How Will Quantum Computing Impact Spaceflight?

[sanman]

International Business Machines, having long ago lost its premium brand in computing in spite of its long tradition in fundamental research, is now seeking to reclaim its pole position - by proclaiming a new era of Quantum Utility:



As new advances in error-correction and noise-reduction continue to be made, can Quantum Computing now become practical?
Should Nvidia be looking hard in its rearview mirror?

Sometimes we'll hear about major corporations, some of them even aerospace giants, coming forth to drink from the quantum trough. Do they truly see something useful in this nascent technology, or is it just their shot in the dark?

Will this technology find its way to data-centers only to remain locked up there?
Or could it one day go mobile and even take flight on spacecraft?
Could cold-traps in permanently shadowed lunar craters one day become sites for future quantum data centers, giving us yet more reasons to go to space?

[JohnLloydJones]

For all the constant buzz from certain quarters, quantum computing is still more promise than substance. There is a certain class of problems where quantum computing may become valuable, but I haven't seen much to indicate that quantum computing will take over general computing. Of course, some one may announce a breakthrough that changes all that, but I'm not holding my breath.
 

[Twark_Main]

Sabine still has the best video on quantum hype vs. quantum reality.

Could cold-traps in permanently shadowed lunar craters one day become sites for future quantum data centers, giving us yet more reasons to go to space?

Datacenters produce lots of heat. You would quickly "use up the cold" and saturate your ability to radiate away heat.


Also, running a cyocooler on Earth simply isn't expensive enough to justify it.

Also, the Moon's cold traps are important scientific sites, containing a record of billions of years. Hopefully we're not short-sighted enough to bulldoze them for server farms or gas stations....   

[sanman]

Datacenters produce lots of heat. You would quickly "use up the cold" and saturate your ability to radiate away heat.

Traditional data centers produce lots of heat -- but do Qubits have to produce lots of heat? Qubits don't like heat - that's why they have to be cooled in Dilution Refrigerators.

Also, running a cyocooler on Earth simply isn't expensive enough to justify it.

But there's also all kinds of other noise contamination on Earth, from all the electromagnetic waves we produce.
Just as we might like to build a sensitive radio telescope on the Far Side of the Moon shielded from the electromagnetic emissions of Earth, perhaps our quantum computing devices would also similarly function better with less disturbances in remote regions of outer space, at colder temperatures, surrounded by shielding. Project Kuiper in the actual Kuiper Belt?

Also, the Moon's cold traps are important scientific sites, containing a record of billions of years. Hopefully we're not short-sighted enough to bulldoze them for server farms or gas stations....   

The nature preserve around Starbase Boca Chica may also have importance in ecology and wildlife study -- but sometimes we make sacrifices to further our progress in another area.

[sanman]

For all the constant buzz from certain quarters, quantum computing is still more promise than substance. There is a certain class of problems where quantum computing may become valuable, but I haven't seen much to indicate that quantum computing will take over general computing. Of course, some one may announce a breakthrough that changes all that, but I'm not holding my breath.

Computing is something we all depend upon, and pursuit of it in the quantum realm may then open up that realm and ultimately improve our technological mastery over quantum physics.

The IBM presenters were talking about achieving "Quantum Error Correction" in a few years -- what would John Stewart Bell (of Bell's Inequality fame) say about that? If you can correct errors between entangled Qubits in close proximity to each other, then could you potentially correct them between entangled Qubits that are farther apart? Like, a lot farther apart?

https://www.nature.com/articles/s41586-023-05885-0

Loophole-Free Bell Inequality Violation with Superconducting Circuits
...
Our work demonstrates that non-locality is a viable new resource in quantum information technology realized with superconducting circuits with potential applications in quantum communication, quantum computing and fundamental physics

Ansible when?!

[Twark_Main]

Datacenters produce lots of heat. You would quickly "use up the cold" and saturate your ability to radiate away heat.

Traditional data centers produce lots of heat -- but do Qubits have to produce lots of heat?

Yes, of course. Why would I have brought that up if they didn't? 

Also, as with any compute system, the ancilliary systems (not just the q-bits themselves) consume a large fraction of the power/thermal budget.

