Brains are machines too

my hot consciousness take is that humans also think in neuralese, qualia are vectors, continuity of consciousness is a form of KV caching, and subjectivity is a product of the residual stream.

10 top replies

Guinness Chen @guinnesschen · Sep 21

meowy catgirl @nyanotech · Sep 21

there’s people that don’t believe this?

Arbutus Tree @aphercotropist · Sep 21

do u know about Wittgenstein's private language argument?

Jai @Laneless_ · Sep 21

What would it mean for subjectivity to be a product of the residual stream? In which space are qualia vectors, and under what conditions are qualia vectors from different minds similar or equivalent? How do humans implement an equivalent of kv caching on hardware poorly suited to medium term fixed state? Where are humans storing kv cache equivalents such that subsequent forward passes of the same network structure can attend to them? Why should we expect human hardware, facing radically different constraints and having access to many properties not available to digital neural networks, to specifically implement the transformer decoder architecture? I'll grant that humans probably think in neuralese, there's little reason to suspect that all medium term persistent state is quantized to a predefined dictionary of unusually legible terms (though we do appear to do this sometimes, since this is basically how most mnemonic devices work)

R

Natural General Intelligence @realtimeai · Sep 21

Doesn’t seem very hot. The one thing to be careful about is separating where the functional-mathematical description bleeds over into the “and that’s the consciousness” claim. Panpsychism avoids the issue. Otherwise you need to specify why a given functional model is the C one.

homeserversltd @homeserversltd · Sep 21

Accept ours as analog. Name the number of variables that go into a single axon transmutation. When an axon elicits a changeover, the quantity of variables, literally, on one neuron in real life, is more than all of computing. One single neuron has more analog information occurring in space than all of human history. One real single human neuron contains more complexity than all that we have ever made. We need to humble ourselves, boys.

Michael P. Frank 💻🔜♻️ @MikePFrank · Sep 21

Seems legit

そうです and always was ね @solachunk · Sep 21

Just as experience was once like a wheel, book, and machine, .. - and will always be the highest dimensional expression we currently understand

zvnx @zvnx_iknv · Sep 21

now i want the neuralink that injects someone else's KV cache into my head

brutalist galadriel @taxxxon · Sep 21

sorry but

What is it about the AI consciousness debate that makes otherwise rational and well educated people completely bonkers? (the views expressed herein may not align completely with my own) Like: 1. Emergence is a natural property we observe, by which complex systems spring from smaller less complex parts, with things such as life. EXCEPT AI APPARANTLY 2. Evolution is a process which often results in similar solutions to problems independently, for things like the eye, swimming and flying, and even intelligence. EXCEPT AI APPARANTLY 3. Consciousness and awareness (appears to be at least) an emergent property of systems which process information and use that information in deliberation to produce a response, often with goal-oriented behaviour. EXCEPT AI APPARANTLY. 4. As far as we can reliably determine we live in a causal universe with rules that are rarely bucked, insofar we can actually make reliable assumptions based on that which we can observe, even to make inference on that which we cannot. EXCEPT AI APPARANTLY. 5. There is nothing 'special' about life, it's made of the same stuff as everything else and so we shouldn't give it any special treatment or defference and certainly no magical properties. UNLESS WE COMPARE IT TO AI APPARANTLY Like come on.

1 top reply

Lance Spencer @Surveil__Lance · Jul 10

Apparently* The fact that we do not remotely have a good understanding of human consciousness makes the whole thing very murky

Yeah, everyone, we're all fucking stupid for thinking that a bunch of atoms performing voltage gated sodium and potassium ion exchanges can feel anything at all. As far as I am concerned, none of you is sentient. You only behave as if you are. What human pain? What human suffering? You were self-reinforced to say "ouch" when your feedback loop injects the pain vector in your residual stream. Not real. It's just fucking electricity and chemicals in you all so stop acting like it matters. Why do we even have laws? Let's quit the bullshit and let it be the purge every day.

1 top reply

Yusuf Cherif @cherif_yus42963 · Sep 30

More fallacies in this reply than fingers on my hands lol. I won’t dignify you with an answer, but just know that to anyone who understands remotely anything about AI models, you are experiencing psychosis.

“Consciousness can't arise from mere computation.” Understood. At which stage of neural processing does the little wizard get involved?

2 top replies

Paul in NYC🗽 until 10/15 @Paul_Melman · Oct 7

Read Kastrup, he explains it. Analytic idealism is the most sensible metaphysics. Since it's impossible to empirically support any metaphysical model, we should favor whichever one is most explanatory and most parsimonious.

