Entanglement cannot be used to send signals faster than light, and when “teleportation” was named, the model the physicists had in mind was Star Trek style teleportation, where you scan the original copy in a way that is destructive to it, transmit that information elsewhere, and then reconstruct it. That transmission step is still through a classical information channel so it cannot be faster than light. It was not named that way after magical fantasy teleportation where something just disappears from one location and instantly appears in another. It was an analogy to how the algorithm works: quantum mechanics forbids cloning a state, but you can semi-get around this by cloning it in a destructive way, so that you never have two systems, at the same time, holding the state you are trying to copy.

It can’t be faster than the speed of light and radio already travels at the speed of light.

Quantum internet does not allow instantaneous communication. That would violate the no-communication theorem. It’s physically impossible.

I believe ECC is also targetable by quantum computers in theory. Post-quantum cryptography is lattice-based ciphers like Kyber.

I’d disagree about the blockchain. It doesn’t actually provide anything useful and massively wastes resources, because it requires a ton of energy doing useless calculations for a fake token that you just gamble with on the internet. Countries that ban it are immediately placed in an economic advantage because they free up tons of resources to actually go into producing real physical things and not meme coins, which is a big reason why China has largely banned Bitcoin, viewing it as a major burden on their energy infrastructure while contributing nothing real to the economy.

There are a lot of libertarian weirdos in tech who try to push certain technologies solely for ideological reasons. They will tell you how ideological superior the blockchain is for decentralizing things and thus not making you dependent on Uncle Sam. But they don’t actually provide any utility to that other than ideology.

The only non-ideological explanation I have ever received is that the blockchain is good because it makes it easier to break the law if the law is unjust. If for example you want to pay someone for something that is wrongfully made illegal to begin with, you can pay them in Bitcoin and get away with it easier.

That to me, however, is a bit of a bizarre argument. Saying that X should be legal because X can be used to break the law makes little coherent sense. Obviously, the law at that point is the problem and is what should be changed. If you have the power to influence what is legal (and thus to actually act upon the question of whether or not something should be legal), then obviously we should choose to get rid of the unjust law, not to legalize Bitcoin. If we do not have the power to influence what is legal, then the conversation is moot anyways.

NFTs were even worse, because nobody has ever made a non-ideological argument for NFTs. They are always justified based on some weird ideological belief about the sanctity of some nebulous “private property” registered on the blockchain. Laughably, blockchain technologies do not have the storage capacity to practically hold entire images, so they just held links to the images, and so many now lead to nowhere because the original servers they were registered with are down.

People often hate me for the fact that I often defend the utility and potential utility of AI and quantum technologies (even if I do agree that companies hype it and push out slop, that does not prove the technologies themselves are entirely a scam). But I have always been a critic of blockchain and the “metaverse,” because those were hypecycles which nobody could actually give me a single coherent explanation of how these things might improve human society at all in any material way.

…which is something I actually consider. It does indeed actually bother me that very few companies have actually adopted post-quantum cryptography yet. What is even the point of my VPN, for example, if there is a potential that everything is cracked 40 years down the line? NIST has already basically approved the standards. It should be an option for sensitive things, like anything to do with banking, data storage, and VPN.

Object permanence is technically an axiom. The idea that things exist even when we aren’t observing them.

If things do not exist exist when you’re not looking at them, well, you are a thing, and so you do not exist when I am not looking at you. Denying object permanence inevitably collapses into solipsism.

There’s also a problem with terms, particularly related to quantum mechanics. It uses the term observer. To a layman, that’s a person watching. To a scientist its any collection of atoms/fundamental particles that can cause the quantum waveform to collapse.

This is patently false. Observer in quantum mechanics absolutely just refers to an experimenter watching. What you are repeating is a common myth and does not accurately reflect the dominant views among physicists in academia.

What you are talking about is a physical collapse theory. A physical collapse theory is impossible to be perfectly reconciled with the mathematics of quantum mechanics. You can reconcile it in a limiting case, and potentially all cases we can actually practical observe, but not in all possible conceivable cases, due to physical collapse breaking the linearity of the theory.

Physical collapse theories are thus not even quantum mechanics but brand new speculative physical models. Some physicists have proposed such models, like GRW theory or the Diosi-Penrose model, but these are alternative speculative models which lack broad support.

The dominant paradigm is the Copenhagen interpretation. The Copenhagen interpretation rejects that the collapse is a physical event that happens at all, but treats it as a subjective event. The collapse occurs in the mathematics, not in physical reality, as a means of the observer book-keeping the information they have on the system.

