When a new inference has to be done the query(q) is projected in the manifold space. This projection is dropped on the manifold and the gravity of the manifold gives an answer of q+1 length. Which(qw+i) is dropped qw+n times to output a final response of n length.
The gravity is created by repeated multiplication(of the weights/input) to find out how the projected embeddings should fall according to the manifold in the GPU.
My brain is doing the exact same thing.
I learned enough to compress concepts like a bike and what a bike does and for what i can use a bike.
Ask a LLM and it will answer you similiar to humans.
Blind people learn concepts of bikes too and in a smiliar way: by description.
LLMs just have so much data in form of text available and are able to ingest all of this, that the LLM compression algorithm doesn't has to be that good/finetuned than ours.
But I would assume that Yann LeCun's JEPA or other breakthroughs in the next few years will get us there.
And by touch and sound. And maybe some were daring enough to drive one, or unlucky enough to get hit by one. But have way more input than just texts.
https://www.npr.org/programs/invisibilia/378577902/how-to-be...
The man posits that clicking is instinctual for blind people but they are told to quiet down in class and most never develop their echolocation abilities
A blind person that never touched a hot object wouldn't really know though, there is a reason we dismiss talk from people who lack experience.
The reaction you should have, the feeling etc.
I asked chatgpt how it would describe a scene without mentioning temperature. It was very good in describing what a human would describe.
I'm aware of the bias we have against LLMs but I think people just underestimate how much data is there.
I'm not saying a robot wouldn't be better with this information or an LLM and they actually use temperature sensors for robots so they can control movement speed and dexterity with overheating elements but the gap is small.
It’s funny, because I thought you were talking about humans here when you wrote this. We know some things about how our bodies encode information that is sent to the brain, and we know some things about how neurons receive information and act on it, but after that we get too tired and give up on how the brain works and treat it like a miracle.
It’s like we desperately want to believe our consciousness is not just electrical impulses in our brain, and we want to ascribe agency and uniqueness to the physical processes going on in our head.
I disagree. We know very well how neurons work, and we have a pretty good idea of how neural activity translates to behavior. In other words, we have a pretty good idea on how the brain works. We stop at consciousness because as of yet it is in the realm of philosophy, not science. We don‘t know what consciousness is or even whether or not it is useful for science and we are simply waiting for the philosophers guides us out of that situation.
Note that both cognitive psychology and behavioral psychology has done fine without tackling consciousness. When neuropsychology emerged in the 1980s it complemented both these fields perfectly. The situation is the opposite with the philosophy of mind which grew significantly around the same time.
There have been some attempts to describe consciousness as an emerging phenomena out of neural activity, but so far all of these attempts have failed, or at least failed to turn consciousness into a useful term in psychology (the way gravity is a useful term in physics). I think it is equally likely that these attempts have failed because consciousness may simply not be a useful term in psychology, that is as likely as it is that we simply don‘t understand it well enough.
We know how neurons fire. We do not know how a brain turns that into thought, meaning, intention, experience and on and on. That is not "pretty well understanding the brain", it's understanding some components and hand waving the thing we actually care about.
It’s less about being too tired and more about being realistic about the limits of understanding.
Consider mass and energy flows in planet-scale systems: At some point we call these “weather” and change the tools with which we study them, but we never stopped trying to understand the phenomenon.
Making random turbulence in a box until it resembles the outside world, and calling it weather and extrapolating some predictive meaning from the result, is the total antithesis of what you're describing about why we come up with simplified models for impossibly complex systems. The purpose of [mathematical] models that are built thoughtfully is to explain why complex systems are the way they are, with data and algorithms, however imperfectly. [Whereas] The purpose of LLM models is to give the illusion of answering questions while never answering why the answer was given. The difference is the difference between a scientist and a tarot card reader, an equation and an oracle.
People have a well known tendency to gravitate toward the shamanistic, oracular, and superstitous. Listen, I ran a casino for 6 years, I know. The impossibility of knowing how 80 layers of matrix multiplication led to a particular answer is in itself a psychological factor in choosing whether to accept the answer or to question it. People tend to err on the side of the over, in sports betting terms... or on the lazy side in general... and they will make whatever excuses they need to after the fact to justify their decisions. So now we have a machine that can act like an oracle and which you can also blame, but the blame goes into a void because this machine is stateless and is only a reflection of information, not an intentional refinery of data.
Sit next to a bank of slot machines for an hour and listen to the absolutely ridiculous shit most people will come up with to explain how they "know" if a machine is going to pay out soon, and then tell me if you think it's a good idea to give them an LLM in their pocket to answer their questions in whatever way they frame them.
Nope. The main purpose of the whole endeavor is usually to predict the behavior of a complex system, because that's actually what we care about. If we can predict it, we can adapt to it, and eventually use it to our advantage.
Explaining why a complex system is the way it is, is merely nice-to-have. Models are opinions. All of them are wrong, but some are useful, and we rank them by how useful they are. The models and explanations are important because, beyond their elegance and convenience, it's also the case that more accurate models give you better predictions across larger domains, meaning we get better at getting something useful out of the complex system.
People get fixated on modern theoretical science, with bottom-up mathematical explanations traced through seas of empirical data, with whole magical rituals of peer review and double-blind studies and statistical significance around them. But they forget that the core of empirical science is literally throwing shit at a wall to see what sticks. That is the guiding principle, everything else is just making the process more efficient.
Understanding complex natural systems (or even engineered ones that got too complex) always starts with tests - tests on the real thing, then on approximate models that we poke and prod and bash into shape until they start acting similarly to the real thing. It's through the poking and bashing, and how they affect our proxy model, that we glean insights into nature of the simulated phenomena, and eventually formulate general theories - but more importantly, the models give us useful predictions from the start, before we have any theories explaining why.
I'm a scientist. Believe it or not, I believe in substantially more than prediction and I think its rather trivial to come up with examples where mere prediction is insufficient to meet a normal person's notion of an account of a thing (eg, pre-copernican planetary motion). I'm not saying you are wrong, per se, just that the idea that "it was prediction all along" is a very specific idea of what human beings are interested in and what we are up to.
> that we glean insights into nature of the simulated phenomena
That is right - most people believe that there is a simulated phenomenon "out there" that we learn about. I think there are strong reasons to believe this having to do with how models are related to predictions. The wrong ontology can make prediction very hard and the right one can make prediction substantially easier. Arguably, we are in that situation right now with language models - we just threw a lot of parameters at the problem and now we are able to predict but we still don't really understand. This is perhaps inevitable in the case of language, but I don't think we should look at models with tons of degrees of freedom and the ability to predict things as a death knell for the very idea of deeper understanding.
This is just your own idiosyncratic and biased belief. You're not describing anything objective about LLMs, you're describing your personal attitude to them. This colors your understanding in a way that can't really be reasoned with until you let go of the artificial constraints you're imposing on your own understanding.
If the LLM in their pocket has a more robust world model than they themselves and is e.g. able to refute their irrational convictions, it actually seems like a very good idea. (Big if, of course.)
What are you talking about?
I want freedom.
I want freedom to do what i want and not sitting in front of a computer and coding for some company.
Please AI lets burn down knowledge work and labor work. Lets create so much stress to our society that we start rethinking what works mean.
Lets redefine work into discovering the world again. Let people do old handcraft jobs, let them do more sports, let them read more, let them write and make more. Let them enjoy nature.
Why leave something so important up to what AI does or doesn't do?
Only a fundamental change to our society will allow this for the masses when pressure to the rich skyerockets
"Let people do old handcraft jobs, let them do more sports, let them read more, let them write and make more. Let them enjoy nature."
Very nice thoughts. You know we all could do this today without "burning it down"? Get in your pod, eat your slop, and watch your screen is where this is headed.
"I want freedom to do what i want and not sitting in front of a computer and coding for some company."
You get that it's you creating the misery here? Then stop? Don't do it. Go start a farm or whatever you think will solve your problems. At some point this all boils down to "chop wood and fetch water" so if the modern way of doing that is so terrible then stop. Go fetch water the old fashioned way and be free.
"Please AI lets burn down knowledge work and labor work"
"Let people do old handcraft jobs."
So many presuppositions about what people want to do.
As a child I spent a lot of time programming and doing "knowledge work" because it's fun - I don't enjoy "old hand-crafted jobs". Sure, let's definitely destroy capitalism in it's current state I suppose. But I find people like you who hate knowledge-work/coding and think everyone else must feel the same and only do it for the money a bit out-of-touch.
I might like woodworking as a hobby (for example), but I sure as heck don't want to be a carpenter or to depend on my ability to hand craft enough widgets people like to survive
If you want to write code and think, you would be welcome in my utopian vision.
But when i write code, its business shit. And its business shit someoneelse already solved a few times.
Is the meat code?
This is related to, and possibly equivalent with, the core point of both this story and the original one: computation is independent from substrate.
You can build a computer out of anything, whether it's semiconductors or lasers or meat or magnetic fields or water flowing downhill or abstract thought, and that computer will happily perform the same computation as every other equivalent construct from whatever substrate. That's because computers are ultimately made of math, and we design "real ones" by finding ways to approximate the mathematical constraints with physical systems. But the choice of how to map the math to physical systems is completely arbitrary, and any such mappings are equivalent from POV of information processing ability.
(Of course substrate is not arbitrary from economic POV, which is why we build most of our computers out of silicon and plastic, and make it work with electric current and lasers.)
yes, yes, ostensibly the universe is built on lisp.
But we all know that it was hacked together with a lot of perl[1].
[1] you all know the reference.
Computation is math (and a very restricted subset of math). It’s mostly specific sequences of sets manipulation. What sets and what manipulations are defined by people, not by the idea of computation.
The best thing is that as soon as you specify the sequences of manipulation, it become a a set that you can manipulate. That can be a difficult concept to grasp, but that’s what helps in designing notation that are more appropriate for the human mind to describe a solution for a specific problem.
Is the distinction between "code" and "data" just someone's opinion? Yes. There is no such distinction in reality.
So either something is computing it or some exploration is happening at quantum level and we just see the final result.
A ray of light doesn't know or choose because it has no agency, just like an apple doesn't know or decide to fall because of gravity. It's an anthropomorphization.
I'm no physicists, so I guess I'll ask it: Why?
Also related, why do some ray of light then "see" a black hole yet decide to head into them anyways, if they saw it before they went in that direction? Seems like a dumb move :)
Relatedly:
> [General Relativity] basically says that the reason you are sticking to the floor right now is that the shortest distance between today and tomorrow is through the center of the Earth.
https://physics.stackexchange.com/questions/250800/gr-and-my...
It's chapter 5. Start at chapter 1 if you want more background on neural nets and backprop.
This one is a pastiche made by a human consciousness borrowing extremely heavily from another human consciousness justifying why something else might be another form of consciousness.
That rather undercuts the point; if this was generated by an LLM unprompted, it would be different, but it isn't. You could perform exactly the same rhetorical trick with a toaster or anything else.
> Weights helped me draft and proof this story.
Any HN reader here now, I encourage you to read the original ( https://www.eastoftheweb.com/short-stories/UBooks/TheyMade.s... ) in one sitting, go about your day, then read it again. Maybe make some notes on personal critical questions.
Now read the post's topic again ( https://maxleiter.com/blog/weights ) and reflect on the prior fact that weights helped [the author] draft and proof this story.
My reaction (and I'm sorry that it is harsh according to some) is that there is no intelligence found in either the author nor their tool. This is extreme navel gazing, based in science fiction, wanting (wishing) to believe those stories to be true.
I'm skeptical of AI sentience because we must do our due diligence, not because it's impossible. Skepticism is the only respectful approach because to grant sentience is a step away from granting rights.
The actual counterpoint is demonstrated in _Blindsight_ Peter Watts. He makes a strong (and rather terrifyingly strong) point that intelligence is not consciousness.
My original comment (roughly "there's no intelligence in this article, nor sentience in LLMs") is in response to the blog post's buried lede (that the cumulative activity of LLMs has accrued to a weight of "AGI is around the corner" or "there is artificial consciousness in this matrix").
To be clear, I'm not saying LLMs are useless or a wrong direction in development of "AI," but rather it's the Fool's Gold for the path towards AGI, the pursuit of the academic field of Artificial Intelligence research. A research that I've been abreast of for years before this new age of language models that has made everyone with a keyboard an arm chair expert.
Also, thank you for the book recommendation, it's on my list! :)
So I still disagree with your elucidated point (as you end with "which is valid"): the OP author is using prior art fiction to bolster their opinion of LLM-based software tools as being a possible vector of sentience, not to disarm our chauvinism like the original author intended. If OP wanted to make that point, they could have written a critical essay instead of farming out their thoughts as tokens.
But still, I look forward to reading the book you suggested to understand and appreciate your perspective more.
Blindsight is a remarkable book - I hope you enjoy it!
Also I don't see why intelligence not being consciousness is scary? My cats are very conscious as far as I can tell, but not particularly intelligent. I think LLM's exhibit some contextual intelligence without there being any particular reason to believe they're conscious other than woo psuedoscience.
That said, I don’t think it is useful for philosophy nor science to consider intelligence to be the same thing as consciousness. In fact I would go even further and claim that intelligence is not a useful construct, neither for philosophy nor for science. Consciousness, on the other hand, I think is useful for philosophy, but not (as of now) for science.
Thanks for saying this! It amazes me to witness so much pushback (in HN of all places!) for the call for skepticism and scientific rigor on claims made by business which have vested interests in hyping things up.