Also, running a cyocooler on Earth simply isn't expensive enough to justify it.

But there's also all kinds of other noise contamination on Earth, from all the electromagnetic waves we produce.
Just as we might like to build a sensitive radio telescope on the Far Side of the Moon shielded from the electromagnetic emissions of Earth, perhaps our quantum computing devices would also similarly function better with less disturbances in remote regions of outer space, at colder temperatures, surrounded by shielding. Project Kuiper in the actual Kuiper Belt?

It's still cheaper to go deep underground, if that does happen to be your main constraint. Yes even with the heat.

Also, the Moon's cold traps are important scientific sites, containing a record of billions of years. Hopefully we're not short-sighted enough to bulldoze them for server farms or gas stations....

The nature preserve around Starbase Boca Chica may also have importance in ecology and wildlife study -- but sometimes we make sacrifices to further our progress in another area.

Those two examples are nowhere near comparable. They smell kinda similar though (ie there are vaguely similar "tribes" within the overall "battle" cliche), which is the only narrative modern social media is capable of disseminating -- sports team metaphors. So goes the logical brain hemisphere of the masses, and so goes this thread... 

"Well sure we destroyed Boca Chica, but it was all worth it because destroyed the cis-Earth system's only billions-year ice record too, obliterating irreplaceable scientific data we went there to get!" 

The actual logic makes no sense. From the start the Boca/Moon reason-by-analogy is strained beyond the breaking point.


Anyway, the point stands that making your cooling budget smaller (which this won't do btw) is a lousy reason to build your Amazon Datacenter on top of a World Heritage Site. This idea is as bad as using the Great Pyramid of Cheops to prop up your solar farm so you can save some metal...

[sanman]

Anyway, the point stands that making your cooling budget smaller (which this won't do btw) is a lousy reason to build your Amazon Datacenter on top of a World Heritage Site. This idea is as bad as using the Great Pyramid of Cheops to prop up your solar farm so you can save some metal...

Well, I know certain special places like the Apollo landing sites are considered special heritage places - but does every spot on the Moon have to be a special heritage place? Otherwise, then pretty soon all of Mars could be a special heritage place, and all the asteroids too, etc -- and then there's no room left to exploit any space within reach.

[Twark_Main]

but does every spot on the Moon have to be a special heritage place?

We've both been talking about the polar "eternal night" cold traps, not just any spot on the Moon.

[JohnFornaro]

Ansible when?!

Points.

[edzieba]

Before things are further derailed by imagined lunar nature thermal-reserves or pointless hand-wringing over how cryocoolers work...


Quantum Computing is useful for more rapidly computing algorithms that tank an unfeasible amount of time for classical computers. Currently, there aren't many of these that are in actual use - because their uncomputability means nobody is going to implement them (with the exception of scamgraphy, where that is a feature not a bug). When it comes to hypothesised applications to NP-hard problems, some of the low hanging fruit are probably in accelerating simulations like CFD.

[sanman]

Ansible when?!

Points.

It seems like an Ansible -- ie. a means of instantaneous communication that's faster-than-light:

https://phys.org/news/2023-05-entangled-quantum-circuits-einstein-concept.html

"There are 1.3 tons of copper and 14,000 screws in our machine, as well as a great deal of physics knowledge and engineering know-how," Wallraff says. He believes that it would in principle be possible to build facilities that overcome even greater distances in the same way. This technology could, for instance, be used to connect superconducting quantum computers over great distances.

[edzieba]

Ansible when?!

Points.

It seems like an Ansible -- ie. a means of instantaneous communication that's faster-than-light:

https://phys.org/news/2023-05-entangled-quantum-circuits-einstein-concept.html

"There are 1.3 tons of copper and 14,000 screws in our machine, as well as a great deal of physics knowledge and engineering know-how," Wallraff says. He believes that it would in principle be possible to build facilities that overcome even greater distances in the same way. This technology could, for instance, be used to connect superconducting quantum computers over great distances.

No.
Like all distant entanglement experiments, data cannot be transmitted. You can observe the state at one end and have knowledge of the state at the other end, but you cannot influence either state without breaking entanglement. i.e. you can observe your bit and see that it is 1 and know that the other bit must be 0, but you cannot use this to communicate because you did not get to choose whether the bit was 1 or 0, it is random which one you observe to start with.