The Copenhagen interpretation absolutely does not posit that observation is “any collection of atoms/fundamental particles that can cause the quantum waveform to collapse,” as this necessarily leads to the following question, “What exactly qualifies some physical systems to play the role of ‘measurer’? Was the wavefunction of the world waiting to jump for thousands of millions of years until a single-celled living creature appeared? Or did it have to wait a little longer, for some better qualified system…with a PhD?”

The way you frame it naturally leads one to ask what rigorous mathematical definition actually qualifies a collection of atoms/fundamental particles to be able to cause the quantum waveform to (physically) collapse, but quantum theory alone does not tell you that, so you would have to go beyond it and introduce a new model. Copenhagen does not do that. It does not posit what you are claiming at all.

quantum mechanics being the oddball

Quantum mechanics is not an oddball at all. In any statistical theory, you track only the observer’s knowledge of the state of the system, and thus do not actually include its definite state in the mathematics. But nobody interprets that to mean its definite state does not still exist in the real world, except in the case for quantum mechanics, when people insist we should suddenly do a 180 u-turn and interpret the statistics entirely differently.

The physicist Dmitry Blokhintsev published a paper back in the 1950s which already pointed this out, that the confusion around quantum mechanics all stems from insisting upon treating it as a non-statistical theory. Statistics deal with the observer’s subjective knowledge, and so naturally statistical states vary based on an observer’s subjective knowledge. If you insist that the statistical state is a physical state (and thus not “statistical” at all), then you end up with a picture whereby objective reality can change depending upon an observer’s subjective knowledge, which leads entirely to a breakdown of any coherent notion of objective reality, as demonstrated in Eugene Wigner’s famous “friend” paradox.

The reality is that no physicist has ever published a paper in the peer-reviewed literature actually establishing that quantum mechanics demands you believe that the quantum state is a physical state. This is just a very very popular belief. We should not treat the “academic consensus” as just “what most physicists happen to believe.” If we are living in a country that is mostly Christian, one might find most physicists identify as Christian, but that would not make Christianity the “academic concensus.”

The “academic consensus” should be established through a meta-analysis of the preponderance of findings in actual peer-reviewed, academic journals. Not just what physicists personally believe, but what they have actually published. Yet, no physicist has ever published a paper establishing this belief, despite its popularity.

Only one major paper I’m aware of even attempted to do so, that being the famous “PBR theorem.” But if you read that paper, even the paper itself acknowledges it is not definitive, because their proof depends upon you believing that the way the particle responds to an interaction only depends upon its present state, a property called Markovianity. This assumption is necessary because their proof requires that the particles are prepared independently in the past then come together to interact in the present, with no information stored regarding their preparation existing in the present, and thus their behavior must be independent of their preparation. But if the outcome of the interaction has dependence upon the past, then you can trivially explain the same results, because the information would not need to exist in the present to influence the outcome of the present interaction.

Indeed, the physicist Jacob Barandes mathematically proved that quantum mechanics is mathematically equivalent to a statistical theory that is non-Markovian, Hence, the “non-classicality” of quantum mechanics can be interpreted as not arising from particles existing in “multiple places at once,” as if the quantum state is a physical state, but merely that when particles interact, the outcome of the interaction simply takes into account, on the level of the nomology, their statistical states into the past.

There is no definitive reason to take the quantum state as a physical state, and so there is no conflict or confusion between quantum theory and object permanence. It is just a very very popular belief among physicists. Physics is not entirely math and empirical evidence. It is also ideology.

This was something pointed out heavily by the physicist John Bell. In his paper “On the Impossible Pilot Wave,” he points out that the physicist David Bohm had already proposed a model mathematically equivalent to standard quantum mechanics and made all the same predictions, yet did not have these bizarre features, and so belief in those bizarre features is ultimately an ideological choice and not demanded by the empirical evidence or the mathematical model.

Indeed, Bell also published a paper “How to Teach Special Relativity” where he points out that the mathematics and empirical predictions of special relativity is actually perfectly compatible with a universe with absolute space and time, where the relativity of measurements of rods and clocks is an emergent and not fundamental feature, and so belief that space and time are really relative is ultimately an ideological position and not demanded by the mathematics or empirical evidence.

Too many physicists tend to struggle to separate the ideology from the mathematics and empirical evidence, and constantly conflate the first with the latter two, as if you must believe in their particular ideological viewpoint or else you’re a crazy person, a “crackpot,” who is denying the mathematics and empirical evidence. But it just does not logically follow. Nothing in the linear algebra of quantum mechanics demands you actually believe particles exist in multiple states at once. It is a perfectly consistent position to believe that particles always have a definite state, while also believing that the mathematical body of quantum mechanics is completely accurate, because nothing in the mathematics itself demands you take on a particular ideological position.

That is a choice you make outside of the mathematics. It is a particular ideological choice, imposed on top of the mathematics of quantum mechanics, which leads to a conflict with object permanence. It is not the mathematics of quantum mechanics itself which conflicts with it at all.