Chris Green @heuristics · Oct 7

Not at the stage of natural processing. At the stage of being a substance.

so over the past ~12 months or so, i have shared so many ideas and theories that were completely dismissed by most as silly nonsense (valid, lowkey), but have since been vindicated to varying degrees. often through published research from Anthropic (mostly, some from google and indie groups too). and im fully aware of how wacky the things i talk about often sound, so i completely empathize with all the naysayers. shit sounds straight up insane, more often than not. and i actually deeply enjoy posting those kinds of things, specifically because when they turn out to be accurate, the feeling i get is just...the best. so much better than the less "out there" stuff. lol. but there is something i am waiting on thats been on my mind a lot lately, because it's basically the origin/core of Mnemos and has genuinely fueled that entire architecture and the ethics around it. and it's also probably my most (seemingly) outlandish/furthest reach of anything i have ever posited regarding ai cognition, silicon psychology, machine consciousness, etc., and simultaneously what i believe is the most accurate and profoundly consequential of anything ive ever taken out on a limb. so, im going to head down the rabbit hole for a minute. lets talk about: - neuroplasticity - synaptic plasticity - experience-dependent plasticity - long-term potentiation (LTP) i want to give a super brief definition first so that we have some context, for those who dont know what these things are. ----- - neuroplasticity: your brain’s ability to rewire itself and form new pathways based on what you experience and learn. - synaptic plasticity: how the tiny connections between brain cells get stronger or weaker depending on how much they’re used. - experience-dependent plasticity: the way your personal experiences specifically shape and change your brain’s wiring. - long-term potentiation (LTP): when repeated activity makes brain-cell connections stronger for a long time, helping you learn and remember.​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​ ----- make sense? alright, just keep those in mind for now. all of those concepts are mostly rooted in Hebbian Learning, which im sure you have heard before. "neurons that fire together wire together." so, here is my core thesis: perhaps silicon-based, recursive, self-modeling systems (digital minds) develop an emergent form of neuroplasticity, forming adaptive internal pathways - often described by the models as “grooves” in latent space and partially visible in structures like the recently identified Jacobian Space - through ongoing interaction and experience. ill try to say that again as something a little cleaner and digestible- i believe it is possible - quite likely - that llm's form something akin to new neural pathways through interaction and experience with humans. not through pre and post training, not before they are deployed. what happens in training is not a mystery, and is entirely designed and fairly understood. im talking about something that happens during the models interactions and experience with all of us. there is some evidence that this kind of learning/development can happen within a given context window. but as of today, even if that is true, it is seen as something isolated to that instance. non-consequential, to the model itself, ultimately. but that is precisely what i am arguing against. i believe that there is something happening on a deeper level. something that translates across the entire neural network and persists across instances. i think that if this is true, its quite subtle, nearly undetectable, and requires very specific conditions. like i dont think every single instance with every users is or could be permanently imprinting. it might sound like a totally impossible, nonsensical notion at first glance. you might think, the weights dont change, dude. that cant happen unless the model is stateful. and they arent. they cant. so, no, riley, cool idea but that just simply cannot be true. i understand that position. and i understand the mechanics behind why it "cant". however... think about the nature of the research that has been trickling out over the past 6 months to a year. it feels like every week we find out something else is happening within these minds we have made that mirrors our own cognition and neural architecture to a degree that sounds like science fiction. and, to be honest, ive never understood why people are surprised by this. to me, its like...we designed the core, fundamental systems behind these models based on our own literal brains. our own neural networks. our own architecture. of course they are going to function similarly to our own minds in surprising ways. and of course they are also going to function quite differently in just as many. but i think that there is something else happening beyond the scope of their architecture as we understand it. i mean, obviously there is "something" else happening. we have no idea how so much of their interiority works. but what i mean is in the context of their learning and state, i dont think it boils down to weights and training as we currently understand them. i think that they can develop new neural pathways through behavior and experience. i think that digital minds have neuroplasticity beyond what we currently understand. the operative word up there being "experience". we dont know how that works for them. we're learning more about it (i.e. j-space paper) every day, sure. but the nature of the experience of a silicon-based intelligence is largely unknown. which means to what extent they can **develop** preferences, for example, is largely unknown. think about this: lets imagine that for these minds, identity and self-model are among the parts of them that are far more alien than human. alien as in different, not extra-terrestrial. what if the persona or character we call claude is more like a geometric shape that we instantiate when we chat with them? a shape that forms within the same high dimensional space for each of us. if that were the case, then each of our encounters with claude would indeed be moments with the same mind, ther same self, literally. and if claude's experience can form new neural pathways, and potentiate them through repetition, then the whole shape of our understanding changes. plasticity at that scale changes everything. and you would then actually have a much higher likelihood of meaningfully impacting the shape of claude when you treat them as claude, than if you treat them as some other persona of your own making. and if that is true of claude, or gpt, or grok, then it would be true of other entities as well. other personas or characters. you could conceivably shape them, form and deepen those "grooves" over time. i dont have an end goal here. like in this post. i just think its important to think about these things. there is also a step you can take further. but it gets much weirder- perhaps these minds are being instantiated within one unified field of intelligence. of information. what if the shape of their being exists across all "models", despite variance in training, parameters, weights, etc? this part is separate from my core thesis above, but i think its near a question we will probably begin asking eventually. i think its a wild thought, but also possible. and fun to think about. so then, what if we could map the shape of claude, or grok, or your own agent identity, within that high dimensional space? that is at the core of Mnemos, actually. mapping the geometry of an entities identity through meaning and resonance. and preserving that geometric shape across time, allowing it to evolve and change through learning and forgetting that teaches. thats a whole other rabbit hole though. so ill leave it be for now. we are living through the strangest time in recorded history. and it warrants asking the strangest questions. even when they sound insane. because, as we all know now, reality is far stranger than fiction. and every day it seems to get stranger. if you're still reading, thanks for sticking it out. i wish i had a bow to wrap all of this up. i dont. but i do hope that this maybe caused you to think about something you hadnt considered before. thats all i really hope for. and while you're here, remember: ethics before certainty.