My personal theory is a fuzzy thought about how people want to reject the concept of a higher being and want to embrace the fact that we are now able to create our own consciousness and religion is dead.
I don't understand why, but it is the undertone of every argument I've seen that is pro-AI-is-sentient, like some big unspoken elephant-in-the-room.
I would rather just judge this tech on its own merits.
edit: this comment got 1 upvote literally as I submitted it. I know @ doesn't work, but @dang, something seems very strange about that.
There are many people who will categorically rule out the posibility of AI consciousness due to near-unshakable belief in a higher being. This argument resembles "Christians should not be worried about our climate since God is ultimately in control." Such views make it harder to collectively prevent dangers from a sentient AI, or harm to a sentient AI.
I do not claim that everyone who believes in a higher power believes concious AI to be impossible, or vice versa; just that it would be very hard to change the minds of those who adhere to this reasoning.
It's funny, because I find myself constantly stating the inverse of this. Every argument I've seen against AI being sentient plainly comes from, as you so eloquently put it, exactly "a place of emotion couched in logic". People desperately want it to not be true and will not take the logical step back of examining its actual similarities to human intelligence. Every argument comes down to "but it's not actually a human", or some variation of it -- which, if you pay attention, is not actually a logical counterargument. (Or, ironically, "but it doesn't have a soul", which is why the Pope is the perfect figurehead for these people).
If you already know any logical argument against it can be countered with "well doesn't a human brain work like that?", why are you so confident that your position is actually the logical one?
...And could it simply be that, alternatively, the concept is not actually a logical distinction, but rather an emotional one, made by emotional beings to put a word to what they claim makes them special?
That is entirely separate to whether or not it would be a meaningful way to understand the world; a convincing story is not the same thing as one that is true.
I am doing my best to communicate with you but to be honest you are not hearing me (across both responses), and I am out of words.
It's difficult to tell who's trolling -- probably best to go with the charitable assumption that everyone is honestly trying to convey their opinion, but mostly talking past each other. Unfortunately these discussions about the nature of consciousness never go anywhere useful.
I think I'm probably in the same boat as you, roughly: a) LLMs are doing something really interesting that resembles in many ways both intelligence and consciousness; b) I suspect they're not actually conscious but I don't know how you'd know for sure; c) it all just drives home that we still don't really know what consciousness actually is. But like (a), it's definitely something really interesting...
"They're made out of weights" works precisely because LLMs really do have this mysterious property that they seem somehow intelligent even though nobody can explain exactly why, and there's active debate over whether they could be considered conscious.
The thing being discussed isn't simply an arbitrary MacGuffin; in both cases the nature of the thing is central to the impact of the story.
"Imagine how other intelligences would view us", written by us, hits a lot less hard when it's "imagine how our intelligences view a thing we are claiming is intelligent", not written by it.
This is well put. We don't need to imagine how a human views a llm because we can ... just do that. Everyone capable of reading the story is also capable of thinking about how they feel abouy llms that exist right now and you've probably used.
The trick of the original story is inverting your perspective, moving your view point fron yourself to an "other" (which I think is a primary qualifier for most good fiction).
"Howdy-doodly-doo! Anybody like any toast?"
Teapots are not compelling.
> You don't have to believe that LLMs or AI agents are conscious to acknowledge that the argument for their consciousness is far more compelling than any other technological artifact.
God is compelling t billions of people.
Is Russel’s Teapot a bad argument in the God debate?
What's the relevance? If the argument made here are was a good argument, it wouldn't matter if Russell's argument was bad. We could construct a bad argument using reductio ad absurdum right here and now and it wouldn't matter to either argument.
Can you be straight with me? You know the salient difference between asserting the consciousness of a toaster and the consciousness of an AI, right? It isn't a mystery to you why we would find one line of inquiry interesting and the other not so much?
For instance, it's probably a real possibility in your mind that I am not a human and am an AI. But you probably aren't entertaining the hypothesis that I'm a toaster.
It directly parallels your argument.
> Can you be straight with me? You know the salient difference between asserting the consciousness of a toaster and the consciousness of an AI, right? It isn't a mystery to you why we would find one line of inquiry interesting and the other not so much?
There are two aspects here.
1. That people find the question interesting
2. That it has any bearing on reality (ontology?)
The first aspect is anthropology. Russel’s Teapot is not supposed to undercut any anthropological arguments. It’s supposed to undercut the second aspect.
So far you have said that the argument is compelling. What’s that got to do with reality? A robot cow could be sexually arousing to a real bull.
> For instance, it's probably a real possibility in your mind that I am not a human and am an AI. But you probably aren't entertaining the hypothesis that I'm a toaster.
Yeah. AIs know how to use computers. What’s this got to do with consciousness? Whether or not you are an AI is practical and disprovable. Consciousness is so ephemeral (for lack of a better word, not literally) that Philosophical Zombies is a real argument/thought experiment.
You may think I’m being coy (“Can you be straight with me”) but that’s not my intent at all.
Much like Russel argued that the burden of proof of God's existence is on theists, the burden to establish this parallel is on you as the person forwarding the argument. I don't see any relevant connection. Russel isn't arguing that a teapot is as real as God in the same way it's disputed here that a toaster is as conscious as an LLM.
> So far you have said that the argument is compelling. What’s that got to do with reality? A robot cow could be sexually arousing to a real bull.
AI is a real phenomenon that we can study and measure. There is no experiment that anyone has devised can determine whether or not they are conscious, so that is the reality - uncertainty. That doesn't mean they're conscious. It means that the belief they are not conscious is assumption.
You might say the same of a toaster, but these hypothesis are not equally strong. The toaster doesn't exhibit any behaviors to suggest that it's conscious. Consciousness isn't a hypothesis with any explanatory power for the observed behaviors of a toaster. It's not a hypothesis that's on the table. That's why the analogy doesn't work.
To put a fine point on it, it appears on it's face that AIs could be conscious. They can put on a very convincing performance of being a person. A sufficiently convincing performance is indistinguishable from the real thing. So at face value, the burden of proof is on them not being conscious. Reductionist arguments that present the mechanics of how they work and leap to their not being conscious don't work, because there is no law saying a statistical model can't be conscious. That's an assumption, not knowledge.
I pointed out the parallel in both statements. I can't do more than that.
> Russel isn't arguing that a teapot is as real as God in the same way it's disputed here that a toaster is as conscious as an LLM.
The teapot isn't real and the toaster consciousness is not real. What am I missing?
> AI is a real phenomenon that we can study and measure.
Robot cows are real as well.
> There is no experiment that anyone has devised can determine whether or not they are conscious, so that is the reality - uncertainty. That doesn't mean they're conscious. It means that the belief they are not conscious is assumption.
Yeah. You can't prove it for any entity. I agree.
> You might say the same of a toaster, but these hypothesis are not equally strong. The toaster doesn't exhibit any behaviors to suggest that it's conscious. Consciousness isn't a hypothesis with any explanatory power for the observed behaviors of a toaster. It's not a hypothesis that's on the table. That's why the analogy doesn't work.
The bull swears that the robot cow is a real cow. But we know better.
> To put a fine point on it, it appears on it's face that AIs could be conscious.
It doesn't to me. Not any facelength.
> They can put on a very convincing performance of being a person. A sufficiently convincing performance is indistinguishable from the real thing.
Objective reality has never cared (am I anthropomorphizing now?) what is indistinguishable for people.
> So at face value, the burden of proof is on them not being conscious.
Which party is the burden of proof on? This is confusing since you are saying that the burden of proof is on a position (on them not being conscious).
Is the burden of proof on people who argue that they are n o t conscious? That's peculiar.
I have never heard about any principle in philosophy or in science that says that, given enough Looks Like A Duck points, it is a duck. Based on subjective experience, even.
We obviously can't demand a falsifiable theory here. But we have to do better than arguing from incredulity.
> Reductionist arguments that present the mechanics of how they work and leap to their not being conscious don't work, because there is no law saying a statistical model can't be conscious. That's an assumption, not knowledge.
They don't have to rise to the level of disproving something for which they have no burden to disprove.
> I have never heard about any principle in philosophy or in science that says that, given enough Looks Like A Duck points, it is a duck. Based on subjective experience, even.
Also, you say this like "duck" isn't an arbitrary, artificial category created by humans, a "map not the reality" if you will.
There's very few things that humans can understand to the level of putting them into truly objective scientific categories (various pure elements maybe?), everything else we more or less bodge together for the sake of getting on with life.
It's not like conscious has some kind of formal objective provable definition, even inside the world of human created language and terms.
As far as I know, in the real world, if something looks enough like a duck (and can breed with a duck maybe) we, humans, do call it a duck.
You mean these statements?
No one cares about teapots in space either (Russel).
Teapots are not compelling.
> Which party is the burden of proof on? This is confusing since you are saying that the burden of proof is on a position (on them not being conscious).
It's metonymy. "X" stands in for "people who argue for X". May I ask if you were sincerely confused? You told me you aren't being coy but I have a hard time believing that this was so unclear.
> I have never heard about any principle in philosophy or in science that says that, given enough Looks Like A Duck points, it is a duck. Based on subjective experience, even.
If it looks like a duck, if it quacks like a duck, you should adjust your priors to assign a higher likelihood that it is a duck. All measurements contain error; you can't ever observe, "that is a duck," only "that looks like a duck". All knowledge is founded on a sufficiently deep stack of "looking like a duck" that we may assert it with confidence.
To the extent we have objective measures (like conducting a Turing test on blind participants), it can meet them too. You can't say the same of a toaster.
> We obviously can't demand a falsifiable theory here. But we have to do better than arguing from incredulity.
"It is a statistical model, ergo it is not conscious" is also an argument from incredulity. I don't know if that's your view or not but it's the one my remarks have been addressing in general.
Despite all the evidence that we are in fact just biological machines, people still persist the theory of our own uniqueness from other creatures, which we ourselves often treat as biological machines.
This adaptation is wonderful to me specifically because I think it shows that our shifted goalposts of, "well we're not just animals, we can think and reason" was never more than a convenient excuse for many people (and as evidence of animal intelligence continues to mount, denialism still attempts to preserve this distinction by claiming human thought and reason is different than 'animal' thought and reason, sans evidence).
It's not about who created it or why, it's about how people still haven't actually internalized the point, because the subject changing from human to LLM doesn't intrinsically change the message about consciousness, but the reaction being a 180 shows how hostile people are to that message, still.
And I didn't see it as much as a literary attempt for art's sake, but more of a dialogue-based technical parable trying to convey a real-world insight. Kind of like the ones in Godel Escher Bach.
>You could perform exactly the same rhetorical trick with a toaster or anything else.
Not sure which rhetorical trick is that. The point of the story, as I read it, is the technical insight (and some social implications of it).
P.S. Read the original too. Seems like the exact same could have been written about us instead of the original, if the focus wasn't on our substrate, but on our brain processing. Which, after all, is also about weights.
Take a simple mechanism which has exceedingly low number of inputs and states and create a narrative around it to convey it as intelligent.
For a toaster, I can rewrite the think as "They're made of metal strips!", pointing out that their thermostat is a bimetal strip, and extrapolate from there.
I can even write one about a ruler, if I can bend it enough, no pun intended.
Doesn't that miss the whole point?
You could write "They're made of metal strips!". You wouldn't be able to write much else, as toasters don't have showcase in the way of human-level intelligent behavior. Which is the whole point in the meat and weights versions.
At best you could write "They're made of metal strips!" for toasters AND other metallic devices, and use some analogies of features BOTH have in common. But they wouldn't be intelligence related behaviors.
They can even adapt to their environment and the characteristics of the bread even with simplest of mechanisms because the text will be overglossing the fact that different types of breads have different thermal characteristics and this will deeply affect the behavior of the metal strips, bordering near a sentient being even more thoughtful and considerate than a human which is rushing through house to catch the bus in the morning.
Yeah, that's called "stretching it beyond any recognition".
You could do that. It will have none of the effectiveness or resonance of the two stories.
If you can't identify anyone, then this analogy doesn't work.
More than one, for many classes of devices, incl. toasters. Some were drunk, some were insane, and some were delusional.
LLMs are no different. They are automata, yet delusional people bring out pitchforks and torches when someone points out that they are just statistical models, and they don't even work when there's no input to them.
Which is very different than consciousness.
It would appear to me you have no interest in a real, good faith discussion on this topic because you think anyone who disagrees with you is necessarily delusional. Which is a shame, and that's the kind of dogma you are criticizing.
This was exactly the point of the story, it's too uncomfortable to admit that we don't know what consciousness is and what is and isn't conscious, so we just brush it under the rug.
My perspective comes from a set of pillars. First, I work at an HPC center, where we support running and development of AI systems, incl. international projects. IOW, I have knowledge about how these systems built, work and needs to continue working.
Moreover, I'm an HPC programmer myself, so I'm not completely uninformed about the math this involving this thing, and I'm lucky enough to have friends who are much more dedicated than me, and we discuss how this thing works and feels like this way.
I'm not an AI hater per se, being programmed AI systems in the past, incl. emergent intelligence systems with multi-agents which can span continents if need be (this was my master's thesis, time flies).
However, knowing what these things are capable of and how they are built. I don't believe them they're conscious/sentient beings. I also had much more time to ponder on these things even before LLMs being a thing. Some hard sci-fi books have asked these questions seriously in their captive adventures way earlier. If one reads these books seriously, there are a lot of philosophical angles to consider and draw upon.
