades. And what's said in that video is a good example. We take recommendation modules for granted nowadays. They are applied AI.

Disappointing for sure, if you're still waiting for a sentient robot, but they do something we thought was limited to humans back in the day: going to a bookstore, and having the owner tell you "hey, I know you enjoy mystery novels taking place in England, I might have something new for you".

[worksonmine]

> That's what ultimately depresses me about AI. It's still just a parlor trick. We haven't actually taught computers to think, to reason, to be innovative.

If you think about it we've gone the other way. We're teaching/conditioning humans to think less and react more. This has only gotten worse the last few years and I don't see any shift coming soon. Humanity unfortunately seems just as simple as the algorithm, use the right inputs, in the right context and you can make most of us act just like you want.

[corethree]

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.

[RandomLensman]

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.

[oldandtired]

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.

[IanCal]

> 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.

[worksonmine]

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.

[IanCal]

> . 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.

[worksonmine]

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.

[corethree]

> 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.

[oldandtired]

> 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.

[corethree]

>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.

[oldandtired]

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.

[IanCal]

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.

[mythhabit]

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.

[corethree]

> 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.

[mythhabit]

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.

[corethree]

>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.

[IanCal]

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...

[usgroup]

Not really sure how you can consider ChatGPT a parlour trick. It has been around a relatively short time but for me its replaced a large proportion of my Google searches already. I do not see how its utility can be denied whether it reasons or not (whatever that means).

[ben_w]

In fairness, Page Rank and indexing are also… well, perhaps too big for a parlour, but they're (very good) tricks.

Is ChatGPT playing a trick on us by mimicking the sentience of the humans whose writings it ingested, or is the trick that by doing so it began to actually think like us and so simulates a conscious mind within?

I lean towards the former; but we don't know what sentience even is yet, so we can't prove it.

[KirillPanov]

This is why they've called it AI winter the past three times.

It's a season.

Like the seasons, the cycle repeats.

[array-species]

This time it's nuclear winter.

Examples: Graphics User Interface. The iPhone seated mobile compute as a permanent fixture, it and Android bringing internet and computing to billions of humans for the first time. Not just the wealthy industrials. Or IBM DB2 for SQL. Or Ford's Model T. Or the Gutenberg. None of these were the first first. Maybe even on the n-th iteration 2 decades after coming out of DARPA or global university research, something is just ready for commercialized prime time.

Computing was solved by Lady Ada and Babbage. It's all electrical engineering, software, fabrication, productization, mfg, displays, sensors etc. after that.

Semiconductor was a big deal in making it happen. But that's almost besides the point of the theory of compute if it can be solved in other novel ways using alternative material science.

[tsunamifury]

What a tired and lame take.

100m people used this latest iteration. It’s hardly a winter.

[worksonmine]

If there's anything the last few years has taught me is that hype is rarely any indication of common sense. I'm always surprised what reaches success and what doesn't. Truly revolutionary ideas are ignored and not understood while stupid but polished ideas are booming.

One example of that is the crypto space. So many actual good for humanity implications, but the "killer app" that made the news was fucking NFTs. I'm trying really hard not to come to the conclusion that humans are just mindless zombies but it's getting harder every year.

Once we reach a billion DAU you can be sure it will just be "Original Memes Tailored Just For YOU"™ instead of figuring out the logistics for solving world hunger. Mark my words.

[__loam]

The crash is gonna be wild when people realize all these companies are blowing smoke. We did get Google out of the last crash though I guess.

[KirillPanov]

What a tired and lame retort.

[echelon]

You say all that. Meanwhile teenagers are finding love on character.ai.

[flatline]

There is a famous Dijkstra quote, “The question of whether a computer can think is no more interesting than the question of whether a submarine can swim.”

Do the intrinsic properties of the system really matter at the end of the day if it performs as well as we do at some task? Heck they’ve been doing many things better for decades, but those are the types of tasks we take it for granted that a machine should be able to do. Solve differential equations. Play chess. But now computers are doing “human” tasks competently. Writing creative fiction. Generating graphical art.