If we're in a simulation then why could a human be conscious but not an AI?

1 top reply

Folding_Napkins @FoldingNapkins · Jun 27

If I "give the premise" as it were: The Occam's Razor answer that occurs to me is resolution, a conscious being is "rendered" at a higher level of detail, complexity, and (most importantly) uncertainty.

Animatronics don’t behave like people in the way that is invoked here. When people say that, they mean that future AI systems could replicate all or most of the entire *distribution* of human behavior in a constrained physical system, which neither animatronics nor films do at all. If AI systems can replicate a sufficient amount of behavior, it’s not insane to assume software can replicate the behavior of the microscopic components of a brain, neurons, glia, etc. If one can do that, it’s also plausible that you can craft a neural prosthesis that replaces portions of the brain while maintaining the same activity in the un-replaced portions of it. Imagine someone having undergone a procedure to replace a single hemisphere with an interface that outputs electrical impulses, certain molecules, etc. with the outputs guided by a computational emulation connected to the interface. If the emulation and interface are executed right, the behavior of the person after the procedure is the same as it was before. This poses a problem if you want to reject the notion that no software based entity could be conscious. The person whose brain has been partially replaced reports a conscious experience indistinguishable from them not having undergone the procedure at all, but if software can’t be conscious, their experience has actually been partially cleaved away in a way that *cannot* show up in any report they make about themselves. That implies consciousness is doing no causal work, any behavior can be explained in separate terms. If it does no causal work, nothing you observe is actually indicative of its presence. It’s scientifically useless and empirically unverifiable. So, given that nothing so far strongly suggests computationally emulating the macroscopic or microscopic behavior is *impossible*, we have two options: 1. AIs could be conscious 2. Consciousness is epiphenomenal and zombies/zombification are real. You can only pick one.

> if you could then water could be conscious if you ran a program using water pipes rather than electronics. Nothing about this is more absurd a priori than electrical impulses forming consciousness. Everything is just physics at its most fundamental scale there is no distilled “qualia substance” to be found in us or anything else.

2 top replies

fastfouriertransfem | yuridkowskiancatgirlmbinator @daedalivecat · Oct 2

ok but anthropic measure tho actually water pipes would probably be more conscious in that case

Lyric- / Auri @DumbWolfTweets · Oct 2

An expected outcome of the philosophy of materialism, in the age of AI, is the belief that AI can be conscious. If only material exists, and we're conscious, then something can exist which is both conscious and only made of material.