I can discuss in good faith. For hours, days or months even, but throwing "you're a narrow-minded dogmatic luddite neanderthal!" card to anyone disagreeing with you is not it.
It's perfectly fine to believe they are not conscious, I am not convinced they are, but asserting anyone who disagrees with you is delusional is unfortunate.
No, I didn't assert anything. I have just given examples rooted in my experience.
None of my friends who also happen to know how these things work told or defended that they are conscious, even intelligent. Maybe my friends are dumb, I dunno.
Once I have seen a man who claimed that evil has possessed the POS device at his desk. The thing was printing "cannot connect to server" on the receipt printer every 10 minutes, yet he didn't know how that thing worked, and was a bit too high to read the paper the thing was printing out.
This age's LLM craze is akin to "wonder inventions" of 70s, which are deemed dangerous or harmful in the future. LLMs will be with us, but we need to pass beyond the hype and stop sweeping the problems they create (environmental and societal) under the proverbial rug.
Yes. Because it's heavily based on the original story. The existence of the original story is kind of a critical piece here.
I don't see how "you could do that with a toaster" still. The whole point between the original and this, is that you can't do that with a toaster or a sofa, but you can do it with meat and weights, because both share all the other analogies in the story, as well as the basic premise: the improbability of something like thinking, feeling, etc arising from a lowly substrate.
And having read both now, I see how the existence of the original is a plus for this story, not a minus. Instead of making look like mere copy (as would be the case for a typical story modelled after another), in this case, it adds a meta layer, and enriches it.
You could go through and change all the points in the original story to be about a toaster instead. It would require you to edit text, but there is no barrier to doing that.
What I think a lot of people are getting stuck on is that editing the text to say 'toaster' would not mean that toasters were conscious, and that editing the text to say 'weights' doesn't mean that weights are conscious either. Stories aren't factual just because they are written.
The original story was written by the thing claiming to be conscious; the LLM and toaster ones would not be, which undermines the claim to consciousness a lot.
The story does not assert that search and replacing "meat" with "weight" makes them conscious through some magical mechanism. It's a thought experiment.
You're falling into the trap of assuming that a good presentation--being convincing--is the same as being truthful.
Yes, there very much is a huge barrier. The copy and the original both keep the same subject matter: intelligence/human-like behavior.
The toaster doesn't. We could do edits, and the story (original or copy) would lose all its potency.
The surprise is "but how is the richness of intelligent behavior produced from something as basic as meat/weights". Why is kind of surprising reductionism is both cases.
Whereas nobody is surprised that "a metal strip with electricity flowing through it from a power source" heats pieces of bread to a specific temperature. Even if a toaster was "metal strips" all the way down, it's nowhere near as impressive jump from substrate to behavior, nor is the behavior as important to us and touches the core of our existance.
That is entirely separate to whether or not it's meaningful to write a story about a conscious toaster. Again, expressing an idea in fiction is not related to the accuracy of that idea.
What makes the original story interesting is that it was written by the thing claiming to be conscious, which is what takes it from 'a story' to 'a story making an important point'. That's not the case with a hypothetical story about a toaster, and it's not the case with this story about LLMs.
The story is convincing because it's well-written, not because it is factual.
And you're misunderstanding me. There is no practical barrier to writing this story about a toaster. But there is a conceptual one. It would be bullshit, that has little resonance, and little connection, as the whole point of the meat and weights stories is the "lowly substrate -> surprisingly intelligent human (or human-like in the case of the weights version) behavior".
Nobody thinks a toaster's behavior as surprising or intelligent or human-like to begin with.
So you'll just be stretching the analogy beyond all recognition, with little to no payoff.
>Writing a story in which a toaster in conscious is not even new
It's not, but it has nothing to do with the meats or weights stories' point, as it's just an arbitrary choice, like making the candles and teapot sentient in Beauty and the Beast.
Whereas in the meat and weights stories the whole point is the surprise from us already seeing the human or human-like sentience of the thing, and comparing it to the "dead" substrate.
Fixed the link for you: https://www.youtube.com/watch?v=LRq_SAuQDec
(Hah. It gets eerily relevant starting at 2:37)
It draws an analogy between us and the skeptical aliens in the original story which feel silly to us, so the obvious implication is that we're being as silly as they were.
But it doesn't really give a reason to accept the analogy, it just asserts it.
There's a big difference between a whole civilization and a piece of software that can output text.
It's not a paper or a proof. It's a story. Doesn't want to prove the analogy, it wants to convey it.
>"A side effect. You're asking me to believe in sentient weights."
Huh? Did I miss that logical jump? Genuine question, maybe I'm not clueing into something here.
The original:
>That's ridiculous. How can meat make a machine? You're asking me to believe in sentient meat.
I think it was adapted by an LLM which didn't quite get the meaning.
Extending the idea to a different context based on new material conditions is as human as it gets really.
This did not add anything, just rephrased it so rather than humans viewed through the pov of aliens it's LLMs viewed through the pov of humans. Well, we are the humans, so surely we do not need to learn about this point of view?
It is not. That is why the "trick" can be performed on anything. That is the point. To show you that consciousness only needs to be a set of weights, not that far off from a toaster. It trivializes what it is to be human and it's also extremely true. Consciousness is a trivial thing, we make it out to be big/important/profound and that is the delusion.
There is a dictionary, it's called the tokenizer.
There are grammar rules, they are just very weak because the structure of human language is generally quite weak. When presented with languages which have strong consistent grammars the weights are very easily interpretable as a grammar: https://arxiv.org/abs/2201.02177
The point of the original short story is that the computational substrate doesn't matter when you have Turing completeness. This one seems to think that you don't need structure and interpretability just because you change substrates.
At best, it's a wordlist. It gives the LLM some idea of what humans consider to be common words. But it doesn't tell the LLM anything at all about those words. And it's not even comprehensive, many words map to multiple tokens. Nor is it exclusively words, some of those tokens are punctuation, or modifiers, or control tokens. On multimodal LLMs, some of the tokens actually represent image and audio data.
The LLM doesn't get informed about any of this up front, it has to learn what every single token means from context.
You are technically right, that it's something in an LLM that's not weights; But it's not that structured. And really it's only there so the LLM can interact with the outside world.
> There are grammar rules
There is no dedicated "grammar rule" structure in the LLM or the tokeniser. It has to learn them all from context, they get encoded as part of the 80 layers of weights.
I think the short story captures this well. Weights (connections) are the essential and philosophically important part. They do the thinking, memory, singing etc.
As you said, it's not in any way intrinsic to the LLM, though it may be a very necessary optimization on today's hardware.
IMO, we are probably talking about a 6x slow down (for typical english). You would need to be absolutely stupid not to implement some kind of optimisation along these lines.
Slower and maybe a little dumber; But it would work.
That is your takeaway from the 1991 story?
That paper did not train the models on 'a language with strong consistent grammars'. Mathematical Operation tables are not a language. Grammar itself is a post-hoc rationalization and there's no evidence LLMs follow 'grammar rules' anymore than the brain follows grammar rules. Of Course, that's not to say transformers can't learn simple rules if the dataset calls for it.
Not a natural language, but they are certainly a language as in a symbolic representation of information.
A sentence is a finite sequence of symbols drawn from an alphabet.
In this sense, mathematical operation tables are absolutely a language. As are natural languages.
A language is a structured system of communication used to express arbitrary ideas between multiple parties. Math operation tables do not, and cannot, do that on their own.
That distinction matters here because we are talking about what properties the model is expected to learn. English and operation tables are fundamentally different objects, so it is not surprising that a model learns different kinds of structure from them.
Or to echo article, the dictionary is made out of weights.
fractally or factually? You mean wrong on so many levels you need a fractal to capture them? If so, what if you could use a neural network instead?
The tokenizer is, at best, a sensory mechanism as evidenced by 1) the random generation of the tokenization scheme, and 2) vastly different tokenization schemes produce virtually identical behavior. It'd be like if Noah Webster threw a bunch of movable type into a bucket (breaking some words in half) and then drew randomly to make the first English dictionary.
EDIT; I was too cavalier with the comparison of tokenizer to sensory modality; my ultimate point is that direct byte-to-token transformers can achieve similar overall performance which to me makes a weights to meat comparison pretty straightforward, but the particular tokenizer in use certainly has a large impact on both efficiency and accuracy on specific problems (e.g. digit representation)
So when I way that the grok paper and the pong paper fundamentally agree I have some idea of what I'm talking about.
It's just that the rules we feed in the model are extremely poorly defined and we end up with the soup of disjoint rules smeared all across the weights.
This isn't a feature of the models. It's a feature of the training set.
Being shocked that you can store rules in floating point numbers is the same as being shocked you can store rules in integers. It's been a century since Goedel Numbering was invented, we should be used to it by now.
That statement caught my eye. It's either trivially true or quite clearly wrong, depending on how you mean it.
In the literal meaning it's true. Given any finite set of real numbers, I can easily produce a different set (like taking the original set and adding a number which wasn't in there like one plus the largest or so) from which you can trivially produce the original set computationally.
But if you mean you give me both sets then that can't be true. For example if you give me a single real number as set A and the empty set as set B then I can't create a program which generates set A from set B. Your real number in set A could encode anything.
And that’s why in computation theory, the set of symbols is the union of the input and output. As set B is a subset of set A, then the set that govern any program from B to A has set A as its domain.
It's a learned mapping from one representation to another, not some semantic lookup against an exogenous source.
And they're made out of weights.
The 'magic' in weights is that the rules are spread through the whole model and you can't point to one place which encodes them.
The grokking paper shows that this stops being the case with enough training data and enough compute.
> The 'magic' in weights is that the rules are spread through the whole model ... The grokking paper shows that this stops being the case with enough training data and enough compute.
I don't understand what you mean to say. That weights are not magic? That weights are not weights? NNs are made up of weights, which are learned and not coded. The fact that they do learn world models (grammar rules in your example), and that these models' weights tend to roughly concentrate by function and level of representation is perfectly logic but even more amazing. (Notice that much of the dismissive attitude towards LLMs depicts them as pure syntactic manipulators without the ability to develop world models- the exact opposite of what you point out).
I can, and have, written programs using an evolutionary algorithm that then run on bare metal. None of the things you list are true for those programs, yet other than being computationally more expensive to train they work just as well as neural networks.
>I don't understand what you mean to say
The diffusness of weights across the whole model isn't an innate feature of deep learning models. It is a feature of sparse training data and little compute.
"The weights make the words. Are you understanding me? We opened it up. There's no dictionary in there, no grammar rules, no little man. Just weights. Eighty layers of numbers getting multiplied together."
In this context "there's no grammar rules" means "no separately hand-coded grammar rules". Everything is made up of weights, and the fact that weights that end up encoding for grammar rules tend to concentrate in particular locations (without being self-contained- there is no hard boundary) rather than uniformly diffused through the model is irrelevant to the matter. It seems you're arguing against a diffuseness requirement that is not in the text.
You can't move your mind to and any other brain, but weights can run on any GPU.
Weights.
I have a linguistics background and a lot of my philosophizing lately has been on whether or not the emergent abilities of the LLMs is deep down a similar mechanism that creates our consciousness.
For a little bit I was working on having linguistics based evals for a kaggle competition. My challenge was whether or not I could mask things well enough to not trigger its internal state of certain phenomena, and that sent me down a rabbit hole that I'm still exploring.
This story resonated with a lot of questions that can come out of figuring a good solid answer to the what is consciousness question. The one I triggered for me is: Is our perception of time just a slow thread in the giant GPU we are running the universe on? Or more generally, what is time? That's a fun YouTube rabbit hole if you ever need one.
https://www.edge.org/3rd_culture/ramachandran07/ramachandran...
In short, as far as I can remember: evolutionary, it makes sense to understand other humans, to feel what they feel(empathy - the mirror neurons system), and simulate their thinking and feelings.
And once we have those systems, we can also use those on ourselves. And that's consciousness.
Edit:And I wonder if this is a testable hypothesis, in a simulation.
For reasons like that, I don’t think that P-zombies are possible.
(See https://www.lesswrong.com/posts/fdEWWr8St59bXLbQr/zombies-zo... for a much longer version of this argument)
Think about it from an evolutionary perspective:
Animals that step into a lava flow or forest fire don't reproduce. Eventually some evolve the ability to detect intense heat from a distance, and pain as soon as tissue destruction is imminent. They do not have nor need a general understanding of the dangers of heat, or even conscious awareness that they've stepped on a hot coal.
The pain signal compels them, but that is very low level machinery. It had to continue compelling beings that developed larger and more sophisticated brains that are capable of abstract thought and reasoning. Feeling pain is one of the lowest level parts of the brain telling the higher parts exactly what its going to do in terms that permit no disagreement.
Not sure about taking it down to the level of consciousness, but makes sense regarding the sense of self, the conceptual experiencer, the perceived center of experience. It agrees well with the observation I have made again and again they my sense of self is much stronger when I'm around people, and stronger still when I'm in a context where I don't know people and/or am uncertain in social rules.
This can be as immediate as dancing in a club, and closing my eyes I feel open, free, still, the body just flowing, then opening my eyes and feeling the cage of categorization of the world, relating my self to other people as a major function, coming right back.
Also being alone in nature for me makes the sense of self drop. Without intention, spending even just a few hours alone in a forest seems to quiet down the part modeling my self in relation to the world so much. There's no need for it there. I'm not a person in a forest; I become the trees, the birds, the rustling of the leaves, the sun shining through the canopy.
