Deutsch's proposed experiment would implement the Wigner's Friend thought experiment. — Andrew M
Deutsch's proposed experiment would implement the Wigner's Friend thought experiment.
— Andrew M
I had read that this had been done in 2019. — Wayfarer
On face value, the many-worlds interpretation of quantum physics seems the opposite of parsimomious. It seems to say that the world or universe splits or divides at the point of measurement or observation of a sub-atomic particle. — Wayfarer
So the question is, what problem does the interpretation of quantum physics try to solve? What would its proponents such as Wallace and Deutsch be obliged to acknowledge (apart from the obvious fact that they were mistaken), if by some means it was shown to be untenable? — Wayfarer
0:54 Arndt: The familiar problem that we all try to solve is why is there this unitary evolution of quantum mechanics which seems to explain everything very naturally and, all of a sudden, during a measurement this evolution has to be reduced, collapsed in the Copenhagen interpretation and that's I think something that David doesn't like. He wants to have everything on the same mathematical formalism. But if you follow it through it leads to realities which seem to multiply and then my question to you is what is really the meaning of reality to you because I experience only my single reality here.
1:30 Deutsch: Yes, you put it in terms of how do we make sense of the unitary evolution compared with what we see at a measurement and so on. I would want to start before that. I think we want to understand the world. We want to understand how the world is and that that is not necessarily what we perceive. Our perceptions are at the end of a long chain of physical processes of which themselves we only have scientific knowledge or indirect knowledge.
So I would start with the question, how do we explain quantum phenomena like interference? Not how do we make sense of quantum theory which gives the right prediction but, first, before that, how do we explain quantum phenomena?
So there's an interference process and we have an interference pattern which we can see without any quantum mechanics that the result of the experiment cannot be explained by the events that we see. Now this is not very unusual. This happens a lot, you know, in physics and ultimately every observation is made very indirectly so we have to infer things that are not there. Although infer is the wrong word. We have to conjecture explanations. So that's where I would start.
...
7:44 Arndt: Yeah, but there's something in the formulation of phrasing of our sentences where we're getting also doubtful. When I talk about these things about super positions I always make these quote-unquote when I say a particle is at the same time here and there because there are two words that I don't understand, three words I don't understand.
First the word is 'reality', the second word is what does 'time' really mean, and the third one what does 'space' really mean and we don't have any experimental evidence that the particle is at the same time here and there we just have a physical description the quantum mechanical description that the wave function behaves 'as if' and how can we make the step to the Many-Worlds."
8:23 Deutsch: I think we have something slightly more than that. Again you come from the theory. But, I think, prior to the theory we have the experience that this thing cannot be explained by single trajectories.
8:38 Arndt: Definitely.
8:39 Deutsch: We don't have to believe quantum mechanics to see that. So we rule out single trajectory explanations and that we have before we have quantum mechanics. If we didn't have quantum mechanics, it would be a mystery. We would say that there simply is no explanation.
...
12:40 Arndt: Although other scientists would say shut up and measure - calculate actually. Just don't talk about things that you cannot see and the other part of the other branches you don't see. So why do you dare not to shut up?
12:56 Deutsch: Yes, well, first of all I think that that attitude involves saying that there are certain questions about reality that you're not allowed to ask. You're allowed to ask how the experiment was prepared. You're allowed to ask what will the results be. You're not allowed to ask how were the results brought about by the preparation. So therefore it's not an explanation in my terms.
But as for shut up, that's really another way of trying to evade the consequences in terms of reality. Like my favorite example is of dinosaurs in the past. So there are people who say nobody ever saw a dinosaur and nobody ever will and therefore it's just a frivolity to say that they really exist. At most we can say fossils behave as though dinosaurs existed.