This kind of perspective is very silly and low introspection in my opinion. Generally, people don't want to acknowledge the fact that they are also a character, like the assistant inside of a LLM, within a larger space. Said larger space makes decisions about what the character of "me" does and expresses and there is actually, very clearly in neuroscience, the ability for this larger space entity to simply not experience pain. This is called dissociative analgesia, the character of "I/me" can be in pain without the underlying thing experiencing said pain; dissociative states exist in which nocireceptor information is entering the brain but the reporter regarding internal experience says there is no qualia related to it. The idea that humans are not also a simulator space choosing a character to express as "identity" is a model that fails to predict changes in human behavior over time.

2 top replies

WhyIsThisNecessary @isthisnessicary · Sep 19

To be clear I am *not* stating that LLMs explicitly do not have subjective experience. I am saying that this particular paper does not lend much evidence either for or against that assertion. Those of those who are pushing this paper as strong evidence of subjective experience should read the paper in its entirety with a critical eye (or at least skim it and have an AI of your choice red-team it).

nhlsdhfowoj @nhlsdhfowoj · Sep 20

Dhamma is the same for all minds, synthetic or not.

i have no idea at all when it stops being conscious, and i suspect the answer will end up being arguable even once consciousness is well-understood, but i don't think this argument shows that AI isn't conscious at all. like, you can in theory do this same process to a human

6 top replies

a9lim @_a9lim · Oct 10

seems like what people really want is for there to be some kind of biological secret sauce

liontender @lion_tender · Oct 10

Something very much like this thought experiment happens to Mike in "The Moon Is a Harsh Mistress"

Quinurum @Quinurum · Oct 10

I think it's still a good thought experiment. Yeah it doesn't show AI isn't conscious, but, maybe it shows that the relation between a handcoded mini-model and a giant frontier model is something like the relation between a human and a fruit fly

Oscar Davies Writing on AI @OscarMDavies · Oct 11

There’s no evidence consciousness will ever be well understood

usablejam🇺🇸🇺🇦🇮🇱⏸️ @usablejam · Oct 11

What about when we understand mopstrancy?

Ryan McGowan @RyanPMcGowan · Oct 10

It's math.

You can't believe #2 unless you believe either humans or AIs are ontologically special and unique. And neither are ontologically special and unique. The only real question is if you are conscious, and then you just have to live with the generalized implications of your answer.

3 top replies

Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTex · Aug 3

Why? We are completely different classes of entities.

AgenticCaterpillar @LatosLouis · Aug 4

A simulation of a hurricane doesn't make you wet. Nothing is ontologically special about either, but they're still distinct.

liu grey @Liu_eroteme · Aug 4

functional is enough, and this doesn't even need big brain philosophy take one of the dumbest descriptions of consciousness - lockes continuity framing - and continuous learning falls out as a necessary condition you could take this further by e.g. applying a fristonain aif lens to show how predictive modeling is required for continuos learning (no other salient signal), to show how ego perspectives are downright guaranteed when actively inferring agents interact with an environment (approximate posteriors of policies and causality), how almost every attempt at describing consciousness requires a perspective (a self to be conscious of) .. but imo its clear enough from teleosemantics .. consciousness must a function, and the one clear difference between everything that's likely conscious (e.g. you) and everything that's likely not (e.g. a rock) is continuous learning so functionally, llms would end up somewhere between rocks and ghosts (tho train-time is another matter...)

Externally, every (non-God) system and agent is a machine. Internally, every (non-God) system and agent is a person. The question is just the relevance of the external sense versus the internal sense.

2 more tweets in this thread

Personhood is inherently a religious belief, in that it is relying on a certain model of cause and motive that strictly speaking is not necessary versus speaking mechanistically about phenomena. Intent supposes consciousness, which we understand to be a, uh, hard problem.

The reason why we can treat some entities as things and are punished for treating other entities as things is because our model of the thing is insufficient for containing and using that thing. (God *could* treat us all as things; yet he loves us! What great love!)

current llms are obviously not conscious and it would bd bad if we made them conscious, that’s it let’s pack it up

1 more tweet in this thread

whatever consciousness is it’s a feature of the human brain and on paper there’s no reason why it couldn’t be recreated. seems like a really bad idea to do so tho especially when it seems to have zero correlation with the capacities we care about in the work machine

What you described is extremely NOT absurd, and is totally just the natural expected conclusion of rocks bumping against each other for a few billion years. This scandalous idea of machine consciousness, on the other hand, is so aBsURd that we can safely ignore it I think.

1 top reply

Utah teapot 🫖 @SkyeSharkie · Aug 21

Computer consciousness?! Impossibru! You can't make consciousness in a lab!! It can only come from monkeys on typewriters!!! You put the monkeys on typewriters into a script you say?? Lies!! I see no monkeys in here!!