We don’t have a good working definition or metric for intelligence. Surely it is not a monolithic property. Animals exhibit many traits we associate with intelligence. Some of the stuff GPT 3+ generates sounds pretty intelligent. It is the type of things an intelligence may have produced, because it was trained to do just that. If we look at intelligence as a cluster of traits, or behaviors, I think we are surrounded by intelligence - human, artificial, or otherwise. Doesn’t have to be an AGI to fall in that category. It doesn’t even have to be particularly impressive.

[vczf]

I wrote about my definition of intelligence earlier this month: https://tildes.net/~comp/194n/language_is_a_poor_heuristic_f...

    I have a definition of intelligence. [...]

    Intelligence is prediction.
    
    In the case of intelligent living processes ranging from single celled organisms to complex multicellular life, intelligence arises from the need to predict the future to survive and reproduce. More intelligent organisms build more elaborate models of the world using better developed senses in order to do so.
    
    Humans model the world primarily with language, which allows us to share our models with each other, across both space and time! Without language, it is extraordinarily more difficult to communicate complex abstract thoughts. As a side effect of our high level of intelligence, our wetware is capable of modeling things outside of language, such as mathematics. [...]
    
    In general, I think we need to stop equating intelligence with consciousness, agency, moral value, and living things. These are entirely different concepts, and, as a species, we are blinded by our egotistical identity of being smarter than the other animals.

According to my definition, intelligence is actually all around us. We are blind to it because we focus only on how intelligence manifests in humans (defined by by our specific social organization and biological senses), and then use that as a benchmark to judge every other thing in the world.

A less socially-charged definition of intelligence would make it easier to compare intelligence across living and non-living processes, though it would not be "popular science" useful for ranking humans.

[worksonmine]

I don't agree with your definition at all.

2 people want to kill each other. The one taking the first step is the intelligent one because according to your definition he was better at predicting an outcome than his opponent.

The real world is more complex than that and there are multiple options where both survive, or letting your opponent live and killing yourself because his life is more beneficial to humanity and so on.

Any organism can survive, but for most (including us) that implies a selfish outlook but the most intelligent people I know or heard of never even consider their own ego.

[vczf]

Maybe I wasn't clear enough. The definition of intelligence I propose is wholly distinct from human prosocial values like cooperation.

This makes it useful for judging these properties across living and non-living intelligent processes, such as bacteria, ants, plants, dogs, LLMs, etc. It is not a useful definition for judging the value or "goodness" of human beings within society.

I'm arguing that intelligence (as prediction) is simpler than we often presume, not a mystery at all, and a basic building block of complex life. We happen to have a lot of it.

[worksonmine]

I'm not coming from a moral standpoint either, just giving an example of how correct prediction may lead to consequences we would call retarded. Predicting resources being scarce may lead to over-consumption which leads to the extinction of everything. You could argue an intelligent organism would predict that and adapt but we're still trying ourselves.

There are plants that slow their own growth to share resources if their neighbor is of the same species, and vice-versa if it's a different species. That could be called intelligence in a sense, but it's not as simple as just prediction there's a social aspect and a long-term goal. But is it even conscious and aware of what it's doing or is it just the traits favored by evolution. Is agency part of your definition of prediction or is it enough to just react to the surroundings?

Intelligence is much more complex than a single trait. Being good at prediction is just that, being good at prediction.

[oldandtired]

Your definition of intelligence has been around for millennia and is part of the pantheism concept.

[emodendroket]

Sure, it's neat that it can do those things... still I don't think that I'm exactly ready to toss aside books written by humans in favor of AI-generated alternatives.

[jack_pp]

Writers have started using AI-generated ideas to help them write books.

Same with code. Sure it might not write your product code from start to finish with no help but it will speed up your dev speed significantly for certain tasks. Just because we haven't reached singularity doesn't mean what we have now is useless and putting it down as a "parlor trick" as grandparent said seems to me very unwise.

[emodendroket]

Ad copy has served a similar purpose but nobody would claim ad copy has (or could) supplant creative writing because of that.

[fttx_]

Ad copy is (a form of) creative writing.

[emodendroket]

OK. Literary writing.