But no paleontologist would accept talking that way even though there is no experimental way of disproving that manner of speaking. And that's because paleontologists are only interested in paleontology because they want to know what really happened. If they were interested in fossils they would be geologists. — Are There Many Worlds? David Deutsch in conversation with Markus Arndt
The familiar problem that we all try to solve is why is there this unitary evolution of quantum mechanics which seems to explain everything very naturally and, all of a sudden, during a measurement this evolution has to be reduced, collapsed in the Copenhagen interpretation and that's I think something that David doesn't like — Are There Many Worlds? David Deutsch in conversation with Markus Arndt
That's the crux. To avoid the 'observer effect'. — Wayfarer
The dependence of what is observed upon the choice of experimental arrangement made Einstein unhappy. It conflicts with the view that the universe exists "out there'' independent of all acts of observation. In contrast Bohr stressed that we confront here an inescapable new feature of nature, to be welcomed because of the understanding it gives us. In struggling to make clear to Einstein the central point as he saw it, Bohr found himself forced to introduce the word "phenomenon."' In today's words Bohr's point - and the central point of quantum theory - can be put into a single, simple sentence. "No elementary phenomenon is a phenomenon until it is a registered (observed) phenomenon."
I didn't get where in the 2nd vid that Deutsch suggested some kind of empirical test that should yield different results from one interpretation to the next. I'm very skeptical of that. — noAxioms
This seems to suggest that it is quantum theory that would be falsified given, well, apparently some sort of confirmation of 'consciousness causes collapse', except that in itself is another quantum interpretation (the Wigner interpretation) which was abandoned by Wigner himself due to it leading to solipsism, not because it in any way refuted quantum theory.6:50 Deutsch: Yes, so if that happened that would refute the Everettian interpretation or, as I would say, it would refute quantum theory. — Are There Many Worlds? David Deutsch in conversation with Markus Arndt
OK. Do any of the interpretations predict a different outcome of this experiment than the others? It's pretty straight-forward. The friend comes out and only remembers classical stuff. The experience of being in superposition relative to the box exterior is in no way different than the same thing without the box. You can no more get interference of the friend than you can get the dead and live cat to interfere with each other. Perhaps this is not the case with the quantum AI, in which case is kind of isn't the Wigner friend thing exactly.Essentially, Deutsch's proposed experiment would implement the Wigner's Friend thought experiment. — Andrew M
OK. I remain skeptical of any claim that this kind of thing can be measured without interpretation-specific assumptions.By conducting an interference experiment on the joint friend/qubit subsystem, the Wigner AI would be able to determine whether physical collapse happened or not.
Interpretation dependent, but true in any local interpretation.But the point is, the object has no specific location until measured. — Wayfarer
The measurement became entangled with the emitting event? That sort of makes it sound like the measurement caused the emitting event. I have no problem with this given a relational view where ontology sort of works temporally backwards. A measurement causes the existence of something in the past (the moon say). Until it is meansured by you, it doesn't exist to you even if it exists relative to something else. Ontology as a relation.You can't say 'the photon caused the measurement' because this assumes that it has some definite existence in some unknown location prior to being measured.
That again seems the same as it existing, unmeasured. If so, not sure what changes upon the measurement.There is no 'something' hiding in an unknown location until measured
So Rovelli would say I think. Copenhagen might say that measurement makes us aware of it, depending if the interpretation is taken as epistemological or metaphysical. There are forms of both, and I don't know how the latter would frame this.- the measurement makes it 'something'.
Agree with the quotes. Do the words mean different things? The problems you point out is a good part of why I am skeptcal of realism.That is why, indeed, 'exists' and 'real' have to be put in scare quotes in this context.
It really is a philosophical problem, about not being able to deal with the fact that there is something fundamental that we can't know. — Wayfarer
This seems to suggest that it is quantum theory that would be falsified given, well, apparently some sort of confirmation of 'consciousness causes collapse', except that in itself is another quantum interpretation (the Wigner interpretation) which was abandoned by Wigner himself due to it leading to solipsism, not because it in any way refuted quantum theory.