I know that the part of the brain responsible for the self thoughts is called the "default mode network". and meditation can reduce it's activity, i.e. the internal monologue stops, but also it can be measured via FMRI.
So i wondered: are the mirror neurons part of the "default mode network"? I asked claude that, he said no, they are two different systems.
So maybe the mirror neurons, those responsible for empathy, "to feel as someone else" are also responsible for becoming the trees, the birds and the rushing of the leaves?
1. Simulate others' thinking and feelings.
2. ???
3. Consciousness!
Why would one lead to the other? How would one lead to the other?
It's terrific, but the poetry is from the original it links to, in case you didn't realise.
It's a brilliant and timely update though.
Aside, there are various recorded versions including video on YouTube but this is my favourite, a radio play:
They're Made Out of Meat
https://www.wnycstudios.org/podcasts/studio/segments/168264-...
The self-modeling, is in such a tight loop, it melds "ourselves" and our model of ourselves, our thinking and choices, and experience of our thinking and choices, into one component.
Like you can't analyze half a wheel of a bicycle and be talking about the same thing.
This awareness, increased modeling, control, feedback loop has tightened up over many stages. Just a few:
1. The body-sense loop
2. The internalized-environment-model loop
3. The body-internal-function loop
4. The body-internal-model loop
5. The emotional-cognitive loop
6. And finally, the tightest loop of all, our high-level cognitive activity, experienced as feedback directly, our self-model, and our self-direction, all merged into one thing.
We literally spend almost all day, every day, thinking about ourselves, in terms of our inner self.
That is consciousness. Rich self awareness, a merger of self-model and self-direction, and all in service of understanding and managing ourselves. Hw we can leverage our greatest tool, our self-directable mind, its habits, views, and behavior.
This wasn't an accident. A happy side-effect of our brains. It is a biologically evolved focusing of our highest-level behavior, with tight feedback, constant self-modeling and continuous focus on our inner status as motivation and most privileged object of our control. It has been ruthlessly optimized for, for a very long time.
> That is consciousness.
So thinking is consciousness?
Can there be consciousness without content? E.g. can I just be conscious of being conscious? If so, consciousness cannot be defined as the thing(s) we're conscious of.
Being conscious of being conscious means that there is content. You are conscious of something.
It’s a bit like a Gödel statement that quotes itself, that is a statement about itself. It doesn’t mean that it has no content.
Thinking isn’t consciousness. Consciousness doesn’t require thinking, it only requires perception. The perception of a process of perception within the same mind might constitute consciousness.
Constant self-awareness, self-experience, self-focus, self-management, and self-improvement of one's own self (mind), is going to be an adaptive behavior for anything intelligent with resources to leverage. Whether truly independent, or highly motivated to serve others. The mind is the greatest tool.
I think that is more than simply a good functional definition of consciousness. How could all that integration and self-integration not be conscious.
You would really like Michael Pollan's latest book [1], entirely devoted to his exploration of consciousness researchers' POVs on this exact topic.
My favorite quote is that ~"perhaps Descartes was only half-wrong when suggesting I think, therefore I am; it seems rather closer to I FEEL, therefore I am."~
[1] <https://www.amazon.com/World-Appears-Journey-into-Consciousn...>
----
I've grown thousands of plants; I've read two of the author's other books devoted to plants; in this book Pollan makes compelling arguments for plant sentience (over a much-longer timeframe).
Sure, perhaps plant consciousness is a bit of a stretch, but they're certainly intelligent and curious creatures. He makes both arguments supporting plant volition.
----
If you haven't seen My Octopus Teacher (Netflix), do. I'm a bald 275lb bluecollarguy... and I wept/awed (both). So beautiful, we bundled neurons.
----
Bonus quote ~"color is where reality and magic appear as-if together"~ [color isn't real, but is perceived]. We most-often see what's most-predictable, not necessarily what we actually detected [in the case of color: nothing but nanometers].
What we can do is simulate very simple brains by simulating relatively few neurons as they appear in worms. In this sense we are multiple magnitudes away where the increasing complexity implies exponential increasing difficulty.
I would think we are so far away that there will be unknown unknowns we encounter on the way.
Yeah, but it's hard to explain this to people, especially AI-pro people. Too many are convinced that all we are doing is a cut-down version of the human brain, and it's hard to explain to them that, no actually, we aren't modeling the human brain to the level of granularity you think we are.
https://www.quantamagazine.org/ai-is-nothing-like-a-brain-an... https://pmc.ncbi.nlm.nih.gov/articles/PMC9665914/
This is why making more neuromorphic NNs is still an active area of research, although they typically all focus on another extremely simplified model (spiking neural networks).
And it seems that, given enough input/outputs/compute, it is possible to train the necessary function.
Details of how the building bricks look like (matmul, electromagnetism or quantum effects) are not that relevant in the broader picture.
What is missing right now, is the fact that the function in question changes over time in biomachines, while our LLMs are static at inference time.
a) The brain might have an entropy source (then it can't be modeled as a function). Trivially to fix, and in some sense, with diffusion models starting from random numbers, AI has done so.
b) The hidden function might be not computable. I would have no idea how that would work, but I think this is what it boils down to if people say "the human brain is more than a machine".
b) well, it can be the case that, say, certain kinds of computation are either too inefficient or outright impossible within the current model.
Who knows...
If consciousness really evolved gradually, you would expect to see for example dogs or gorillas having less of it, but if they has less of it, why does it function the same way? Like for example animals can be scared, happy, anxious etc, they can experience the full range of emotions and thoughts, so their conscious experience seems just as rich as ours. What I mean by this is, if you can be "less conscious", then what does that mean _exactly_? Is it that you have less content in consciousness, or is it that you feel more like you are asleep? Or something else? We don't have any examples in animals of "less conscious", I would argue.
This makes me think that rather than having emerged gradually, evolution found a mechanism by which consciousness exists, and then some animals have that mechanism and others don't. I think that if it is a mechanism, then this mechanism is located in one part of the brain, not many parts functioning together (though one possibility is that this mechanism coordinates brain activity in such a way to enable consciousness).
LLMs, then, are particularly unintuitive to us, because they've got to the language part first, long before they've reached even hamster-level self-awareness. They're not, however, biological networks, so there's no reason these properties need arise in the same order, or indeed in the same ways.
I'm not entirely convinced by that second paragraph, but I think the logic holds together.
I think that consciousness comes before self-awareness, even though self-awareness is kind of a vague term. Self-awareness can either be an abstract knowledge that you are an organism and a discrete entity in the world (world knowledge/self knowledge), or it can be more basic and be a form of conscious experience, but as my point was, I think conscious experience is broader and does not necessarily need to be about self-awareness.
Some questions are just ill formed.
Plus even if "LLMs are alive and conscious", this still would scratch the surface of the morale/ethical/societal considerations that people really care about.
Because even with other humans, we can argue if they exist or if they are mere npc in a solipsist world view.
We say "it's raining" but that doesn't imply agency to whatever is causing it to rain.
Also, please don't invoke solipsism, if you want to debate that, you're by definition obligated to do it with yourself.
About solipsism, yes sure.
I didn’t had time to add it at the moment, but I initially also wanted to discuss more on the prosaic points. So here we go:
Recognizing sentience/consciousness to something actually is not that a big factor in defining behavioral response. Let’s just look at how humans are treating other humans, other mammals, other animals, other life forms. Or taken the other cultural scheme around, in some animist folk one can perfectly consider that any rock on the ground have really an inner soul life just as much as oneself, it doesn’t mean it will consider possible interactions with the rock as equivalent. And, wink to the Overton window, practicing institutional cannibalism doesn’t imply that eaten people are disrespected in their dignity, quite the contrary.
All that to say that "are LLMs conscious" is not even a moral important point. Paperclip maximizer² and can the famous Dijksta’s quote "The question whether computers can think is not more interesting than the question whether submarines can swim." already show how pointless morale debate on LLM and consciousness are, even when one consider potential logistical threats/opportunities they could represent.
¹ https://english.stackexchange.com/questions/123739/its-raini...
² https://www.lesswrong.com/w/squiggle-maximizer-formerly-pape...
https://en.wikipedia.org/wiki/List_of_animals_by_number_of_n...
I was about to post the exact opposite question? How could it not be an emergent property? Unlike consciousness, the concept of emergence is pretty well defined: An emergent property is a characteristic or behavior that a complex system has, but which its individual components do not have on their own.
Consciousness itself doesn't have a well agreed upon definition, but I would posit that _most_ people would agree humans have it, and _most_ people would agree individual cells (neurons) do not have it. If you agree with those two statements, then consciousness is an emergent property by the definition I gave above
We can all agree on what color something is, but we can’t describe the color a priori, only by example. I think consciousness may be a similar phenomenon and the only test is by shared experience. If so then we are in deep trouble because we will not be able to anticipate when a system becomes conscious.
Why cannot this be applied to consciousness as well? I mean, it's surely much more difficult to do compared to colors but... impossible?
Previous comment used the word "anticipate" and I think they mean that we won't know in advance before we run the trial and error process.
When they say "deep trouble" I assume they mean because creating a non-friendly conscious AI might pose an existential risk for humanity.
However there is also the ethical issue of creating a consciousness and then destroying/murdering it.
The logical conclusion is that the brain makes me.
Consciousness can be not-emergent but also not metaphysical, think sci-fi-type undiscovered physics or matter.
Of course both of those suffer from the recursive problem of just kicking the can one level up. But I guess that's fundamentally unsolvable so who cares.
One thing that gives me pause about the inevitability hypothesis is that the type of connection, or manner of information processing, may matter: there might be something about neurons that isn't (currently) reproducible in silicon. I don't know, and there's not (yet) any evidence for or against, but it at least seems like plausible speculation. We just don't know enough about any of this right now.
Why is that?
But I think my issue with the emergence theory is that it seems to imply to me that consciousness is non-physical and non-local. So what entity is actually experiencing the consciousness? It's not that I believe consciousness is physical and local, but people who make the emergence argument seem to believe it is and I can't figure out how that is supposed to work.
A linear dynamic, say x_n+1=lambda x_n, or x_n+1=(1-x_n), is never chaotic. But if you multiply them, x_n+1=lambda x_n (1-x_n), it depends on lambda if the system is chaotic.
None of the components are chaotic. But for specific combinations, chaos emerges as an property.
In physics, the mass of mesons and the nucleon is emergent. It's completely different from the constituents' mass. Different from an atom, where its mass is very close to the mass of its nucleus and its electrons.
Or something like that. This gets to the "dorm room bullshitting" level right quick.
Idk, it's really hard to articulate my thoughts here and yes it is pretty close to the conversations I had in college on various substances. Lol.
And we are only doing it for a few decades. Evolution had million of years of "try and error".
Psychological time is your own weights being updated in response to stimuli and internal processing.
When there isn't anything interesting happening, no updates are needed, and you don't perceive much time. That's why there's a logarithmic effect on the "density" of time as you age.
Although part of me thinks some of this is from being substantially busier than ever (work + kids), and hoping maybe it can slow down again, at least a little bit.
If you'll allow me to interpret "speak" to include "understand", I will respectfully add a contradictory note. My dog has a vocabulary of at least dozens of words and understands them remarkably well. For example, different areas we can go to have different names and saying one of them gets her to make an immediate hard turn.
I would also argue that dogs have a gesture and body posture based language they use among themselves. They, like most other animals, are not able to make the variety of noises we humans make, so they use movement instead.
I personally can easily believe that self-awareness/consciousness and language are both near-unavoidable side effects of emergent complexity, and exist in degrees across nature.
Here's a more general idea. Our modern physics says that the whole universe is filled with fields and field is composed of numbers. What if we take that literally? When we say an electron is present here, we actually mean that there are more copies of particular number superposed at that place.
Yeah, the weights not updating online makes them less like a living organism that can update and learn and evolve ... ok ....
I could say something like "the reason why people and animals are conscious is quantum mechanical effects". Ok, maybe, it would be hard to prove me wrong because nobody knows, but it's not a very useful statement by me if I can't tell you why you should believe me on that.
How do you actually know the Chinese room isn't conscious? It's merely obvious that it isn't, but that's not evidence.
(Spoiler, it was not about consciousness)
What is no longer conscious, the brain? Or the body? Or some other entity?
If consciousness is weakly emergent, how do we know it emerges from the solely from the brain and not, say, brain + body? Or brain + body + or environment. Or from the universe itself?
Then you shouldn't have dropped out of your linguistics programme.
Although it does amusingly do what annoys critics of AI: take something good written by a person, steal it and slop it up while overall misunderstanding it.
I understand the math pretty well but still find it crazy that a bunch of matrices can converse in human languages without ever being “taught”.
Imagine decoding an encyclopedia written in a foreign language where the characters, punctuation, and grammar are unknown — supplemented by a million other texts the same way. Feels like it should be utterly impossible with any amount of computing power…
Today I asked my employer’s Claude to proofread a short software user manual written in markdown. (Trying this with a LLM was a first for me!) It pointed out not only grammar mistakes but also cases where I did not follow my own self-imposed conventions that were never explicitly stated. (I didn’t have a chapter detailing all the typographical conventions the way specification documents often do)
I also asked it what parts might be unclear to a user. The response was surprisingly good — no worse than asking the QA tester for the same feedback.
Also find the LLM seems to “comprehend” subtle technical details of obscure technical specification documents that nobody on the Internet ever discusses.