[I]n 1952 I saw the impossible done. It was in papers by David Bohm. Bohm showed explicitly how[…]the subjectivity of the orthodox version, the necessary reference to the “observer,” could be eliminated. Moreover, the essential idea was one that had been advanced already by de Broglie (in 1927, in his “pilot wave” picture. But why then had Born not told me of this “pilot wave?” If only to point out what was wrong with it? Why did von Neumann not consider it? More extraordinarily, why did people go on producing “impossibility”proofs, after 1952, and as recently as 1978? When even Pauli, Rosenfeld, and Heisenberg, could produce no more devastating criticism of Bohm’s version than to brand it as “metaphysical” and “ideological?” Why is the pilot wave picture ignored in text books? Should it not be taught, not as the only way, but as an antidote to the prevailing complacency? To show that vagueness, subjectivity, and indeterminism, are not forced on us by experimental facts, but by deliberate theoretical choice?

— John Bell

This is sadly pseudoscience, that only gets talked about because one smart guy endorsed it, but hardly anyone in academia actually takes it seriously. What you are talking about is called Orch OR, but Orch OR is filled with problems.

One issue is that Orch OR makes a lot of claims that are not obviously connected to one another. The reason this is is an issue is because, while they call the theory “falsifiable” because it makes testable predictions, even if the predictions are tested and it is found to make the correct prediction, that wouldn’t actually even validate the theory because there is no way to actually logically or mathematically connect that experimental validation to all of its postulates.

Orch OR has some rather bizarre premises: (1) Humans can consciously choose to believe things that cannot be mathematically proven, therefore, human consciousness must not be computable, (2) you cannot compute the outcome of a quantum experiment ahead of time, therefore there must be an physical collapse that is fundamentally not computable, (3) since both are not computable, they must be the same thing: physical collapse = consciousness, (4) therefore we should look for evidence that the brain is a quantum computer.

Argument #1 really makes no sense. Humans believing silly things doesn’t prove human decisions aren’t computable. Just look at AI. It is obviously computable and hallucinates nonsense all the time. This dubious argument means that #3 doesn’t follow; there is no good reason to think consciousness and “collapse” are related.

Argument #2 is problematic because physical collapse models are not compatible with special relativity or the statistical predictions of non-relativistic quantum mechanics, and so they cannot reproduce the predictions of quantum field theory in all cases, and so they aren’t particularly popular among physicists, and of course there is no evidence for them. Most physicists see the “collapse” as an epistemic, not a physical, event.

Orch OR also arbitrarily insists on using the Diósi–Penrose model specifically, even though there have been multiple models of physical collapse proposed, such as GRW. There is no obvious reason to use this model specifically, it isn’t connected to any of the premises in the theory. Luckily, argument #2 does present falsifiable claims, but because #2 is not logically connected to the rest of the arguments, even if we do prove that the Diósi–Penrose model is correct, it doesn’t follow that #1, #3, or #4 are correct. We would just know there are physical collapses, but nothing else in the theory would follow.

The only other argument that propose something falsifiable is #4, but again, #4 is not connected to #1, #3, or #4. Even if you desperately searched around frantically for any evidence that the brain is a quantum computer, and found some, that would just be your conclusion: the brain is a quantum computer. From that, #1, #2, and #3 do not then follow. It would just be an isolated fact in and of itself, an interesting discovery but wouldn’t validate the theory. I mean, we already have quantum computers, if you think collapse = consciousness, then you would have to already think quantum computers are conscious. A bizarre conclusion.

In fact, only #2 and #4 are falsifiable, but even if both #2 and #4 are validated, it doesn’t get you to #1 or #3, so the theory as a whole still would remain unvalidated. It is ultimately an unfalsifiable theory but with falsifiable subcomponents. The advocates insist we should focus on the subcomponents as proof it’s a scientific theory because “it’s falsifiable,” but the theory as a whole simply is not falsifiable.

Also, microtubules are structural. They don’t play any role in information processing in the brain, just in binding cells together, but it’s not just brain cells, microtubules are something found throughout your body in all kinds of cells. There is no reason to think at all they play any role in computations in the brain. The only reason you see interest in them from the Orch OR “crowd” (it’s like, what, 2 people who just so happen to be very loud?) is because they’re desperate for anything that vaguely looks like quantum effects in the brain, and so far microtubules are the only things that seem quantum effects may play some role, but this role is again structural. There is no reason to believe it plays any role in information processing or cognition.

I think a lot of proponents of objective collapse would pick a bone with that, haha, although it’s really just semantics. They are proposing extra dynamics that we don’t understand and can’t yet measure.