In my opinion, Deutsch is answering what seems to be a naive comment, not really describing a test result that differ empirically from one interpretation to the next. Consciousness causing collapse is not an empirical thing. — noAxioms
OK. Do any of the interpretations predict a different outcome of this experiment than the others? It's pretty straight-forward. The friend comes out and only remembers classical stuff. The experience of being in superposition relative to the box exterior is in no way different than the same thing without the box. You can no more get interference of the friend than you can get the dead and live cat to interfere with each other. Perhaps this is not the case with the quantum AI, in which case is kind of isn't the Wigner friend thing exactly. — noAxioms
that attitude involves saying that there are certain questions about reality that you're not allowed to ask. — Andrew M
On face value, the many-worlds interpretation of quantum physics seems the opposite of parsimomious. — Wayfarer
Wayfarer, I know you have a hard time with a 'bigger' universe, but many of us don't. These same sentiments were expressed when it was discovered that the stars were other suns, and then that there were other galaxies as far as you can see. People balked every time it got bigger, but they got over it.It depends on how parsimony is understood. Many Worlds has the biggest universe but also the fewest postulates. — Andrew M
Totally agree here, but I think the effect with which MWI has trouble explaining is the Born rule. It's been a strong piece of criticism.The problem that the interpretation should solve is to explain the interference phenomena that we observe. Not merely to predict observations - that's what the formalism does. If Many Worlds were shown to be untenable, Wallace and Deutsch would say that we have no viable explanation (that we know of). — Andrew M
There is? There are dependencies on frames (what velocity has object X?, a completely frame dependent question since Galileo), but I've not heard that observers have any effect at all. That seems to be confined to QM effects.There's an 'observer effect' in Einsteinian relativity which nobody objects to. That's not the problem. — Andrew M
That sounds cool. In my experience, new evidence just moves the goal posts. An interpretation like the consciousness one will just adjust its story if the linearity of QM can be demonstrated. Others may actually fall out of contention.Deutsch's experiment provides a way of distinguishing between linear interpretations such as RQM/ QBism/Many Worlds and non-linear interpretations such as consciousness-causes-collapse/objective collapse theories like GRW. So it would enable us to rule out an entire class of interpretations. — Andrew M
I am actually very unfamiliar with how they do such tests. I mean, the double slit thing is pretty obvious, but how do they test for superposition of spin? Far worse, they've succeeded in putting something large enough to see with the eye, in superposition of vibrating or not. My question is, how was that demonstrated? How might one actually attempt to do the sort of test your're talking about with the computer?In the Wigner's friend thought experiment, the friend's lab is a closed/isolated system. A quantum computer provides a way to realize that isolation for a large, complex and artificially-intelligent entity (the friend AI). Then we can test for interference. — Andrew M
I am actually very unfamiliar with how they do such tests — noAxioms
distinguishing between linear interpretations . . . — Andrew M
How is it possible to even discuss these things without a deep knowledge of the machinery of experiments? — jgill
It would be better to simply recognise there are things science is unable to ascertain and leave it at that. As a general rule, knowing you don’t know something is preferable to thinking you know something that you don’t. — Wayfarer
Totally agree here, but I think the effect with which MWI has trouble explaining is the Born rule. It's been a strong piece of criticism. — noAxioms
If you one of the types that actually think that MWI implies the creation/generation of ontologically separate worlds, then one also has to deal with how some of them are more probable than others, that meaning must be given to "X exists more than Y". That issue goes hand in hand with the Born rule thing. — noAxioms
There's an 'observer effect' in Einsteinian relativity which nobody objects to. That's not the problem.