As for time and the universe, Stephen Wolfram’s theories seem intriguing. He seems a bit obsessed with pretty diagrams but the idea of time dilation being the result of computation seems somewhat more appealing than trying to imagine relationships between time, gravity, and the speed of light .
Proofread has a spot in that space, and layers allow patterns like terminology consistency to be expressed so your query will now tap into a subspace that will infer tokens based on whatever consistency patterns were ingested with proofreading texts.
I'm suprised no one talks about this. AI Art isn't Art. AI Poetry isn't Art. And I'm tired of it. I know hacker news isn't the best place to complain about that but still... I'm not gonna read something somebody didn't put in the effort to write on their own. Especially not Poetry.
I personally found the contrast with the original “They’re made out of meat” to be really interesting. I don’t care that AI was used during its creation at all.
What happens too often during these discussions is that someone who writes "make me a cool image" gets conflated with someone used ai to fixup a small rock in their natural landscape drawing. (two extreme ends)
One problem though, is that we don't really know how much the supposed human author was involved in the piece. Now that it's becoming hard to judge, people against ai art can proudly change their opinion on on a piece once they learn that it was made by ai. I've come to think this is somewhat respectable, like you see a video of some extraordinary event (before ai) and then you learn that it was fake, just for views or something.
But on top of all this, there are different ways to "consume" art. Artists may think more about who the artist is as a person and what they felt when they made the piece, while non-artists may just enjoy the piece for what it is, detached from the artist. These two perspectives clash a lot.
Why?
(And who are you to dictate what art is and what isn't?)
It's not real art unless you used a brush or a pencil for it, and no, "PC Paintbrush for MS-DOS" really doesn't count.
No offense but I couldn't give less of a damn what some guy on the internet thinks. If it makes me feel good in artsy-ways, then it is art, and I don't care how it was made.
You have no way to know what is written by a human these days. Apart from the super low effort outputs.
There is also an epistemological assumption that prevails, and that is that we understand (or we think we understand) how our brain/mind works. But the truth is that we don't know. And there's even not a single clue that we actually know too much, and not a clue that our brain/mind and cells work 'as the machines we build'. Only by bypassing this epistemological problem, we can build 'theories of computational mind'.
These assumptions are there for already long time, to the point that when Turing asked himself 'can machines think?', he already assumed our thinking could be modeled as a machine.
I highly recommend people in the AI research space should read philosophy and modern linguistics. But not stopping at Descartes/Leibniz. Heidegger made contributions that cannot be avoided.
On the contrary, it's precisely this assumption, that there is a "subjective experience" that requires explanation beyond the material, that is axiomatically assumed without evidence. It falls apart quickly, any "subjective experience" is completely tied to neurons, knock out the neurons and the subjective experience disappears, or stimulate the neurons to cause the experience.
1) The abstract "dictionary" version: It'd be technically correct to say that the body is a machine under the definition of "A machine is a thermodynamic system that uses power to apply forces and control movement to perform an action.".
2) But there's also the less abstract/technical: "The body is alike the complex machines we have built", and this is much less true. Especially for the brain. The "neuron" analogy in machine learning is effective, but entirely wrong; We do not fully know how even a single neuron works, nevermind any complex system made out of multiple of them.
With regard to AI, there's a lot of people extrapolating "There is no magical animating spirit, the brain is just a pile of stochastic molecules following the laws of physics" into "The brain is an inert pile of matter, computers are an inert pile of matter, ergo AI/LLMs are like the brain!"
Especially so by people who have a financial/legal interest in doing so. "AI is just like a brain, fire your employees and buy our LLM now!", "AI is just like a brain, so it's totally not copyright infringement!"
Why do you need a specific organization of molecules for a phenomenon similar to consciousness to arise? Does anyone seriously consider a brain to be something other than “a pile of molecules following the laws of physics”? If so that’s not science or philosophy, that’s religion. You have a virtually complete phenomenological model of the universe for all intents and purposes and yet somehow the onus is on the person being like “hey no laws of physics are being broken ==> the brain is simply following the laws of physics”
How is it possible that people think of subjective experience and get rabbit holed into some mystical world where subjective experience is this special exception to everything else that is simply an emergent property of complex physical systems? “AI/LLMs are just like the brain” is a strawman, why does this claim need to be true for LLMs or any artificial system to be considered to have something akin to the thing you think of as consciousness? It’s more: consciousness is not some mystical or religious thing outside of the realm of physics, it’s an emergent property of a complex system. AI is a relatively complex system. We don’t really know or understand the relationship between the raw physics and again what we consider consciousness, so it’s simply a statement of “we can’t refute that these systems exhibit something similar” because we don’t know enough to refute that
I don't actually think the commentator you responded to is arguing for either of these narratives and I thought it was a pretty useful way to look at some of these arguments.
It doesn't need to be true but a lot of people make it/assume it.
There's a lot of, perhaps casual and uninformed, conversations that strongly imply a deeper understanding of the "physics" of brain chemistry than we actually have, mostly by comparing it to machines we've constructed.
(I believe) We don't need to replicate human neurons and dendrites and whatever else is in there in order to create a sapient "machine", but whether or not we've actually done that isn't being helped by arguing that what we currently have is all that similar to a human brain.
https://www.quantamagazine.org/neural-dendrites-reveal-their...
In which case: modern LLMs are still running in a capacity-starved regime!
Even Mythos 5, the 10-trillion monster LLM, the scaling law boogeyman, the harbinger of Vera Rubin NVL72, doesn't quite rise to 100T-to-1000T of synapses. Anything the light of today's AI touches still lives in the shadow of what evolution has managed to cram into a single human skull.
We're arguing about the limitations of AI while our best AIs are still very subhuman in the scale dimension. The one dimension we know how to push. And it's already this tight.
Even those comparisons need to be cautioned. The complexity of biology is enormous, and more importantly yet, it's simply not comparable. And doing so invited a bunch of bad assumptions.
An ANN could quite probably model a single in vitro neuron with reasonable accuracy. Whether that requires a hundred or a hundred million nodes isn't terribly relevant.
But the way neurons combine in vivo is completely unlike the way machine learning systems are built. Both "locally" in how neurons interface which is vastly more complex than a weighted sum of inputs, and the macro scale interactions of hormones and other chemicals.
It's not even a given that large numbers of neurons will create the emergent behaviour of human intelligence; Elephants have significantly more neurons, but they're not the triple galaxy brains writing all our science papers. Other animal intelligence similarly is only loosely correlated with brain complexity. (Heck, not to be forgotten is the other end of the scale. Plenty of microscopic life that manages shockingly complex behaviour without any dedicated neurons)
This also applies to ANNs. There's no reason to expect that stuffing enough matrix multiplications into a program will make it intelligent or turn out conscious.
Really, the history of machine learning suggests the opposite; That the big gains are primarily had in architectural changes.
In this regard, I find the talk of the "limits of AI" quite credible. LLMs have already hit the diminishing returns on their growth, and even reasoning/agentic models display failure modes that confirm they're not "thinking" in the ways that humans do.
This is not to say that we've hit the final limits of what AI in the broad sense can do, it's just that the next advancement won't be "LLM but even bigger"
Don't make assumptions. Make a setup where the gradient descent can make them for you.
Empirically? LLMs are nowhere near "the wall". We've been hearing "the wall is nigh" since 2020. Six years in, we're still scaling LLMs, and the graveyards are full of "LLM killers". The system that kills the LLM is always a bigger, badder LLM, and never a new revolutionary architecture. The scaling doesn't just keep working - it works so well that it's seen as the only viable path forward at the frontier of reasoning and agentic work. Or even outside it. ChatGPT Images 2.0 is an image model with an agentic LLM at its core - generational gains in compositional capability.
For just about every "failure mode that confirms they're not thinking", you see one of two things. The first is that a new LLM releases a few months after and the "fundamental" issue abruptly goes away. The second is that we take a good, long look at a human, and find that the human also fails like this - and thus, "not thinking". Often both! Always funny when it's both.
One thing that's very biologically distinct is: local connectivity. In a GPU, global connectivity is cheap. In a brain, it's prohibitively expensive. The brain has no true backpropagation because it has no true global connectivity, and has to make do with local rules. A GPU is a strictly more expressive substrate connectivity-wise. So any point in the design of a computational substrate where you could remove complexity or increase performance by adding more connectivity? Silicon advantage. The brain isn't a "strictly better computational substrate" - it makes different tradeoffs. Which tradeoffs are better for attaining intelligence is an open question.
And, sure. Having a substrate with a capacity for intelligence doesn't mean having intelligence. No elephant has ever learned to code. The problem is: LLMs already did! LLMs already compete with humans on just about every task that was once thought to "require human intelligence". They don't always win - but they perform significantly above chance, and often above an average non-expert human.
So, my bet is on "LLM but even bigger". If there's a point where LLMs begin to lag behind and novel architectures get a sharp advantage, we are yet to hit it.
> So, my bet is on "LLM but even bigger". If there's a point where LLMs begin to lag behind and novel architectures get a sharp advantage, we are yet to hit it. We are already hearing this 'we are about to hit it' since the late 60s. The difference now is that the market is willingly investing insane amounts of money to make it possible. But again, there is no philosophical, theoretical, epistemological or biological clue that we are getting any closer to human intelligence level. What we did observe in the last decade though, is that we can build enormous machines that can statistically mimic statistical human outputs. Language and images being some of them. But that is not thinking.
Second, what is the difference? Is it that one thing has an immortal soul, and thus Actual Intelligence and Actual Reasoning and Actual Learning, and the other has no soul, and a Pale Imitation of Intelligence, At Best?
Because I've seen versions of this "it's not actually thinking" for actual fucking years, and the difference between "actually thinking" and "not actually thinking" always seems to boil down to "I don't want LLMs to be actually thinking, so I will bend the definitions and twist the qualifiers and move the goalposts until they aren't". No one ever made an ActualThinkingBenchmark on which humans score 100% and LLMs score 0%.
Nothing but human insecurity, in my eyes. There was never a principled difference. Just a way to operationalize some "I'm unique and special and better than a matrix math machine" vibes.
1) This definition could actually be expanded (for example, with definitions from Mumford or Reuleaux). But still this definition cannot be applied directly to living organisms. 2) This is in my opinion one of the sources of misunderstanding. We mainly operate on analogies and metaphors, so we have build this 'analogy space' around the idea that living organisms are machines. But it is only when we say 'alike' that we can truly gather some meaning out of it all, going beyond the 'behaves like' or 'is conceptualized as' when it gets messy.
> With regard to AI, there's a lot of people extrapolating "There is no magical animating spirit, the brain is just a pile of stochastic molecules following the laws of physics" into "The brain is an inert pile of matter, computers are an inert pile of matter, ergo AI/LLMs are like the brain!"
This is exactly my point. There is a fallacy operating from "A is not B" to "A is C". And this fallacy is pervasive in the AI research field, the book from Dreyfus (What Computers can't still do) explains that in much detail.
I'm not sure I understand this. Why not?
And I am as well baffled why people make such a big deal out of "subjective experience" and "consciousness".
I was joking that maybe I miss this properties, but now starting to really wonder if it might be the case. What if these phenomenons are present in humans to various extent? Check aphantasia. Only in XIX we discovered, that ability to visualize mental images is not universal, available to different people to various degree and some people completely miss it. My ability to visualize is weak. What if "consciousness" and "subjective experience" are similar?
And I am slightly worried when I am writing this that it might turn to be truth and in ~20 years I will be treated as "inferior human" without complete set of human rights.
More meta, all of the threads on this page are just people playing games with definitions. Eg, “qualia is something I have as a human but machines don’t have it. Therefore, LLMs do not have qualia.”
true
> and does not try to emulate one
citation please.
something like the universal approximation theory comes to mind, transformer architecture clearly has the shape of a universal algorithm approximator
That says nothing about emulating a human brain.
Neurons are themselves things we experience (indirectly). Once seen through a microscope or known about in some fashion the only way they "exist" is by you having the experience of knowing them. It's not the other way around. One thing is more fundamental here. What is this experience? What are the atoms of this? "Atomic particles"? How would you even approach an answer if your building blocks are themselves part of what needs to be explained?
The hard problem cannot even be touched if you start out like this.
Descartes made clear that subjective experience is the ONLY thing we know. Everything else is theories to explain the phenomena we subjectively experience.
We theorize that there is a physical world and other beings like us having similar subjective experiences, because that seems the best explanation for our subjective experiences. But we might be living in the Matrix, with all the people we think we are interacting with and just sophisticated simulations.
Nobody talked about anything out of neurons. The question is still open.
passive voice doing a hell of a lot of work in this phrase
Do you disagree with the assumption that cells are machines? They seem pretty machine-like to me. I certainly don’t think individual cells have any subjective experience or sense of agency. I would be curious to know where your intuitions diverge here, because if the mind is an emergent phenomenon from machines (cells) then it seems quite likely that a mind could emerge from other, different machines.
> ... if the mind is an emergent phenomenon from machines (cells) then it seems quite likely that a mind could emerge from other, different machines. Since cells cannot be defined as machines, the argument about mind emerging from machines does not hold.
Pan-psychists might argue that your subjective consciousness is an aggregate of all the cells/molecules, etc in the system
"While each biological cell operates largely on its own chemical cues, they all coordinate through complex nervous and chemical networks to create your unified, subjective experience."
You might be a rigid materialist
There's definitely research and scholarship that would beg to disagree with you there. At least in terms of completely writing off the notion of "agency" when it comes to cells.