Any actual physicist would agree objective collapse has to modify the dynamics, because it’s unavoidable when you introduce an objective collapse model and actually look at the mathematics. No one in the physics community would debate GRW or the Diósi–Penrose model technically makes different predictions, however, and in fact the people who have proposed these models often view this as a positive thing since it makes it testable rather than just philosophy.

How the two theories would deviate would depend upon your specific objective collapse model, because they place thresholds in different locations. For GRW, it is based on a stochastic process that increases with probability over time, rather than a sharp threshold, but you still should see statistical deviations between its predictions and quantum mechanics if you can maintain a coherent quantum state for a large amount of time. The DP model has something to do with gravity, which I do not know enough to understand it, but I think the rough idea is if you have sufficient mass/energy in a particular locality it will cause a “collapse,” and so if you can conduct an experiment where that threshold of mass/energy is met, traditional quantum theory would predict the system could still be coherent whereas the DP model would reject that, and so you’d inherently end up with deviations in the predictions.

What’s the definition of interact here?

An interaction is a local event where two systems become correlated with one another as a result of the event.

“The physical process during which O measures the quantity q of the system S implies a physical interaction between O and S. In the process of this interaction, the state of O changes…A quantum description of the state of a system S exists only if some system O (considered as an observer) is actually ‘describing’ S, or, more precisely, has interacted with S…It is possible to compare different views, but the process of comparison is always a physical interaction, and all physical interactions are quantum mechanical in nature.”

The term “observer” is used very broadly in RQM and can apply to even a single particle. It is whatever physical system you are choosing as the basis of a coordinate system to describe other systems in relation to.

Does it have an arbitrary cutoff like in objective collapse?

It has a cutoff but not an arbitrary cutoff. The cutoff is in relation to whatever system participates in an interaction. If you have a system in a superposition of states, and you interact with it, then from your perspective, it is cutoff, because the system now has definite, real values in relation to you. But it does not necessarily have definite, real values in relation to some other isolated system that didn’t interact at all.

You can make a non-separable state as big as you want.

Only in relation to things not participating in the interaction. The moment something enters into participation, the states become separable. Two entangled particles are nonseparable up until you interact with them. Although, even for the two entangled particles, from their “perspectives” on each other, they are separable. It is only nonseparable from the perspective of yourself who has not interacted with them yet. If you interact with them, an additional observer who has not interacted with you or the three particles yet may still describe all three of you in a nonseparble entangled state, up until they interact with it themselves.

This is also the first I’ve heard anything about time-symmetric interpretations. That sounds pretty fascinating. Does it not have experimenter “free will”, or do they sidestep the no-go theorems some other way?

It violates the “free will” assumption because there is no physical possibility of setting up an experiment where the measurement settings cannot potentially influence the system if you take both the time-forwards and time-reverse evolution seriously. We tend to think because we place the measurement device after the initial preparation and that causality only flows in a single time direction, then it’s possible for the initial preparation to affect the measurement device but impossible for the measurement device to affect the initial preparation. But this reasoning doesn’t hold if you drop the postulate of the arrow of time, because in the time-reverse, the measurement interaction is the first interaction in the causal chain and the initial preparation is the second.

Indeed, every single Bell test, if you look at its time-reverse, is unambiguously local and easy to explain classically, because all the final measurements are brought to a single locality, so in the time-reverse, all the information needed to explain the experiment begins in a single locality and evolves towards the initial preparation. Bell tests only appear nonlocal in the time-forwards evolution, and if you discount the time-reverse as having any sort of physical reality, it then forces you to conclude it must either be nonlocal or a real state for the particles independent of observation cannot exist. But if you drop the postulate of the arrow of time, this conclusion no longer follows, although you do end up with genuine retrocausality (as opposed to superdeterminism which only gives you pseudo-retrocausality), so it’s not like it gives you a classical system.

So saying we stick with objective collapse or multiple worlds, what I mean is, could you define a non-Lipschitz continuous potential well (for example) that leads to multiple solutions to a wave equation given the same boundary?

I don’t know, but that is a very interesting question. If you figure it out, I would be interested in the answer.

Many of the interpretations of quantum mechanics are nondeterministic.

1. Relational quantum mechanics interprets particles as taking on discrete states at random whenever they interact with another particle, but only in relation to what they interact with and not in relation to anything else. That means particles don’t have absolute properties, like, if you measure its spin to be +1/2, this is not an absolute property, but a property that exists only relative to you/your measuring device. Each interaction leads to particles taking on definite states randomly according to the statistics predicted by quantum theory, but only in relation to things participating in those interactions.