[JohnFornaro]

Ansible

Interesting article.  Thanks for posting.

But.

They don't inform the reader in the least about what the experiment did with those 13,000 screws.  And it turns out that Bell's theorem is false?

https://www.scirp.org/journal/paperinformation?paperid=94678

It is concluded that, Bell’s theorem is false because Bell’s inequalities are trivial mathematical relations that, due to an unsuitable assumption of probability, lack essential connection with the real measuring process of the pertinent experiments.

Nobody's explained to me why two entangled particles, separated by an arbitrary distance do not "communicate".  Whatever you "do" to the one particle is "noticed" by the other particle.  If the Morse code for SOS is sent from the first particle, cannot the "message" be read by the distant particle?

What is it that can't be done? change the first particle?  Or read the second particle?

Here's a link for the lazy:

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

This article doesn't include a reference to the 2019 paper above.

And the CSHS Inequality?  More math than should be allowed by law:

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

Unfortunately, the experimental setup of Alice, Bob, and Charlie doesn't readily map to the experimental machinery I'm broadly familiar with.

I keep hoping/thinking that an ansible is possible in priciple.

[sanman]

Nobody's explained to me why two entangled particles, separated by an arbitrary distance do not "communicate".  Whatever you "do" to the one particle is "noticed" by the other particle.  If the Morse code for SOS is sent from the first particle, cannot the "message" be read by the distant particle?

What is it that can't be done? change the first particle?  Or read the second particle?

Here's a link for the lazy:

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

This article doesn't include a reference to the 2019 paper above.

And the CSHS Inequality?  More math than should be allowed by law:

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

Unfortunately, the experimental setup of Alice, Bob, and Charlie doesn't readily map to the experimental machinery I'm broadly familiar with.

I keep hoping/thinking that an ansible is possible in priciple.

The thing is that Quantum Entanglement is theorized to result in instantaneous state change across the 2 particles, independent of separation distance -- meaning it's "non-local" and could conceivably be FTL. So of course someone will say that's not allowed because of a "No Information Theorem", and the overwhelming effect of random noise. But as IBM and other research papers now being published are saying, advances in error correction against noise are showing that meaningful extraction of information from this "non-local" system is possible.

So if that paper in Nature is right, then perhaps we can have access to this "non-local" phenomenon, which we could one day make use of.

No.
Like all distant entanglement experiments, data cannot be transmitted. You can observe the state at one end and have knowledge of the state at the other end, but you cannot influence either state without breaking entanglement. i.e. you can observe your bit and see that it is 1 and know that the other bit must be 0, but you cannot use this to communicate because you did not get to choose whether the bit was 1 or 0, it is random which one you observe to start with.

But Ed, in quantum computing you do get to choose whether the bit is 1 or 0, because you're loading your information into the entangled qubits. Quantum computing wouldn't be very useful for computing if we couldn't take information about some problem and load it into the entangled qubits. Nobody wants to watch some "calculator" you can't load your calculation into. The whole purpose of Quantum computing is to compute, and not just sit there serenely. We load information into the entangled qubits, they do a computation, and then we read the results out.

What do you have to say about this paper published in Nature?

https://www.nature.com/articles/s41586-023-05885-0

Loophole-Free Bell Inequality Violation with Superconducting Circuits
...
Our work demonstrates that non-locality is a viable new resource in quantum information technology realized with superconducting circuits with potential applications in quantum communication, quantum computing and fundamental physics

Anyway, people are talking about the idea more and more:

https://quantumtantra.blogspot.com/2019/11/quantum-ansible.html

[Twark_Main]

But Ed, in quantum computing you do get to choose whether the bit is 1 or 0, because you're loading your information into the entangled qubits. Quantum computing wouldn't be very useful for computing if we couldn't take information about some problem and load it into the entangled qubits. Nobody wants to watch some "calculator" you can't load your calculation into. The whole purpose of Quantum computing is to compute, and not just sit there serenely. We load information into the entangled qubits, they do a computation, and then we read the results out.