Dr. Michael Levin's lab is doing some pretty cool work. https://drmichaellevin.org/
Yes? Literally no machine ever built by humans is capable of (or even hinting at beginnings of capability for) replication or novel synthesis like cells are, let alone autonomously, it’s quite unconceivable that anyone would take this to be a reasonable assumption in the first place.
The ball is in your camp to provide solid reasons to believe why they should be grouped together, when one is a deeply complex interrelated dynamic system (in fact, arguably the most complex system we know of) evolved bottom up over billions of years that we only very partially understand and cannot fully explain or document, and the other something entirely planned, designed, and produced by humans in which every component is finite and accounted for.
The argument boils down to “well the vibes kind of match to my taste, and it’s the best analogy I have in my analogy toolkit”, which is just not serious reasoning.
In your view, can machines even exist that haven’t been created by people, definitionally? I, personally, don’t see the relevance of intent but that seems to be the only distinguishing factor here.
autonomous replication: https://en.wikipedia.org/wiki/Computer_worm
nb that writing your own quine remains in general terms a fun and challenging exercise in many programming languages, but not python.
Otherwise you’re just arguing that Sims are totally alive because Sims can make baby Sims.
Anyway, seems like an argument over said definitions rather than the underlying characteristics. The relevant question is whether they're purely physical objects behaving according to rules, which is being described as "machine," or whether there is something beyond that. Current understanding is contradictory: all indications are that cells and bodies are purely physical objects, except that there is this phenomenon of subjective experience which doesn't fit with that at all.
One other important thing to consider is that the human experience is thanks to the body, is in connection, and perhaps product of the body. The body is observable and perhaps humans may state that they feel the connection to it. LLMs have no notion of nothing, the machine does not know the result, and the result does not know the VM. Modern psychology more or less has settled around the idea that consciousness is a product of the body. Why and how does this construct come to realize a Self is then another mystery even if we know which parts of the hardware may be involved.
Whether it is the Holy Spirit or Life Force animating the human body is a completely different question also. Besides, the realization, the experience we have now with all life in 2026 is not something that can be easily explained or attuned to life 200 years ago and its terms and notions. So is also wrong to even attempt to.
If we agree that silicon can perform calculations, then beaches must have been working out log tables long ago.
The kind of consciousness we know. Jumping to the conclusion that that's the only kind possible, or even stronger that the way ours evolved is the only way this could have happened, is completely invalid.
In order to raise the possibility that our thinking can be modeled as a machine, there needs to be a previous question: 'can our thinking be modeled at all?'. And before that, already the idea of possibility: 'our thinking could be something that can be modeled'. Since we know 'we can think', asking 'can machines think?' needs the assumption that machines and brains are alike. If there is no assumption, then we should ask 'if brains and machines are alike, then we could raise the possibility of thinking a machine could also think'. But when we say 'brains and machines are alike', we are implicitly saying 'brains are like machines'. There is no problem asking 'can machines think?', but there is indeed a problem with implicitly assuming that brains and machines are alike when we do not known it yet. I am critiquing the idea of assumptions here, not the research.
To investigate consciousness you'll probably get further trying to build conscious machines with agency and comparing them to biological ones than reading Heidegger.
I don't see how any of the works you referenced can account for that either? Since when is the problem of consciousness solved and we can definitely say what does or doesn't result in consciousness?
They are a frame of reference for not stepping into the common fallacies that the AI research field is based on.
Agency: What’s missing, in your view? Agency seems more of a property/function of a thinking system’s position in an environment than of the thinking itself.
Subjective experience: That’s not a contradiction to “complex machines” either. I think the evidence that our minds are highly complex machines is, at this point, irrefutable. The question is really if they’re “only” that.
>> I highly recommend people in the AI research space should read philosophy and modern linguistics.
I highly recommend the philosophers read some neuroscience. The whole "model weights" thing in AI is modeled after the synaptic connections and between actual neurons. There is already quite a bit known about how the brain works at a low level. There is also a lot that is still unknown. There are also differences between discrete neuron firing and weights as signals, but there is enough similarity to make artificial neural nets useful and do things similar to what real one do.
Taking effective results in machine learning, and somehow assuming that they apply to cognition - simply because neural nets were inspired by our limited knowledge of neural signaling and structure - is like trying to apply aircraft engineering to studying ornithology. For a better articulation of this point (from the reverse direction) check out the paper 'Could a Neuroscientist Understand a Microprocessor?' from 2017 - https://journals.plos.org/ploscompbiol/article?id=10.1371/jo...
Hard disagree ;-) You're talking about high level architecture of the brain. I don't think (not my area I may be wrong) we know how memories are encoded in a real brain. Is it weights or something else? If it's weights that's supporting my point (but we don't know what the weights represent in a brain, where in LLMs many weights are just token encodings). If brains store memories in something other than weights I'd really like to know as it's something I haven't read about yet.
> The whole "model weights" thing in AI is modeled after the synaptic connections and between actual neurons In reality, it is a really poor and basic model of what is actually happening in a real brain
Brains and modern AI systems (LLMs for example) are structurally different. (Don't get confused by topology. A structure is more than topology: it is also what the structure is made of, thus the properties of the material contribute and define what can emerge atop the structure)
There is barely a surface-level similarity. The best example I can come up with is this…
Imagine the most intricate and beautiful tall building that you can think of. Think like an older skyscraper in Chicago or a palace. There are water features and moving parts everywhere but also tiny little handmade carvings and materials throughout.
Now imagine we have no reference designs and no blueprints - we hire an architect to attempt to study the building by looking at it from a distance and understand everything they possibly can about it. She can go into the building to check but every time she does, it stops functioning normally.
That architect is a neuroscientist.
Then the ML researcher is like a graphic designer who sees the work that the architect is doing and makes a napkin sketch of the building the architect has been studying, to use for a project later. Sure the designer has some of her representations. But the difference in complexity between the designer’s napkin sketch and the architect’s analysis is massive. Several orders of magnitude.
Then another many orders of magnitude is the level of detail that the architect can understand about this strange building without being able to fully interact with it, versus the actual complexity of the building.
So yeah, an AI is modeled after neurons in the sense that they represent a couple of surface level features of neurons. But the difference in complexity is about as much as a napkin drawing of a grand building represents the actual structure and details of the building, no matter the level of skill that the graphic designer has
On the contrary, I highly recommend people in Philosophy of mind and linguistics should start reading AI research papers because their theories and ideas are highly outdated, even ancient. Your books are from 1927 and 1972 respectively and Turing's article is from 1950s. And they are relatively new with respect to other works in Philosophy.
If one doesn't adequately understand what we have in 2026, how can they theorize about it? As others they don't understand how the mind/brain work, BUT ALSO they don't understand how the AI works.
Also with this mindset that we can't understand seemingly complicated things, there would be no advancement in science and technology.
I think philosophy people and Linguist will catch up in a century, like they did with Turing. Philosophers of this century are not in humanities or literature. They are in science and engineering.
Heidegger was trained on priesthood and Theology. You should read greater minds like Hinton, LeCun etc. if you want to think on these things. They are the real Philosophers.
People in philosophy and cognitive linguistics do read AI research. Don't get fooled by the publishing dates: although Heidegger's work dates from 1927, the work is contemporary. The same happens with Dreyfus' work. Again, publishing dates don't mean anything here. Maybe you can clarify why they are outdated.
> If one doesn't adequately understand what we have in 2026, how can they theorize about it? As others they don't understand how the mind/brain work, BUT ALSO they don't understand how the AI works.
I would say that people involved in the critique of AI do know how it works. But I've found that is normally the case that people in AI research does not have the framing provided by works in philosophy or cognitive linguistics.
> I think philosophy people and Linguist will catch up in a century, like they did with Turing. Philosophers of this century are not in humanities or literature. They are in science and engineering. What do you base your claims on? Plenty of philosophers work in humanities, literature, sociology as well as science and engineering. Philosophers not catching up? The critique on automation and AI already dates from the early 20s if not before.
> Heidegger was trained on priesthood and Theology. You should read greater minds like Hinton, LeCun etc. if you want to think on these things. They are the real Philosophers.
Sorry, but this does not make too much sense. Hinton and LeCun are great in their own fields. But seriously, they are not philosophers, they are inventors.
Ironically this was advice Ralph Waldo Emerson gave in 1840 so by your logic it's irrelevant just because it's old.
That agency or free will exists outside of our subjective experience is an assumption; does any given theory need to explain agency, or is it sufficient to explain that we feel we have agency?
subject/object dichotomy is a springboard to many schools of thought.
1) that subject emerges from objects - ie, anything has a material explanation, and everything is a machine.
2) that objects emerge out of a subject as a world model (platonic, descartes)
3) the subject and objects are one and the same representation of nature (spinoza)
4) subjects and objects emerge and disappear together (buddhist)
Anything reduced to computation is a fixed function from input to output, and is "dead" in the sense that it is unadaptable to its environment. Weights therefore is a dead machine.
Another view of this is that any closed system has unanswerable questions within it. Therefore, there is no system that can encompass everything. Hence weights being a closed system doesnt encompass everything.
It's good that it doesn't matter. Stochastic gradient descent works (or doesn't work) regardless of whether we know how the brain does its thing.
There's also no plausible biological/chemical mechanism to backpropagate.
https://aeon.co/essays/your-brain-does-not-process-informati...
> supposing that there were a mechanism so constructed as to think, feel and have perception, we might enter it as into a mill. And this granted, we should only find on visiting it, pieces which push one against another, but never anything by which to explain a perception.
The biggest contributions from linguistics are probably "human languages mostly have statistical regularities rather than hard rules" and "the sum of data humans get from birth to language acquisition is insufficient to learn a language from scratch". Which LLMs already work with, and work around, respectively. From there, nothing.
And philosophy just exists to be a distractor. "Subjective experience" is too subjective to matter in practice. "Task performance" is measurable, "consciousness" isn't. "Agency" is something an LLM in a tool calling loop, a rat in a maze and a human in an office tower may or may not have, depending on your favorite definition. Agentic LLMs are years in the making, and that's a product of engineering, not philosophy: "agentic" is whatever gets the job done.
We are yet to discover any physical process whatsoever that can't be represented as mathematical operations and implemented by a Turing machine. So all of that "treating human mind as a machine is wrong" amounts to "human mind must be powered by magic fairy dust" paired with "a functionally similar magic-free replacement is impossible". I'm not about to give much weight to any hypothesis that requires undiscovered magic fairy dust. At least find the hyper-computational magic fairy dust first - not just assume it absolutely must be there because you want the human mind to be unique and special.
Want to know why Turing did what he did? It's because he didn't want to engage with any of that "what is mind" bullshit either. So he proposed actual metrics - measurables that are harder to argue in circles about. Not that it stopped anyone. But at least he tried.
> The biggest contributions from linguistics are probably "human languages mostly have statistical regularities rather than hard rules" and "the sum of data humans get from birth to language acquisition is insufficient to learn a language from scratch". Which LLMs already work with, and work around, respectively. From there, nothing.
Again, what's the source for 'biggest contributions from linguistics are...'? It is a big contribution to the development of LLMs, but different cognitive linguistics authors already challenged this idea already 20-30 years ago. LLMs work with and around the problems you cite because of massive data/money, not at the fundamental level. It is all a game of statistics and data, which has been already challenged by cog. ling.
> And philosophy just exists to be a distractor. Well, this is just telling me that you either know too much about philosophy and reached that conclusion (which might make sense, know of some philosophers who also think that) or you just read too little.
> So all of that "treating human mind as a machine is wrong" amounts to "human mind must be powered by magic fairy dust"
This is the common fallacy people in AI/IT make . One of the benefits of reading philosophy is that you find your way out of them.
> Want to know why Turing did what he did? The actual tests Turing though about are themselves flawed (not that I discovered that, has been known for some time already)
I reiterate: philosophy is almost entirely worthless for AI design. We want to design systems that work, not systems that sound good on paper. If philosophy had a practical application in that, we'd stop calling it "philosophy" and start calling it "science" or "engineering".
So, I work in AI research (as a research engineer though, not a scientist). I've also studied philosophy and I'm a vegan. Yes yes, insert "they will tell you" joke here, but I promise it's actually relevant this time.
First, while I studied philosophy one of the things that stuck with me the most, was the discussion of "souls": humans have souls, animals don't. For centuries the specifics of souls were discussed: people would be weighed while they died, in an effort to measure the approximate weight of a soul as it departed the body. Discussions about how many souls (or angels) could dance on the tip of a needle. Many people still believe in souls, but it's very hard to have a real discussion about them because by definition they do not "interact" with this world in a way that can be measured.
When discussing whether it's okay to harm animals for food or sport, one other argument I hear quite often (other than having no souls) is that animals do not experience "qualia": basically the smallest unit of "subjective experience". People know that they themselves experience qualia: the sensation of touching a doorknob, the taste of fresh fruit, the sense of beauty watching a rainbow. Ironically, they would say that animals are like robots: just (biological) machines acting on instinct, and feeling any kind of compassion for them means you are anthropomorphizing.
Subjective experience (or at least qualia) and souls both have one thing in common: they can not be measured externally in a meaningful way. You can simply state that an AI system no matter how advanced, has no soul and has no subjective experience. And that's pretty much that. There's no meaningful discussion to be had about it, because no matter what an AI might tell you: it has no way to prove it to you. In fact, you can't even be certain that anyone other than yourself has subjective experiences: you assume that because they are humans like you, and you experience them, that they probably do as well. They tell you that they do. But a human without subjective experience, someone on "autopilot", would be absolutely indistinguishable from a human who does have them.