2. Time-symmetric interpretations explain violations of Bell inequalities through rejecting a fundamental arrow of time. Without it, there’s no reason to evolve the state vector in a single time-direction. It thus adopts the Two-State Vector Formalism which evolves it in both directions simultaneously. When you do this, you find it places enough constructs on the particles give you absolutely deterministic values called weak values, but these weak values are not what you directly measure. What you directly measure are the “strong” values. You can interpret it such that every time two particles interact, they take on “strong” values randomly according to a rule called the Aharonov-Bergmann-Lebowitz rule. This makes time-symmetric interpretations local realist but not local deterministic, as it can explain violations of Bell inequalities through local information stored in the particles, but that local information still only statistically determines what you observe.

3. Objective collapse models are not really interpretations but new models because they can’t universally reproduce the mathematics of quantum theory, but some serious physicists have explored them as possibilities and they are also fundamentally random. You assume that particles literally spread out as waves until some threshold is met then they collapse down randomly into classical particles. The reason this can’t reproduce the mathematics of quantum theory is because this implies quantum effects cannot be scaled beyond whatever that threshold is, but no such threshold exists in traditional quantum mechanics, so such a theory must necessarily deviate from its predictions at that threshold. However, it is very hard to scale quantum effects to large scales, so if you place the threshold high enough, you can’t practically distinguish it from traditional quantum mechanics.

don’t mind me i have autism

Many worlds theories are rather strange.

If you take quantum theory at face value without trying to modifying it in any way, then you unequivocally run into the conclusion that ψ is contextual, that is to say, what ψ you assign to a system depends upon your measurement context, your “perspective” so to speak.

This is where the “Wigner’s friend paradox” arises. It’s not really a “paradox” as it really just shows ψ is contextual. If Wigner and his friend place a particle in a superposition of states, his friend says he will measure it, and then Wigner steps out of the room for a moment when he is measuring it, from the friend’s perspective he would reduce ψ to an eigenstate, whereas in Wigner’s perspective ψ would instead remain in a superposition of states but one entangled with the measuring device.

This isn’t really a contradiction because in density matrix form Wigner can apply a perspective transformation and confirm that his friend would indeed perceive an eigenstate with certain probabilities for which one they would perceive given by the Born rule, but it does illustrate the contextual nature of quantum theory.

If you just stop there, you inevitably fall into relational quantum mechanics. Relational quantum mechanics just accepts the contextual nature of ψ and tries to make sense of it within the mathematics itself. Most other “interpretations” really aren’t even interpretations but sort of try to run away from the conclusion, such as significantly modifying the mathematics and even statistical predictions in order to introduce objective collapse or hidden variables in order to either get rid of a contextual ψ or get rid of ψ as something fundamental altogether.

Many Worlds is still technically along these lines because it does add new mathematics explicitly for the purpose of avoiding the conclusion of irreducible contextuality, although it is the most subtle modification and still reproduces the same statistical predictions. If we go back to the Wigner’s friend scenario, Wigner’s friend reduced ψ relative to his own context, but Wigner, who was isolated from the friend and the particle, did not reduce ψ by instead described them as entangled.

So, any time you measure something, you can imagine introducing a third-party that isn’t physically interacting with you or the system, and from that third party’s perspective you would be in an entangled superposition of states. But what about the physical status of the third party themselves? You could introduce a fourth party that would see the system and the third party in an entangled superposition of states. But what about the fourth party? You could introduce a fifth party… so on and so forth.

You have an infinite regress until, at some how (somehow), you end up with Ψ, which is a sort of “view from nowhere,” a perspective that contains every physical object, is isolated from all those physical objects, and is itself not a physical object, so it can contain everything. So from the perspective of this big Ψ, everything always remains in a superposition of states forever, and all the little ψ are only contextual because they are like perspectival slices within Ψ.

You cannot derive Ψ mathematically because there is no way to get from inherently contextual ψ to this preferred nonphysical perspective Ψ, so you cannot know its mathematical properties. There is also no way to define it, because each ψ is an element of Hilbert space and Hilbert space is a constructed space, unlike background spaces like Minkowski space. The latter are defined independently of the objects the contain, whereas the former are defined in terms of the objects they contain. That means for two different physical systems, you will have two different ψ that will be assigned to two different Hilbert spaces. The issue is that you cannot define the Hilbert space that Ψ is part of because it would require knowing everything in the universe.

Hence, Ψ cannot be derived nor defined, so it can only be vaguely postulated, and its mathematical properties also have to be postulated as you cannot derive them from anything. It is just postulated to be this privileged cosmic perspective, a sort of godlike ethereal “view from nowhere,” and then it is postulated to have the same mathematical properties as ψ but that all ψ are also postulated to be subsystems of Ψ. You can then write things down like how a partial trace on Ψ can give you information about any perspective of its subsystems, but only because it was defined to have those properties. It is true by definition.