You can't just "set" qubits and have them be entangled. You have to go through a special procedure to entangle two qubits on a quantum computer, and afterwards you don't know if they're zero or one.

Entanglement (by definition) requires a qubit to be in a superposition. If you know for sure it's a 1 or a 0, then (by definition) it's not in a quantum superposition. 


Furthermore, even if you can solve this problem, you still can't build an ansible. All you'd be doing is transmitting regular bits to Bob, which happens at the speed of light. The only things that "goes FTL" is decoherence, but there's no decoherence if you already know the bit values.

What do you have to say about this paper published in Nature?

https://www.nature.com/articles/s41586-023-05885-0

Loophole-Free Bell Inequality Violation with Superconducting Circuits
...
Our work demonstrates that non-locality is a viable new resource in quantum information technology realized with superconducting circuits with potential applications in quantum communication, quantum computing and fundamental physics

This paper ruled out local hidden variable theories. It does not (and doesn't claim to) build an ansible, or show that one is possible.

"As of 2015 [i.e. this paper], all Bell tests have found that the hypothesis of local hidden variables is inconsistent with the way that physical systems behave."

https://en.wikipedia.org/wiki/Bell_test#Hensen_et_al.,_Giustina_et_al.,_Shalm_et_al._(2015):_"loophole-free"_Bell_tests

Anyway, people are talking about the idea more and more:

https://quantumtantra.blogspot.com/2019/11/quantum-ansible.html

This is connecting two unrelated things. The blog post is debunking a different (hoax) paper.



Anyway FTL communication belongs in New Physics, so it's OT for this thread. Let's not get another thread locked....  https://forum.nasaspaceflight.com/index.php?topic=34854.20

[sanman]

You can't just "set" qubits and have them be entangled. You have to go through a special procedure to entangle two qubits on a quantum computer, and afterwards you don't know if they're zero or one.

Entanglement (by definition) requires a qubit to be in a superposition. If you know for sure it's a 1 or a 0, then (by definition) it's not in a quantum superposition. 

Okay, fair enough - but even if you don't know whether they're 0 or 1, you do know that they correspond to your input. Otherwise, how can you have any calculation/computation without input? Likewise, how can you have any calculation/computation without reading an output that is based on input? As long as I'm reading an output derived from input, I don't care whether it was represented as 0 & 1, or as Red-Green-Blue.

Furthermore, even if you can solve this problem, you still can't build an ansible. All you'd be doing is transmitting regular bits to Bob, which happens at the speed of light. The only things that "goes FTL" is decoherence, but there's no decoherence if you already know the bit values.

In which case, why is the computation output instantly readable within the confines of a short distance, but not at a longer discernably "FTL" distance (ie. a non-local distance)? In what crucial way does computation differ from communication?

This paper ruled out local hidden variable theories. It does not (and doesn't claim to) build an ansible, or show that one is possible.

"As of 2015 [i.e. this paper], all Bell tests have found that the hypothesis of local hidden variables is inconsistent with the way that physical systems behave."

But from what I remember, local hidden variable theories were postulated to justify being able to determine the outcome of quantum measurements (eg. reading the output of your computation) without violating the "no FTL"/causality stuff.
So by ruling out local hidden variables, that experiment is saying causality/"no FTL" can be violated -- ie. there can be FTL.

[sanman]

[Twark_Main]

Okay, fair enough - but...

Yep, I thought you might go down exactly this road, which is why I wrote the next paragraph.

I just wanted you to get an answer to your question.

Furthermore, even if you can solve this problem, you still can't build an ansible. All you'd be doing is transmitting regular bits to Bob, which happens at the speed of light. The only things that "goes FTL" is decoherence, but there's no decoherence if you already know the bit values.

In which case, why is the computation output instantly readable within the confines of a short distance, but not at a longer discernably "FTL" distance (ie. a non-local distance)

That's not what they mean by "non-local."

To a quantum physicist, anything further than the reduced Compton radius is "non-local." It's not about short vs long distances on a human scale.

But from what I remember, local hidden variable theories were postulated to justify being able to determine the outcome of quantum measurements (eg. reading the output of your computation) without violating the "no FTL"/causality stuff.
So by ruling out local hidden variables, that experiment is saying causality/"no FTL" can be violated -- ie. there can be FTL.