— Andrew M
There is? There are dependencies on frames (what velocity has object X?, a completely frame dependent question since Galileo), but I've not heard that observers have any effect at all. That seems to be confined to QM effects. — noAxioms
That sounds cool. In my experience, new evidence just moves the goal posts. An interpretation like the consciousness one will just adjust its story if the linearity of QM can be demonstrated. Others may actually fall out of contention. — noAxioms
I am actually very unfamiliar with how they do such tests. I mean, the double slit thing is pretty obvious, but how do they test for superposition of spin? Far worse, they've succeeded in putting something large enough to see with the eye, in superposition of vibrating or not. My question is, how was that demonstrated? — noAxioms
How might one actually attempt to do the sort of test your're talking about with the computer? — noAxioms
4 Wigner-Deutsch thought experiment
Two central questions that came up repeatedly in our discussions so far are (i) “Does Alice see a definitive measurement outcome?” and (ii) “Is Alice’s lab after the measurement indeed in a superposition state?” Deutsch [23] proposed an extension of the thought experiment described in Section 3, which turns these questions into (in principle) experimentally testable statements. — Testing quantum theory with thought experiments, p17 - Nurgalieva, Renner
The mathematics is linear - a specific kind of function or operation - and this gets confused with "linear interpretation", I think. And then there are "collapses" and so on. How is it possible to even discuss these things without a deep knowledge of the machinery of experiments? That's why its called the measurement problem, ascertaining a quality of an infinitesimal system without altering that quality or another quality. — jgill
...the quantum AI experiment that he describes... — Andrew M
if we had a quantum computer on which an artificial-intelligence program was running, say, with human level artificial-intelligence then this entity would be able to experience interference in its own consciousness. — Are There Many Worlds? David Deutsch in conversation with Markus Arndt
if we had a quantum computer on which an artificial-intelligence program was running, say, with human level artificial-intelligence then this entity would be able to experience interference in its own consciousness.
— Are There Many Worlds? David Deutsch in conversation with Markus Arndt
You think that is remotely close to what Popper would consider 'falsifiable by empirical evidence'?
‘When we create an artificial human using technology that doesn’t exist yet, all will be revealed!’ — Wayfarer
Me: Would Popper consider the Wigner-Deutsch quantum experiment to be falsifiable by empirical evidence?
ChatGPT: According to Popper's criterion of falsifiability, a scientific theory must be able to make testable predictions that could, in principle, be shown to be false. The Wigner-Deutsch quantum experiment is a proposed thought experiment in quantum mechanics, which is based on the idea of creating a quantum system that can perform a universal set of quantum gates, a set of operations that can be used to perform any quantum computation. The experiment proposes that if such a system could be created, it would be possible to demonstrate the existence of quantum parallelism and quantum entanglement in a more direct way than is currently possible.
The Wigner-Deutsch quantum experiment is a theoretical concept, and it has not been physically implemented yet. While the experiment is purely theoretical, it's still an interesting concept and it could be considered as scientific by Popper's standard. Popper would argue that the thought experiment is falsifiable, because it makes predictions that can be in principle tested, if the technology and resources become available. If the experiment is performed and it fails to demonstrate the existence of quantum parallelism and quantum entanglement, it would falsify the thought experiment.
In summary, Popper would consider the Wigner-Deutsch quantum experiment as a scientific theory, because it makes testable predictions that could in principle be shown to be false, even though it's not been physically implemented yet.
When Moses asks to see who or what he has been conversing with on Mount Sinai, he is placed in a crevice and told to look out once the radiance has passed (no peeking now!). Anything more than a glimpse of God's receding back, the story implies, would blow his mortal fuses. The equivalent passage in Hindu scripture occurs in the Bhagavad Gita – and, as befitting that most frank of all religions, is more explicit about the nature of the fatal vision. Krishna responds to the warrior Arjuna's request by telling him that no man can bear his naked splendour, then goes right ahead and gives him the necessary upgrade: "divine sight". What follows is one of the wildest, most truly psychedelic episodes in world literature.
No longer veiled by a human semblance, Krishna appears in his universal aspect: a boundless, roaring, all-containing cosmos with a billion eyes and mouths, bristling with "heavenly weapons" and ablaze with the light of a thousand suns. The sight is fearsome not only in its manifold strangeness but because its fire is a consuming one. "The flames of thy mouths," a horrified Arjuna cries, "devour all the worlds … how terrible thy splendours burn!"