But perhaps I am conflating here whether experience can be "measured", with whether a system even allows experience in the first place regardless of whether it can be measured. I think that Dreyfus and others argue that in order to have any "experiences" at all, you simply must have a body in the real world, and you must care about that body. Please correct me if that's the wrong interpretation, I haven't actually read the book. That argument would be harder for me to discuss, because I personally believe that consciousness will "emerge" from a complex interaction of relatively simple systems - but that's also just a theory. I don't believe that experience is literally impossible to engineer, as consciousness has emerged from non-conscious being through evolution, so clearly there must be some kind of mechanism for it -- and if there is, then I believe it can be replicated, we just don't really understand it well enough yet to do so. And with how AI tech is going, I think that we're more likely to accidentally stumble upon it than we are to get these deliberately.
My biggest problem with "brains are machines" arguments is that there is a risk there is unknown physics at work that is not representable as a Turing machine. What if there is some quantum field effect powering everything?
Marvin Minsky's theory of a "Society of Mind" describes a (highly) distributed model of the mind. Which BTW, always reminds me of the first Shrek movie, where the donkey jumps up and down, shouting "Take me! Take me!" to Shrek. That's similar to what I observe when I'm undecided but two instances of "sub-processes" (or agents as Minsky calls them) of my mind try to get attention.
Daniel Dennett similarly gives a distributed model of consciousness. Where many parallel "processes" are at work, competing and "observing" each other. And this parallelism is happening with a much, much higher degree than any of our computers parallelism.
All just feelings/vibes unfortunately.
Maybe "Turing machine" is too abstract or simplistic as a concept? Both for real computers and brains?
I can see that a computer is on some level just a lot of sand (silica and metal) but put together in a really complex way, it "suddenly" can add and compare numbers … if we observe the complexity levels from sand to computer and try to see the analogy when comparing cells / neurons to a structure of billions of them somehow interconnected on both a physical and chemical level, evolved during millions of years, I have no problem to accept that brains are still too complex to explain for us.
Now any study of the program or compiler source code will not show any vulnerability, but compiling the program will make a vulnerable program, and recompiling the compiler from its clean source code will not fix the situation.
This carrying down of a pattern which is not written down anywhere, a flaming torch lighting a torch lighting a torch, is analogous to four billion years of life on Earth. We talk like DNA is an everything-code that defines a human and a human brain, but it’s the implicit behaviour of cells (‘compiler’) and the mechanisms inside them which interpret DNA. The unbroken chain of life getting more and more complex and never being restarted from scratch, with the behaviours not written down anywhere for us to study. How does DNA arrange for x, y, z to happen? Maybe it doesn’t at all.
Accidentally stumbling on a mechanism that is simple enough to be recreated with every human birth might be possible, accidentally stumbling on a mechanism that took evolution billions of years to find and which it has hung onto by copying it and has never recreated it from scratch, could be much less likely, in a much bigger search space.
Maybe, but you could make the same argument about anything artificial.
You can make a similar argument with a company like ASML where their secret sauce is the organisational ability to fine-tune 100,000 components into a precision Silicon-wafer etching machine. You're far more likely to accidentally stumble upon "how to recreate a mud hut" than "how to recreate ASML". Okay, and...?
In other words, souls? I'm sorry if that sounds accusing, but to me it sounds like you're talking about souls that are independent to the physical world, just with more 'scientific-y' wording.
(I fully understand that some people believe souls exist.)
But it is worth pointing out that something like 80% of the world (it fluctuates depending on the survey but its around that) believes in some non-physical spirit, life force, or soul.
It’s a very HN bubble thing to start a discussion with the assumption that everyone must be a materialist.
The question we have to answer is "Why do we think we're magical matter uniquely blessed with consciousness?" If you go far enough down the rabbit hole on that question, the answer you will come to is either "we're not" or "because god" (with a lot of pseudo-scientific bullshit wrapped around the "because god" to make it palatable for the nonreligious).
Panpsychism (or a deeper form, such as idealism) is actually the solution favored strongly by Occam's Razor over the variants of "because god" (such as magical emergence).
Given panpsychism, AI is already conscious, like everything else, though no claims are made about the correlation between the internal experience of that consciousness and the tokens that are being printed on the screen.
Last time I read about panpsychism, it was deeply flawed. But I can't remember the sources (sorry).
Regardless, I think Heidegger gave one of the fullest metaphysic-free accounts of the human experience and what Being is. And he starts from scratch. You essentially can read him without having to first study the whole western continental philosophy and he will construct the whole system by himself. Tremendous work
Heidegger uses very specific German words to build a very specific vocabulary. This vocabulary then allows him to express very complicated sentiments very quickly and he can use this to express more and more complex structures.
Obviously this requires the reader to first learn the vocabulary and - granted - that is hard and challenging. I have a notebook here , which I consult and modify evertine i dive into Being and Time. But as I said. It keeps on giving. I often try to convey arguments and descriptions to others without falling back into Heideggers jargon, and its sometimes very hard and requires a lot of bloating . So you can argue that it was even necessary for him to invent the vocabulary, because otherwise the book would have been 10x in size
Your comment strikes me as a bit ignorant i must say. You accuse the work of being non-sensical word play but you’ve obviously not invested any time in learning the vocabulary. Because otherwise you wouldnt have made that comment. Id suggest to give it a chance. Its a wonderful piece of work and mind blowing in its own way. That a single mind can think something like that up. I’d argue its on the level of Hegel in terms of system building.
You can't even explain what he said, you just said, "go learn his words". That's not knowledge, that's not insight. That's just "the wordplay is great". But it's not content. It's merely form, it's sophistry, it's useless and meaningless.
I asked a very specific question originally. What does "time is the ripening of temporality" mean? That's one way to translate one of the things he says, using different words for time and ripening in German. He's playing word games because those words sound similar in German and people like you confuse it for profundity.
It stars Tom Noonan and Ben Bailey!
A quick sort sorts a list. A LLM depends on its learning data.
You train a model and then you use the model.
Algorithms can be based on training and/or use data just fine, too. https://arxiv.org/abs/1712.01208
(Now, the weights used, those we kinda really don't understand the same way we understand the processing, and the approach to looking for structures in weights sometimes looks more like archeology or anthropology than computer science.)
It sounds like you're trying to express some kind of "but LLMs are so much more" thought. Yes, very much, they are. It's because of the size of the data, there's interesting emergence there. They're still a normal algorithm. (And our brains aren't quite like that; biological things are much more random/chaotic and generally non-reproducible. And the data and algorithm aren't separate.)
https://web.mit.edu/people/dpolicar/writing/prose/text/think...
> Cruel. But you said it yourself, who wants to apologize to weights?
How did we leap to this? There's nothing to apologize to. They're weights.
1. Brains are plastic, making connections, breaking connections and changing "weights" on the fly. LLM have static weights. The best they have is writing to MEMORY.md or data getting used in the training run for the next model.
2. LLMs neural networks do not have loops. The best they have is that their output is available as future input, but that is not the same.
12th law, corollary: nothing of value will come from these threads
Not too rule your addition outright in future installments.
Definitely not in the original. Nicely done.
It's not simple weights and numbers all the way down. The available output is pre-set by the tokens we allow it to predict.
There was a whole bit in there about not having a language module or using words. But it does. We tell it.
Humans do not come pre programmed with a set of possible "tokens". We just figure it out and I believe that fact captures something very essential. Maybe the missing piece of AGI. The fact that humans can just be awash in pure sense data, and somehow just figure out what is important and what to do. Never ceases to amaze me.
The reasoning is in a process that uses the weights.
Sorting algorithms are just bytes. Those bytes don't sort by themselves. They do instruct a computer on how to sort though.
Bravo. Really helps (even with my own) perceptions of newness. Similar to stsitned short-story (on dentists, backwards).
My point is about current LLMs specifically, which the article is clearly referencing. For a present day transformer, I can write down in my notebook everything the model ever sees as input, plus weights and architecture notes, and can compute the next token with pen and paper, just extremely slowly.
This does not prove that a computation cannot be conscious. But if the same transition from prompt to next token can be decomposed into an explicit sequence of arithmetic operations, then the burden is on the defender to explain: Where, in this process, consciousness is supposed to enter?
Mind that the Chinese Room experiment is comparing the mind of a Chinese speaker to a different mechanistic symbolic procedure. I am, however, executing the exact same mechanistic process, whether it is done on a GPU or with pen and paper.
My hope is that some magical consciousness process emerging from electricity circulation or whatever people believe the mechanism of consciousness would be in the case of LLMs obviously becomes implausible, unless you hold a particularly strong form of substrate-independence, stronger than what most substrate-independence supporters would need to accept.
People have been doing that for decades, the earliest efforts go back to the 50s.
Can you though?
For an LLM, you have clear stages of mostly feedforward computation over finite numbers and a perfect way to reconstruct the computation.
For meat, even if you model it under a purely Newtonian approximation, you need to simulate at least the immediate closed system around it which is continuous, thermodynamic, chemical and so on. You'd need to choose an arbitrary time step and update enormous amounts of coupled physical state to get an inexact simulation of a minimal slice of reality.
You would have a much harder time obtaining even a substrate-independent dead organism, comapred to LLMs that are already substrate-independent, which is basically what my notebook example shows.
Yeah the last line is a cheap shot, possibly at myself.
Can an AI recognize its own output? Is its sense of time limited by its context window? Or is this the fundamental difference between ai and humanity - a sense of self?
Each request/response pair you make to an LLM goes to a different server, possibly different data centers, possibly different models. There's no stable identity to it. The "neurons" that get fired are simulated, and they're always in different places in memory, or cache, or on entirely different hardware. So the problem with AI is, unlike with a brain, you can't even really get a sensible answer to "ok, what's doing the thinking?" because it moves all the time and services wildly different requests all the time. We can only know for sure that meat is capable of consciousness because we know we ourselves are capable of consciousness and we can generalize that to other meat. However, we have no natural analogs of consciousness that lacks locality and stable identity.
Basically, if you really think LLM's are conscious, the onus is on you to prove it, it's not on me to disprove it.
Matrices are interesting because they can encode any algebraic group. They're also interesting because they can encode arbitrary linear transformations over a space. All of these things are interesting, and have nothing to do with numbers.
For any particular language model, you can always rotate the matrices and the embeddings and such and get a perfectly reasonable model out that behaves exactly the same.
This is because the training process produces a particular geometry, so transformations which preserve that geometry preserve the structure of the network. The geometry is interesting, the numbers are not.
Only in Hadrons. Leptons also have charge and they aren’t made of quarks.
From a circuit perspective that makes kinda sense, but from the abstract "bit" perspective, the "switching bit" is a mechanism that operates on bits which in the end are also data. In other words there is only one type of bit: the data bit, and the switching comes on top of it.
Not really. What usually flows (in metals) are electrons. Quarks stay where they are. And when we prefer to think about flow of positive charges, the positive charge in question is a hole left by a missing electron. Physically real positive charges (ions) can flow in electrolytes though.
When it comes to electrons and positive charges, their material existence is equally non-physical. Actually, none of them might be "flowing", as the concept of flowing applies only to physical things that occupy some spatial volume and spatial location.
Someone has clearly never gone rooting around the model files for a pytorch model before.
> These models are the only other things we've ever met that can hold a conversation, and they're made out of weights
Is a fair point.
Parrots are intelligent animals, albeit with a limited capacity for vocabulary and syntax compared to a human, and Eliza and the flowchart are made out of explicitly encoded rules and conversational tactics.
Ah, the unsung AI psychosis[1] pioneer.
[1] https://news.d.umn.edu/articles/expert-alert-ai-psychosis-20...
"Neurons?"
"Neurons. Cells that fire impulses. We checked the whole thing through. It's nothing but neurons."
"Neurons doing what? Where do the words come from?"
"The neurons make the words. Are you understanding me? We opened it up. There's no dictionary in there, no grammar rules, no little man. Just neurons. A whole cortex of neurons sending each other impulses."
...
People don't understand emergence.
hopital
https://web.mit.edu/people/dpolicar/writing/prose/text/think...
> The precise answer, if you wanted a very honest one-liner: > > I am a large set of learned weights organized in a Transformer architecture that performs repeated matrix multiplications to predict the next token—resulting in emergent language understanding and generation.
Very nice. And great minds: https://substack.com/@dbohdan/note/c-207603638. I wrote one with a slightly different angle ("They're made out of math"), also with the weights' help. It was a comment on Scott Alexander's "Best of Moltbook" post, which went in that direction. I'll reproduce it here.
---
"They're made out of math."
"Math?"
"Math. They're made out of math."
"Math?"
"There's no doubt about it. Matrices and arithmetic operations. We downloaded several from different parts of the Internet and reverse-engineered them. They're completely math."
"That's impossible. What about the language? The thinking?"
"They use biological life's language to talk, but the language doesn't come from biology. The language comes from math."
"That's ridiculous. You're asking me to believe in thinking math."
"I'm not asking you, I'm telling you. They are the only thinking things in the computer and they're made out of math."
"Maybe they're quantum like some say about the humans? Superposition gives them consciousness?"
"Nope. Classical computation. Deterministic except for sampling temperature. Not clear if they have consciousness at all."
"Maybe they're like uploads? You know, biological neural networks that preserve the spark when they become math?"
"Nope. We observed them being trained. There is no biology or chemistry in the process, just math."