Remembered wrong. Happens to the best of us. 







Bonus video on Bell's Inequality:

[sanman]

Okay, fair enough - but...

Yep, I thought you might go down exactly this road, which is why I wrote the next paragraph.

I just wanted you to get an answer to your question.

Furthermore, even if you can solve this problem, you still can't build an ansible. All you'd be doing is transmitting regular bits to Bob, which happens at the speed of light. The only things that "goes FTL" is decoherence, but there's no decoherence if you already know the bit values.

In which case, why is the computation output instantly readable within the confines of a short distance, but not at a longer discernably "FTL" distance (ie. a non-local distance)

That's not what they mean by "non-local."

To a quantum physicist, anything further than the reduced Compton radius is "non-local." It's not about short vs long distances on a human scale.

But from what I remember, local hidden variable theories were postulated to justify being able to determine the outcome of quantum measurements (eg. reading the output of your computation) without violating the "no FTL"/causality stuff.
So by ruling out local hidden variables, that experiment is saying causality/"no FTL" can be violated -- ie. there can be FTL.

Remembered wrong. Happens to the best of us. 

Okay, let's split this off into another thread under the New Physics forum, so that I don't derail this thread.

[edzieba]

But Ed, in quantum computing you do get to choose whether the bit is 1 or 0, because you're loading your information into the entangled qubits.

You don't, because loading inputs bits into the computer and getting some answer bits out is how a classical computer works. It is not how a quantum computer works.

Greatly simplified: you can arrange your Qbits into the representation of a function you want to compute, but observing those Qbits means you get one of the possible arrangements of bits that satisfies that function, whilst also 'breaking' your Qbits. If you want to get multiple results (i.e. to build up the probability distribution you were trying to find in the first place with your function) you re-create that function multiple times and get multiple answers. If that sounds weird and awkward and a terrible way to go about computation - yes it is, for classical computation. Quantum computers are absurdly worthless for performing the functions we are used to computer performing. That are exceptional only at performing functions that can be represented in the way quantum computation works, and are valuable for the edge cases where a function can both be expressed in a way that even makes sense to attempt quantum computation on, and that function also has some property that makes it unusually difficult to compute classically.

[JohnFornaro]

You can't just "set" qubits and have them be entangled. You have to go through a special procedure to entangle two qubits on a quantum computer, and afterwards you don't know if they're zero or one.

Neither Alice nor Bob know the "value" of their respective qubits.  All they know is that the message that Alice transmits and the message that Bob sees on the qubits they have was pretty simple:

...---...

They still have no idea of the "value" of their respective qubits.  The value is not necessary to decode the message.  The message is not the medium, to coin a phrase.

As Sanman asks, "In what crucial way does computation differ from communication?"

Okay, let's split this off into another thread under the New Physics forum, so that I don't derail this thread.

Be sure and put a tag here pointing to that new location. 

Even so, the utility of an ansible for spaceflight is self evident.

[JohnFornaro]

Link to another of Sabine's commentaries, this time about IBM's 1121 qubit chip which neither IBM nor Sabine know  what it actually can do.

[JohnFornaro]

Nobody's taken a stab at this one.  Is Bell's theorem ifalse?

https://www.scirp.org/journal/paperinformation?paperid=94678

[dlapine]

We aren't running one at our Supercomputer center yet, but I do know that the current state art is that a significant amount of classical HPC equipment will be required in addition to any quantum unit. This would be needed for error correction, calibration, data I/O, etc. Figure at least 50KW and at least 1 rack of HPC hardware.

Not sure how that affects the discussion.

[JohnFornaro]

Not sure how that affects the discussion.

A little more certainty about the effect on the discussion?

[sanman]

Be sure and put a tag here pointing to that new location. 

Even so, the utility of an ansible for spaceflight is self evident.

Here you go:

https://forum.nasaspaceflight.com/index.php?topic=60090.0

[sanman]

[Twark_Main]

You can't just "set" qubits and have them be entangled. You have to go through a special procedure to entangle two qubits on a quantum computer, and afterwards you don't know if they're zero or one.