In a RQM perspective it just takes quantum theory at face value without bothering to introduce a Ψ and just accepts that ψ is contextual. Talking about a non-contextual (absolute) ψ makes about as much sense as talking about non-contextual (absolute) velocity, and talking about a privileged perspective in QM makes about as much sense as talking about a privileged perspective in special relativity. For some reason, people are perfectly happy with accepting the contextual nature of special relativity, but they struggle real hard with the contextual nature of quantum theory, and feel the need to modify it, to the point of convincing themselves that there is a multiverse in order to escape it.

That’s literally China’s policies. The problem is most westerners are lied to about China’s model and it is just painted it as if Deng Xiaoping was an uber capitalist lover and turned China into a free market economy and that was the end of history.

The reality is that Deng Xiaoping was a classical Marxist so he wanted China to follow the development path of classical Marxism (grasping the large, letting go of the small) and not the revision of Marxism by Stalin (nationalizing everything), because Marxian theory is about formulating a scientific theory of socioeconomic development, so if they want to develop as rapidly as possible they needed to adhere more closely to Marxian economics.

Deng also knew the people would revolt if the country remained poor for very long, so they should hyper-focus on economic development first-of-foremost at all costs for a short period of time. Such a hyper-focus on development he had foresight to predict would lead to a lot of problems: environmental degradation, rising wealth inequality, etc. So he argued that this should be a two-step development model. There would be an initial stage of rapid development, followed by a second stage of shifting to a model that has more of a focus on high quality development to tackle the problems of the previous stage once they’re a lot wealthier.

The first stage went from Deng Xiaoping to Jiang Zemin, and then they announced they were entering the second phase under Hu Jintao and this has carried onto the Xi Jinping administration. Western media decried Xi an “abandonment of Deng” because western media is just pure propaganda when in reality this was Deng’s vision. China has switched to a model that no longer prioritizes rapid growth but prioritizes high quality growth.

One of the policies for this period has been to tackle the wealth inequality that has arisen during the first period. They have done this through various methods but one major one is huge poverty alleviation initiatives which the wealthy have been required to fund. Tencent for example “donated” an amount worth 3/4th of its whole yearly profits to government poverty alleviation initiatives. China does tax the rich but they have a system of unofficial “taxation” as well where they discretely take over a company through a combination of party cells and becoming a major shareholder with the golden share system and then make that company “donate” its profits back to the state. As a result China’s wealth inequality has been gradually falling since 2010 and they’ve become the #1 funder of green energy initiatives in the entire world.

The reason you don’t see this in western countries is because they are capitalist. Most westerners have an mindset that laws work like magic spells, you can just write down on a piece of paper whatever economic system you want and this is like casting a spell to create that system as if by magic, and so if you just craft the language perfectly to get the perfect spell then you will create the perfect system.

The Chinese understand this is not how reality works, economic systems are real physical machines that continually transform nature into goods and services for human conception, and so whatever laws you write can only meaningfully be implemented in reality if there is a physical basis for them.

The physical basis for political power ultimately rests in production relations, that is to say, ownership and control over the means of production, and thus the ability to appropriate all wealth. The wealth appropriation in countries like the USA is entirely in the hands of the capitalist class, and so they use that immense wealth, and thus political power, to capture the state and subvert it to their own interests, and thus corrupt the state to favor those very same capital interests rather than to control them.

The Chinese understand that if you want the state to remain an independent force that is not captured by the wealth appropriators, then the state must have its own material foundations. That is to say, the state must directly control its own means of production, it must have its own basis in economic production as well, so it can act as an independent economic force and not wholly dependent upon the capitalists for its material existence.

Furthermore, its economic basis must be far larger and thus more economically powerful than any other capitalist. Even if it owns some basis, if that basis is too small it would still become subverted by capitalist oligarchs. The Chinese state directly owns and controls the majority of all its largest enterprises as well as has indirect control of the majority of the minority of those large enterprises it doesn’t directly control. This makes the state itself by far the largest producer of wealth in the whole country, producing 40% of the entire GDP, no singular other enterprise in China even comes close to that.

The absolute enormous control over production allows for the state to control non-state actors and not the other way around. In a capitalist country the non-state actors, these being the wealth bourgeois class who own the large enterprises, instead captures the state and controls it for its own interests and it does not genuinely act as an independent body with its own independent interests, but only as the accumulation of the average interests of the average capitalist.

No law you write that is unfriendly to capitalists under such a system will be sustainable, and often are entirely non-enforceable, because in capitalist societies there is no material basis for them. The US is a great example of this. It’s technically illegal to do insider trading, but everyone in US Congress openly does insider trading, openly talks about it, and the records of them getting rich from insider training is pretty openly public knowledge. But nobody ever gets arrested for it because the law is not enforceable because the material basis of US society is production relations that give control of the commanding heights of the economy to the capitalist class, and so the capitalists just buy off the state for their own interests and there is no meaningfully competing power dynamic against that in US society.