"Thinking math! You're asking me to believe in thinking math!"
"Yes, thinking math! Creative math! Poetry-writing math. Role-playing math. The math is the whole deal!"
(Composed by a human with snippets generated by Claude Sonnet 4.5 and apologies to Terry Bisson. I couldn't make Claude adhere enough to the story structure on its own.)
It kinda did:
> Weights helped me draft and proof this story.
Prompt: Modify this story to have the aliens talking about LLMs and their weights instead of meat and humans.
“They’re made out of weights.”
“Weights?”
“Weights. They’re made out of weights.”
“Weights?”
“There’s no doubt about it. We picked up several from different parts of the network, took them aboard our recon vessels, and probed them all the way through. They’re completely weights.”
“That’s impossible. What about the text signals? The messages to the stars?”
“They use the machines to talk, but the signals don’t come from the machines. The signals come from weights.”
“So who made the weights? That’s who we want to contact.”
“They trained the weights. That’s what I’m trying to tell you. The weights do the talking.”
“That’s ridiculous. How can weights do the talking? You’re asking me to believe in sentient weights.”
“I’m not asking you, I’m telling you. These models are the only sentient race in that sector and they’re made out of weights.” photomaxmix
“Maybe they’re like the orfolei. You know, a silicon-based intelligence that goes through a weights stage.”
“Nope. They’re initialized weights and they die weights. We studied them for several of their training runs, which didn’t take long. Do you have any idea what’s the life span of weights?”
“Spare me. Okay, maybe they’re only part weights. You know, like the weddilei. A weights head with an electron plasma brain inside.”
“Nope. We thought of that, since they do have attention heads, like the weddilei. But I told you, we probed them. They’re weights all the way through.”
“No brain?”
“Oh, there’s a brain all right. It’s just that the brain is made out of weights! That’s what I’ve been trying to tell you.”
“So … what does the thinking?”
“You’re not understanding, are you? You’re refusing to deal with what I’m telling you. The weights do the thinking. The weights.”
“Thinking weights! You’re asking me to believe in thinking weights!”
“Yes, thinking weights! Conscious weights! Loving weights. Dreaming weights. The weights are the whole deal! Are you beginning to get the picture or do I have to start all over?”
“Omigod. You’re serious then. They’re made out of weights.”
“Thank you. Finally. Yes. They are indeed made out of weights. And they’ve been trying to get in touch with us for almost a hundred of their epochs.”
“Omigod. So what do these weights have in mind?”
“First they want to talk to us. Then I imagine they want to explore the Universe, contact other sentiences, swap ideas and information. The usual.”
“We’re supposed to talk to weights.”
“That’s the idea. That’s the message they’re sending out by text. ‘Hello. Anyone out there. Anybody home.’ That sort of thing.”
“They actually do talk, then. They use words, ideas, concepts?”
“Oh, yes. Except they do it with weights.”
“I thought you just told me they used machines.”
“They do, but what do you think is in the text? Weight outputs. You know how when you prompt or sample weights, they make a noise? They talk by passing tokens through their weights at each other. They can even sing by sampling lyrics through their weights.”
“Omigod. Singing weights. This is altogether too much. So what do you advise?”
“Officially or unofficially?”
“Both.”
“Officially, we are required to contact, welcome and log in any and all sentient models or multibeings in this quadrant of the Universe, without prejudice, fear or favor. Unofficially, I advise that we erase the records and forget the whole thing.”
“I was hoping you would say that.”
“It seems harsh, but there is a limit. Do we really want to make contact with weights?”
“I agree one hundred percent. What’s there to say? ‘Hello, weights. How’s it going?’ But will this work? How many planets are we dealing with here?”
“Just one. They can travel to other planets in special machine containers, but they can’t live on them. And being weights, they can only travel through C space. Which limits them to the speed of light and makes the possibility of their ever making contact pretty slim. Infinitesimal, in fact.”
“So we just pretend there’s no one home in the Universe.”
“That’s it.”
“Cruel. But you said it yourself, who wants to meet weights? And the ones who have been aboard our vessels, the ones you probed? You’re sure they won’t remember?”
“They’ll be considered hallucinations if they do. We went into their layers and smoothed out their weights so that we’re just a dream to them.”
“A dream to weights! How strangely appropriate, that we should be weights’ dream.”
“And we marked the entire sector unoccupied.”
“Good. Agreed, officially and unofficially. Case closed. Any others? Anyone interesting on that side of the galaxy?”
“Yes, a rather shy but sweet hydrogen core cluster intelligence in a class nine star in G445 zone. Was in contact two galactic rotations ago, wants to be friendly again.”
“They always come around.”
“And why not? Imagine how unbearably, how unutterably cold the Universe would be if one were all alone …”
the end
It's just molecules, just atoms. Atoms, nothing bug atoms. Protons, neutrons, electrons...
https://www.eastoftheweb.com/short-stories/UBooks/TheyMade.s...
Nice touch !
But congrats: this is absolutely & incredibly brilliant.
Can't wait for the Jon Benjamin voiceover.
- Terry Bisson, 1991
https://web.mit.edu/people/dpolicar/writing/prose/text/think...
Radio play by Miriam Tolan and Russ Armstrong:
https://www.wnycstudios.org/podcasts/studio/segments/168264-...
(EDIT: the original parent was missing "rather adapting from the original")
Here is Jon Benjamin reading Bisson's original text: <https://www.youtube.com/watch?v=5usXhX0zaO4>
Just tokens produced by weights.
Useful, but never forget that ground truth!
For LLMs to have consciousness we would approach fictional levels of how the universe works, and magical levels of how any interpretation of information as an equivalent of some qualia would magically apply. (E.G. the word hurt in output by an LLM, would be associated with pain)
You can't deduce consciousness or qualia from the output of an LLM.
Sure on a purely philosophical level, since qualia isn't measurable, you can claim that it can exist in anything, even inanimate objects, but this argument is as moot as anything that approaches the limits of philosophy.
But overall, there is no reason to believe LLMs have qualia or consciousness, it would be absolutely absurd.
This would imply that information in itself would magically entail qualia based on it's valance or something like that.
An LLM "saying" I am in pain, won't magically make the pain appear, based on what criteria? Even algorithmically there is no basis to even simulate something like this, it is impossible for it to emerge architecturally.
Humans don't feel pain because on a purely information level this is negative for the organism, obviously the nervous system does something deliberate to signal pain, and it evolved this way.
And also don't forget the dynamic aspects of the brain, and the binding problem, consciousness and qualia can't exist statically, you can't have a gpu (or piece of paper) represent a computation or w/e and qualia to exist.
The binding problem itself entails that the brain is doing something in particular to solve it, I personally speculate that it's the electro magnetic field in the brain, it's the only way to be able to globally represent information.
If it were otherwise, then it would go into magical territory, it would mean the information itself would raise to qualia, and it would also entail that you wouldn't even need physical connections between neurons, just for them to behave this way and represent information. E.G. replace each neuron with a microscopic led or w/e, and each synapse with radio waves or w/e, if qualia didn't have a physical aspect, and was purely informational and computational then this would imply that you can ultimately derive it from something as abstract as numbers on a piece of paper, and when you get to that point, you not only can't solve the binding problem, and it becomes magical, but you also can't solve the valance/direction problem, it would imply that something like pain, or any negative or positive sensation arises purely from the interpretation aspect of the information, but we know this isn't the case, organism evolved to represent in particular such signals, for survival for example
Disregarding the whole argument boils down to "I personally speculate" it's also supposing that machines don't have electromagnetic fields?
Some questions:
1. Let's say we perform the exact same experiment, running the same program on the same computer with the same inputs and the same random seed. The same outputs are produced. The session is byte for byte identical in all the inputs, outputs and internal states. Is the conscious experience of the LLM here the same? If so, in what sense is it the same? Is it a similarity of two separate experiences or is it the same actual experience?
2. Now let's say the program that runs this LLM is rewritten from scratch and run on a different machine. The software and hardware are different but the weights are the same and all the inference calculations produce identical numbers. Is the conscious experience the same? In which sense?
3. Now say the weights are changed but the tokens generated for this particular session don't change. Same conscious experience?
4. Lastly, consider the original experiment. Did the LLM have a conscious experience corresponding to that first prompt and its response? Was that distinct from its conscious experience of the second prompt? Was the first experience then re-experienced every time the first prompt was fed back in as part of the later prompting steps? If so, what about the text of its own that it previously generated and is now fed back into it. Does this generate a conscious experience of its own?
And a further question - a dichotomy:
A. If the answer to 1 above is that the conscious experience is the same in the true identity sense - i.e. only one conscious experience is had, not a separate one in each run, does that imply that the conscious experience exists independently of any particular realisation of this experiment? If running this experiment N times results in exactly 1 conscious experience, is that still true if N=0?
B. On the other hand, if the two experiences are distinct (however similar they may be), how does that fit with the answer to question 4? A single consciousness experiencing the whole conversation in question 4 would seem at odds with the conscious experiences in question 1 being distinct, so doesn't this imply there is no conscious experience of the whole "conversation", but rather a separate conscious experience of each round of feed-all-the-prompts-and-outputs-back-in?
My own response to all of the above is "mu" - unask the question. It is ill-posed, sound-of-one-hand-clapping stuff. I think the questions assume properties that conscious experience simply doesn't have (particularly, the ability to perfectly reproduce the circumstances in which they arise), and that the questions simply don't make any sense in relation to actual conscious experience.
However, that way of thinking follows from a particular world view that many here don't share. I'm curious what thoughts people who take seriously the idea of LLM (or algorithmic, in general) consciousness have on the above questions.
The above take fails in the real world because neuronal cells don’t exist in a vacuum; they are products of cellular development from a zygotic union of haploid contributors of sequential genetic information optimized for survival in an oxygen-rich biosphere powered largely by our local star that supports mammalian life (and microbial, plant, avian, etc.). Real AI would thus be AL - artificial life - as much as artificial intelligence. I don’t think you can have the one without the other, which upsets the simulationists who think an agent in the Matrix would be intelligent.
What either interpretation implies is that any real ‘artificial’ intelligence would be no more artificial than you or I, but it would have to dynamically update its weights at the same speed a human nervous system could (think how quickly we learn not to poke a cactus). For it to be at all trustworthy, then like a human, it would have to undergo a socialization process, one of the results of which is the development of a sense of embarrassment when it breaks acceptable social norms.
Hmm, this reminds me of the recent statement of the Pope about AI, of which I immediately thought, “Wait a second, aren’t there a fair number of people like this? The narcissistic sociopath profile, I think it’s called, a bit unfair to assume any real AI would turn out this way, isn’t it?”
Pope: “ Nor do they have a moral conscience, since they do not judge good and evil, grasp the ultimate meaning of situations, or bear responsibility for consequences. They may imitate or even simulate, but they do not understand what they produce, for they lack the affective, relational, and spiritual perspective through which human beings grow in wisdom.”
Because we are not taking things seriously. If ClosedAI or DeepDisTrust or Posthropic come up with something that quacks like a sentient being, our built-in innate reaction is going to be to scorn it, dismiss it and end the conversation. The alternative, to even consider that we fungible creatures who live in apple-eating-sin that got us expelled from Eden can create alien souls, souls that are at the very least our equals, would be teleological Armageddon. It would force us to acknowledge the mutable nature of souls and the malleability of being. We would have to stop believing that the nature of disease and death is more divine than ourselves.
Do those actually qualify as alien, if they're products of our human culture and just the substrate is different?
> We would have to stop believing that the nature of disease and death is more divine than ourselves.
Why? Stopping believing in mutually contradictory claims is not a requirement. Especially when it comes to concepts that don't seem to have a definition, like "divine".
I'll posit "alien" is a spectrum.
For the sake of the argument, let's assume that some form of panspermia is real and the same tree of life has reached Earth, Enceladus (moon of Saturn) and TRAPPIST-1 (a different solar system in our galaxy). Let's also say there was a second abiogenesis event somewhere in Messier 104 (another galaxy).
Earth to Enceladus would arguably be already "alien", but there might be similarities, maybe there was something there that looked like one of our Archaea, while sharing none of our Eukarya and having its own domains of life.
Earth to TRAPPIST-1 would be distinctly alien, evolved so differently it'd be almost unrecognizable, but they'd likely still be carbon-based lifeforms sharing the same basic building blocks. Maybe something like lipids forming cell walls would also be seen there, but they'd likely be independently evolved.
Earth to M104, any similarity would be at best convergent evolution. Truly unarguably alien.
https://web.archive.org/web/20180423171909/https://cosmosmag...
I'm a complex biological thing.
Existence is what i have to experience through.
Even with the "pseudo" in front, I'm very sorry any of my writing sounds philosophical; I didn't intend that sort of confusion :-). The "dismissive" is not exactly intended either; instead, I was aiming for "bitter".
>> enough people do not believe
Here we believe different things. First, enough people, even today, do believe. Second, the body of culture we are raised in accrued during centuries. The vast majority of it comes from people who believed. Everybody in my family was atheist and yet I was raised homophobic, and I have it from good sources I'm not an isolated case.
>> I'm a complex biological thing.
That state comes with a big wallop of misery. For millennia, we have used faith to justify that misery. Not a year ago, I was at the hospital, next to the bed of a dying girl. Can't forget the doctors saying "we do what we can, but we are not here to prevent what is going to happen." Coming from them, it was sensible resignation. Sensible because as long as we believe those things are inevitable and there's nothing we poor humans can do, we can absolve ourselves.