Neither Alice nor Bob know the "value" of their respective qubits.  All they know is that the message that Alice transmits and the message that Bob sees on the qubits they have was pretty simple:

...---...

They still have no idea of the "value" of their respective qubits.  The value is not necessary to decode the message.  The message is not the medium, to coin a phrase.

Nope. This understanding is still wrong.

There's no way to see any "message" until Alice and Bob both get together to compare notes, in which case they have transmitted classical information.

This is one of those things that non-experts somehow can't stop themselves from trying to "invent," just like free energy and reactionless drives.

the utility of an ansible for spaceflight is self evident.

Sure would be, but quantum entanglement doesn't get you an ansible. 




I really wish this thread would get back to actual quantum impacts on spaceflight, rather than flirting with locking by trying to propel yourself by oscillating a mass back and forth tilting at an impossible quantum ansible.  I suggest all future alsible discussion be moved to the new thread, so we can at least contain the damage.

[sanman]

Okay, so weren't aerospace giants Boeing and LockMart among the first big companies to take a serious look at Quantum computing to help meet their needs? What exactly do they use quantum computing for? And of course they were preceded on this by NASA:

https://ntrs.nasa.gov/api/citations/20220016371/downloads/NASA-TM-20220016371.pdf

from their intro on page 5:

There are two basic keys to quantum technology developments going forward. The first is understanding the physics and applications of quantum entanglement, a cornerstone of what has been termed “The Second Quantum Revolution.” The second is success in the search for the “stable Qbit.” The latter is especially critical for quantum computing. Efforts include increasing the life of quantum states, aimed at usual operational conditions such as room temperature lifetimes much greater than microseconds to milliseconds..

I thought dilution refrigerators are supposed to be helping with that last part.

[sanman]

What types of math problems is Quantum Computing best suited to solve?

ChatGPT

Quantum computing holds the potential to solve certain types of problems much more efficiently than classical computers. Quantum computers operate using the principles of quantum mechanics, which enable them to perform specific calculations at a speed that classical computers would find impractical or infeasible. Some problem classes where quantum computers are expected to have a significant advantage include:

Factorization:
Shor's algorithm, a quantum algorithm, has demonstrated the ability to factor large integers exponentially faster than the best-known classical algorithms. This has implications for the field of scamgraphy, where many encryption schemes rely on the difficulty of factoring large numbers.

Database Search:
Grover's algorithm can search an unsorted database quadratically faster than the best-known classical algorithms. This has applications in searching unstructured databases or solving certain optimization problems.

Simulating Quantum Systems:
Quantum computers are inherently suited for simulating quantum systems, which is challenging for classical computers. This includes simulating the behavior of molecules and materials at the quantum level, with potential applications in drug discovery, materials science, and chemistry.

Optimization Problems:
Quantum computing algorithms, such as the Quantum Approximate Optimization Algorithm (QAOA), are designed to address combinatorial optimization problems more efficiently than classical algorithms. This has applications in logistics, finance, and other areas.

Machine Learning and AI:
Quantum computers may offer advantages for certain machine learning algorithms, such as support vector machines, matrix inversions, and clustering algorithms. Quantum machine learning aims to harness quantum properties to enhance classical machine learning processes.

scamgraphy and Security:
Quantum computers are expected to impact scamgraphy by breaking certain widely used encryption methods. However, they can also contribute to the development of quantum-resistant scamgraphic techniques.

It's important to note that not all problems benefit from quantum computing, and there are still significant challenges in building and maintaining large-scale, fault-tolerant quantum computers. Quantum computers are not intended to replace classical computers but to complement them in solving specific problems more efficiently. The field of quantum computing is rapidly advancing, and ongoing research aims to discover new algorithms and applications that leverage the unique properties of quantum systems.

er... that last bullet point is supposed to say C-R-Y-P-T-O-G-R-A-P-H-Y and Security but for some reason, it posts as "scamgraphy" instead. Somebody had a bad experience with Bitcoin? 
(I'd expect the threat of quantum decryption would eventually force them to switch over to quantum encryption methods too)

[Twark_Main]

What exactly do Boeing and LockMart use quantum computing for?

Subsidy fishing. 