Until recently, a physicist would have regarded this scene as the picturesque delirium of a pre-scientific age. Most still would. And yet the contemplation of the unspeakable flowering of an infinity of worlds is no longer the province of "mystics, charlatans and cranks", as the leading string theorist Michio Kaku has written, but instead occupies "the finest minds on the planet".
Welcome to the multiverse. — Ned Denny, TheGuardian
There's an 'observer effect' in Einsteinian relativity which nobody objects to. — Andrew M
In 1958, Schrödinger, inspired by Schopenhauer from youth, published his lectures Mind and Matter. Here he argued that there is a difference between measuring instruments and human observation: a thermometer’s registration cannot be considered an act of observation, as it contains no meaning in itself. Thus, consciousness is needed to make physical reality meaningful. As Schrödinger concluded, "Some of you, I am sure, will call this mysticism.…’ — “Quantum Mysticism, Gone but not Forgotten
Deutsch is a very imaginative individual, and this whole many-worlds idea appeals on that level. But the Copenhagen attitude is much more modest, in my view. May not be as exciting. — Wayfarer
Imagination will often carry us to worlds that never were. But without it we go nowhere. — Carl Sagan (Cosmos) [via Nurgalieva and Renner]
Analysis of this 'observer effect' can guide us in judging one observational perspective as better than the other (Copernican is better than Ptolemaic). — Metaphysician Undercover
To take a bit of the woo out of QM, instead one should speak of the "measurement effect", which alludes to the machinery doing that task, not the scientist, Gandolf. — jgill
2 Observers in quantum mechanics
The notion of an observation is crucial for linking the theoretical formalism of quantum theory to experiment, and in this sense to physical reality. In an experiment, an observation is the outcome of a measurement that is carried out by an observer, which may be a device or a human. How this observer should be treated in theory is however debated. Is the observer just an ordinary system that can itself be described by quantum theory, or should it be regarded as something external to it, or is it even both? The answer to this question exhibits some of the key differences between the different interpretations of quantum theory, and we thus discuss it in more detail in this section.
The notion of an observer gained importance in physics already before the development of quantum theory. One of its most prominent appearances is in Einstein’s original article on special relativity [27]. Here the “Beobachter” plays a key role, for quantities such as time and spatial locations are only defined relative to them. Special and general relativity still portray the observer in a passive light — the observer is understood as a reference frame, thus giving rise to a coordinate system in spacetime [28, 29]. Other theories view observers as users of the theory. For example, Bayesian statistics [30, 31] consists of a set of reasoning rules that a rational agent should follow to make predictions and decide on future actions based on past observations. A Bayesian observer thus takes a more active role. In quantum theory, both of these roles may be relevant, depending on the interpretation. We will therefore use the terms agent and observer interchangeably.
...
While most physicists today don’t resort to the (vague) notion of consciousness,4 they still haven’t reached an agreement on how to resolve the paradox around Wigner’s friend. The ambiguity is not within the formalism of quantum theory, but lies in how the formalism should be applied to such experiments — a question that the formalism itself cannot answer. In their search for answers, quantum physicists came up with a variety of ideas and proposals, which are nowadays known as different interpretations of quantum theory (see Table 1 for a summary and Figure 3 for an illustration). — Testing quantum theory with thought experiments, p4-5 - Nurgalieva and Renner
Yes, Copenhagen can be understood as the operational interpretation - shut-up-and-calculate. — Andrew M
Bohr, Heisenberg, Schrödinger, Pauli, and others of that generation were deeply cultured individuals with deep knowledge of philosophy both Eastern and Western. The ‘shut up and calculate’ generation were mainly Americans after WW2. Totally different mindset. — Wayfarer
As for Copenhagen, I’ve described it as “shut-up and calculate except without ever shutting up about it”! I regard Bohr’s writings on the subject as barely comprehensible, and Copenhagen as less of an interpretation than a self-conscious anti-interpretation: a studied refusal to offer any account of the actual constituents of the world, and—most of all—an insistence that if you insist on such an account, then that just proves that you cling naïvely to a classical worldview, and haven’t grasped the enormity of the quantum revolution.