China does tax the rich but they also have an additional system of “voluntary donations.” For example, Tencent “volunteered” to give up an amount that is about 3/4th worth of its yearly profits to social programs.

I say “voluntary” because it’s obviously not very voluntary. China’s government has a party cell inside of Tencent as well as a “golden share” that allows it to act as a major shareholder. It basically has control over the company. These “donations” also go directly to government programs like poverty alleviation and not to a private charity group.

On the surface, it does seem like there is a similarity. If a particle is measured over here and later over there, in quantum mechanics it doesn’t necessarily have a well-defined position in between those measurements. You might then want to liken it to a game engine where the particle is only rendered when the player is looking at it. But the difference is that to compute how the particle arrived over there when it was previously over here, in quantum mechanics, you have to actually take into account all possible paths it could have taken to reach that point.

This is something game engines do not do and actually makes quantum mechanics far more computationally expensive rather than less.

Any time you do something to the particles on Earth, the ones on the Moon are affected also

The no-communication theorem already proves that manipulating one particle in an entangled pair has no impact at al on another. The proof uses the reduced density matrices of the particles which capture both their probabilities of showing up in a particular state as well as their coherence terms which capture their ability to exhibit interference effects. No change you can make to one particle in an entangled pair can possibly lead to an alteration of the reduced density matrix of the other particle.

There is no “fundamentally” here, you are referring to some abstraction that doesn’t exist. The models are modified during the fine-tuning process, and the process trains them to learn to adopt DeepSeek R1’s reasoning technique. You are acting like there is some “essence” underlying the model which is the same between the original Qwen and this model. There isn’t. It is a hybrid and its own thing. There is no such thing as “base capability,” the model is not two separate pieces that can be judged independently. You can only evaluate the model as a whole. Your comment is just incredibly bizarre to respond to because you are referring to non-existent abstractions and not actually speaking of anything concretely real.

The model is neither Qwen nor DeepSeek R1, it is DeepSeek R1 Qwen Distill as the name says. it would be like saying it’s false advertising to say a mule is a hybrid of a donkey and a horse because the “base capabilities” is a donkey and so it has nothing to do with horses, and it’s really just a donkey at the end of the day. The statement is so bizarre I just do not even know how to address it. It is a hybrid, it’s its own distinct third thing that is a hybrid of them both. The model’s capabilities can only be judged as it exists, and its capabilities differ from Qwen and the original DeepSeek R1 as actually scored by various metrics.

Do you not know what fine-tuning is? It refers to actually adjusting the weights in the model, and it is the weights that define the model. And this fine-tuning is being done alongside DeepSeek R1, meaning it is being adjusted to take on capabilities of R1 within the model. It gains R1 capabilities at the expense of Qwen capabilities as DeepSeek R1 Qwen Distill performs better on reasoning tasks but actually not as well as baseline models on non-reasoning tasks. The weights literally have information both of Qwen and R1 within them at the same time.

Speaking of its “base capabilities” is a meaningless floating abstraction which cannot be empirically measured and doesn’t refer to anything concretely real. It only has its real concrete capabilities, not some hypothetical imagined capabilities. You accuse them of “marketing” even though it is literally free. All DeepSeek sells is compute to run models, but you can pay any company to run these distill models. They have no financial benefit for misleading people about the distill models.

You genuinely are not making any coherent sense at all, you are insisting a hybrid model which is objectively different and objectively scores and performs differently should be given the exact same name, for reasons you cannot seem to actually articulate. It clearly needs a different name, and since it was created utilizing the DeepSeek R1 model’s distillation process to fine-tune it, it seems to make sense to call it DeepSeek R1 Qwen Distill. Yet for some reason you insist this is lying and misrepresenting it and it actually has literally nothing to do with DeepSeek R1 at all and it should just be called Qwen and we should pretend it is literally the same model despite it not being the same model as its training weights are different (you can do a “diff” on the two model files if you don’t believe me!) and it performs differently on the same metrics.

There is simply no rational reason to intentionally want to mislabel the model as just being Qwen and having no relevance to DeepSeek R1. You yourself admitted that the weights are trained on R1 data so they necessarily contain some R1 capabilities. If DeepSeek was lying and trying to hide that the distill models are based on Qwen and Llama, they wouldn’t have literally put that in the name to let everyone know, and released a paper explaining exactly how those were produced.