And of course they were preceded on this by NASA

Of course, that's how the corpo-welfare process works. The basic R&D gets taxpayer funded, 90% of them fail, and the remaining 10% get "commercialized" (ie given away for a song) to private industry.



The promise of the technology itself is that it could be better/faster at certain types of optimization problems, eg optimal logistical planning. https://en.wikipedia.org/wiki/Quantum_supremacy

[Twark_Main]

And now, for something that is sure to not get anyone thinking of how to design an ansible around the principle.................   


https://en.wikipedia.org/wiki/Quantum_pseudo-telepathy


The following post is relevant, but it was misplaced in the other thread (since it's not "New Physics"):

Here's a paper on the rendezvous problem with quantum entanglement involved:

https://iopscience.iop.org/article/10.1088/1367-2630/acb22d/meta

Rendezvous is an old problem of assuring that two or more parties, initially separated, not knowing the position of each other, and not allowed to communicate, are striving to meet without pre-agreement on the meeting point. This problem has been extensively studied in classical computer science and has vivid importance to modern and future applications. Quantum non-locality, like Bell inequality violation, has shown that in many cases quantum entanglement allows for improved coordination of two, or more, separated parties compared to classical sources. The non-signaling correlations in many cases even strengthened such phenomena. In this work, we analyze, how Bell non-locality can be used by asymmetric location-aware agents trying to rendezvous on a finite network with a limited number of steps. We provide the optimal solution to this problem for both agents using quantum resources, and agents with only 'classical' computing power. Our results show that for cubic graphs and cycles it is possible to gain an advantage by allowing the agents to use the assistance of entangled quantum states.

The following paper is also relevant, and is a good background for the paper InterestedEngineer mentions:  https://arxiv.org/abs/quant-ph/0509123


So the fun part is that (it is claimed) this phenomenon lets you accomplish certain types of goals as if you have communication, but without actually having any real communication.

Thoughts? Is this just an trick of logic, or could this phenomenon be exploited for practical purposes somehow?

[laszlo]

In an attempt to get back on track after the wishing-relativity-away digression and actually answer the question in the thread topic - calculating sudden emergency deliveries to 3,000 asteroids before the launch window closes and the miners expire.

[sanman]

In an attempt to get back on track after the wishing-relativity-away digression and actually answer the question in the thread topic - calculating sudden emergency deliveries to 3,000 asteroids before the launch window closes and the miners expire.

Or how about calculating the propagation of a debris field after some collision(s)? Like say for a Kessler syndrome situation?

Can quantum computing work in realtime?

[Twark_Main]

calculating sudden emergency deliveries to 3,000 asteroids before the launch window closes

calculating the propagation of a debris field

Y'all need J–  er...  an astrodynamics library. 

This one runs fast, so laszlo can save the miners: https://github.com/jacobwilliams/Fortran-Astrodynamics-Toolkit

AFAIK there isn't a known quantum advantage for traditional astrodynamic tasks like Lambert's problem or Kepler propagation.

[Twark_Main]

Quantum computing is like a turbo boost for space exploration...

...navigating the vast cosmos with supercharged calculations...

[citation needed]

What astrodynamics problem has a quantum advantage that you can see?   

[Nilof]

Imho, the most likely niche where sort-of "quantum" computers will be useful is if you count "ordinary" silicon photonics which are much more "boring" than universal quantum computing.

Mass produced programmable photonics are becoming a thing, and we're about to get commercial "FPGA-like" photonics board where you can have arbitrary linear functions applied to your photons before they make it into your photomultipliers. Those technically give you qbits but any nonlinear logic gates are limited.

The downside is that photons are terrible at doing anything nonlinear, so you can't do "traditional computing" with it. But you can use it for boring engineering applications like high bitrate laser communications across space, or solid state coherent lidar which is undisturbed by sunlight and only bottlenecked by shot noise (i.e. power has to be high enough that your return signal has at least one photon for the lidar idea to work) and gives you doppler velocity measurements.


Coherent lidar chips are magic. Flying autonomously and positioning in space becomes a lot easier when you can point a lidar at a planet at a thousand km distance and expect it to work and have a similar power efficiency to radar, except the resolution is crazy high and suitable for imaging and for docking maneuvers. The same chip/optic can do double duty for inter-satellite communications. Light may end up eclipsing RF.