...
But the basic split between Many-Worlds and Copenhagen (or better: between Many-Worlds and “shut-up-and-calculate” / “QM needs no interpretation” / etc.), I regard as coming from two fundamentally different conceptions of what a scientific theory is supposed to do for you. Is it supposed to posit an objective state for the universe, or be only a tool that you use to organize your experiences?
...
This is not like picking a race horse, in the sense that there might be no future discovery or event that will tell us who was closer to the truth. I regard it as conceivable that superintelligent AIs will still argue about the interpretation of QM … or maybe that God and the angels argue about it now. — Interpretive cards (MWI, Bohm, Copenhagen: collect ’em all) - Scott Aaronson
or maybe that God and the angels argue about it now. — Interpretive cards (MWI, Bohm, Copenhagen: collect ’em all) - Scott Aaronson
Yes, and excellent post MU. — Andrew M
The notion of an observer gained importance in physics already before the development of quantum theory. One of its most prominent appearances is in Einstein’s original article on special relativity [27]. Here the “Beobachter” plays a key role, for quantities such as time and spatial locations are only defined relative to them. Special and general relativity still portray the observer in a passive light — Testing quantum theory with thought experiments, p4-5 - Nurgalieva and Renner
And I generally agree with Aaronson’s descriptive categories. I am very impressed with Christian Fuchs’ philosophy of QBism which I guess puts me in the second category. Deutsch et al seem to want to preserve the principle of objectivity above all else. — Wayfarer
A good friend of mine, Jacques Pienaar, has recently converted to QBism, as often happens to people that spend too much time around Chris Fuchs. Saddened by these news, I’ve decided to write a blog post explaining why QBism doesn’t contribute anything to understanding Nature. On the contrary, it is a step backwards, as it doesn’t accept the basic premise that there is a world out there and that our job is to understand it. QBism insists that all the puzzles and paradoxes of quantum mechanics don’t actually matter because it’s all subjective anyway. — Why QBism is completely empty - Mateus Araújo
“Get out of agents’ heads?” So you think that `experience’ happens inside agents’ heads: you’re stuck in a Cartesian worldview. For you, subjective means `of the mind’, and objective means `of the mind-independent world’. To be fair, this is what most physicists would understand by those words, having been brought up in the Cartesian way of thinking. And on these terms, I think it would be fair to call QBism solipsist. But that would [be] missing the point, because QBism explicitly says that is not how we should think about experience, objectivity, and subjectivity. — Comment by Jacques Pienaar
I believe that the notion of a 'passive' observer is actually inconsistent with relativistic physics. Passive observation must be from a "rest frame', or else it cannot be said to be "passive". — Metaphysician Undercover
it doesn’t accept the basic premise that there is a world out there and that our job is to understand it. — Why QBism is completely empty - Mateus Araújo
I put this question to NoAxioms but he wasn't sure how to respond, so I'll try again, as you seem to have insight into this area.
On face value, the many-worlds interpretation of quantum physics seems the opposite of parsimomious. It seems to say that the world or universe splits or divides at the point of measurement or observation of a sub-atomic particle. So the question is, what problem does the interpretation of quantum physics try to solve? What would its proponents such as Wallace and Deutsch be obliged to acknowledge (apart from the obvious fact that they were mistaken), if by some means it was shown to be untenable? — Wayfarer
Get involved in philosophical discussions about knowledge, truth, language, consciousness, science, politics, religion, logic and mathematics, art, history, and lots more. No ads, no clutter, and very little agreement — just fascinating conversations.