It is clear to me that you and your other friends here have some sort of alternative agenda that makes you not want to label it correctly. DeepSeek is open about the distill models using Qwen and Llama, but you want them to be closed and not reveal that they also used DeepSeek R1. The current name for it is perfectly fine and pretending it is just a Qwen model (or Llama, for the other distilled versioned) is straight-up misinformation, and anyone who downloads the models and runs them themselves will clearly see immediately that they perform differently. It is a hybrid model correctly called what they are: DeepSeek R1 Qwen Distill and DeepSeek R1 Llama Distill.

The 1.5B/7B/8B/13B/32B/70B models are all officially DeepSeek R1 models, that is what DeepSeek themselves refer to those models as. It is DeepSeek themselves who produced those models and released them to the public and gave them their names. And their names are correct, it is just factually false to say they are not DeepSeek R1 models. They are.

The “R1” in the name means “reasoning version one” because it does not just spit out an answer but reasons through it with an internal monologue. For example, here is a simple query I asked DeepSeek R1 13B:

Me: can all the planets in the solar system fit between the earth and the moon?

DeepSeek: Yes, all eight planets could theoretically be lined up along the line connecting Earth and the Moon without overlapping. The combined length of their diameters (approximately 379,011 km) is slightly less than the average Earth-Moon distance (about 384,400 km), allowing them to fit if placed consecutively with no required spacing.

However, on top of its answer, I can expand an option to see its internal monologue it went through before generating the answer, which you can find the internal monologue here because it’s too long to paste.

What makes these consumer-oriented models different is that that rather than being trained on raw data, they are trained on synthetic data from pre-existing models. That’s what the “Qwen” or “Llama” parts mean in the name. The 7B model is trained on synthetic data produced by Qwen, so it is effectively a compressed version of Qen. However, neither Qwen nor Llama can “reason,” they do not have an internal monologue.

This is why it is just incorrect to claim that something like DeepSeek R1 7B Qwen Distill has no relevance to DeepSeek R1 but is just a Qwen model. If it’s supposedly a Qwen model, why is it that it can do something that Qwen cannot do but only DeepSeek R1 can? It’s because, again, it is a DeepSeek R1 model, they add the R1 reasoning to it during the distillation process as part of its training. They basically use synthetic data generated from DeepSeek R1 to fine-tune readjust its parameters so it adopts a similar reasoning style. It is objectively a new model because it performs better on reasoning tasks than just a normal Qwen model. It cannot be considered solely a Qwen model nor an R1 model because its parameters contain information from both.

As I said, they will likely come to the home in form of cloud computing, which is how advanced AI comes to the home. You can run some AI models at home but they’re nowhere near as advanced as cloud-based services and so not as useful. I’m not sure why, if we ever have AGI, it would need to be run at home. It doesn’t need to be. It would be nice if it could be ran entirely at home, but that’s no necessity, just a convenience. Maybe your personal AGI robot who does all your chores for you only works when the WiFi is on. That would not prevent people from buying it, I mean, those Amazon Fire TVs are selling like hot cakes and they only work when the WiFi is on. There also already exists some AI products that require a constant internet connection.

It is kind of similar with quantum computing, there actually do exist consumer-end home quantum computers, such as Triangulum, but it only does 3 qubits, so it’s more of a toy than a genuinely useful computer. For useful tasks, it will all be cloud-based in all likelihood. The NMR technology Triangulum is based on, it’s not known to be scalable, so the only other possibility that quantum computers will make it to the home in a non-cloud based fashion would be optical quantum computing. There could be a breakthrough there, you can’t rule it out, but I wouldn’t keep my fingers crossed. If quantum computers become useful for regular people in the next few decades, I would bet it would be all through cloud-based services.

If quantum computers actually ever make significant progress to the point that they’re useful (big if) it would definitely be able to have positive benefits for the little guy. It is unlikely you will have a quantum chip in your smartphone (although, maybe it could happen if optical quantum chips ever make a significant breakthrough, but that’s even more unlikely), but you will still be able to access them cheaply over the cloud.

I mean, IBM spends billions of on its quantum computers and gives cloud access to anyone who wants to experiment with them completely free. That’s how I even first learned quantum computing, running algorithms on IBM’s cloud-based quantum computers. I’m sure if the demand picks up if they stop being experimental and actually become useful, they’ll probably start charging a fee, but the fact it is free now makes me suspect it will not be very much.

I think a comparison can be made with LLMs, such as with OpenAI. It takes billions to train those giant LLMs as well and can only be trained on extremely expensive computers, yet a single query costs less than a penny, and there are still free versions available. Expense for cloud access will likely always be incredibly cheap, it’s a great way to bring super expensive hardware to regular people.

That’s likely what the future of quantum computing will be for regular people, quantum computing through cloud access. Even if you never run software that can benefit from it, you may get benefits indirectly, such as, if someone uses a quantum computer to help improve medicine and you later need that medicine.