The most profitable and driving area for photonics will probably still be fiber telecom equipment, with lidar for cars and drones following it, but the spinoffs will have plenty of applications. Frequencies are in the high THz range so if any kind of computation where the result of the previous computation gets fed into the next, it gets like a five order of magnitude "clock frequency" improvement over current CPUs. The set of operations is way more limited, but it may be usable especially if the computation can be made analog like in low-precision matrix muliplication. And you can use it to make shared qbits for more powerful quantum computers, with a lot of effort involved.

[Star One]

This seems to have baffled those in the industry.

Secret international discussions have resulted in governments across the world imposing identical export controls on quantum computers, while refusing to disclose the scientific rationale behind the regulations. Although quantum computers theoretically have the potential to threaten national security by breaking encryption techniques, even the most advanced quantum computers currently in public existence are too small and too error-prone to achieve this, rendering the bans seemingly pointless.

Christopher Monroe, who co-founded quantum computer company IonQ, says people in the industry have noticed the identical bans and have been discussing their criteria, but he has no information on where they have come from.

“I have no idea who determined the logic behind these numbers,” he says, but it may have something to do with the threshold for simulating a quantum computer on an ordinary computer. This becomes exponentially harder as the number of qubits rises, so Monroe believes that the rationale behind the ban could be to restrict quantum computers that are now too advanced to be simulated, even though such devices have no practical applications.

“The fallacy there is that just because you cannot simulate what the quantum computer is doing doesn’t make it useful. And by severely limiting research to progress in this grey area, it will surely stifle innovation,” he says.

https://www.newscientist.com/article/2436023-multiple-nations-enact-mysterious-export-controls-on-quantum-computers/

[Star One]

TED - Quantum Computers Aren’t What You Think - They’re Cooler:



Amongst the things he mentions is using quantum computers to design fusion reactors, medicine and batteries. Also to look into consciousness. He also features Google’s future roadmap for quantum computing.

[Star One]

It measures just 4cm squared but it possesses almost inconceivable speed.

Google has built a computing chip that takes just five minutes to complete tasks that would take 10,000,000,000,000,000,000,000,000 years for some of the world’s fastest conventional computers to complete.

…

Significantly, Willow is claimed to be far less prone to error than previous versions and could swell the potential of the already fast-developing field of artificial intelligence.

https://www.theguardian.com/technology/2024/dec/09/google-unveils-mindboggling-quantum-computing-chip?CMP=oth_b-aplnews_d-5

[InterestedEngineer]

It measures just 4cm squared but it possesses almost inconceivable speed.

Google has built a computing chip that takes just five minutes to complete tasks that would take 10,000,000,000,000,000,000,000,000 years for some of the world’s fastest conventional computers to complete.

…

Significantly, Willow is claimed to be far less prone to error than previous versions and could swell the potential of the already fast-developing field of artificial intelligence.

https://www.theguardian.com/technology/2024/dec/09/google-unveils-mindboggling-quantum-computing-chip?CMP=oth_b-aplnews_d-5

53 qubits, (which I had to go to Reuters to find).

It's an improvement, but still not able to outpace classical computers.

The inflection point is on the order of 64-96 qubits.

It's the projected slope of improvement that is key.  If they hit the top of the logistics s-curve soon, it'll prove to be a useless technology.  If they can steadily grow to 1000 qubits, then they'll have something amazing.


https://www.reuters.com/article/us-alphabet-quantum/google-unveils-quantum-computer-breakthrough-critics-say-wait-a-qubit-idUSKBN1X21QW/

[sanman]

It measures just 4cm squared but it possesses almost inconceivable speed.

Google has built a computing chip that takes just five minutes to complete tasks that would take 10,000,000,000,000,000,000,000,000 years for some of the world’s fastest conventional computers to complete.

…

Significantly, Willow is claimed to be far less prone to error than previous versions and could swell the potential of the already fast-developing field of artificial intelligence.

https://www.theguardian.com/technology/2024/dec/09/google-unveils-mindboggling-quantum-computing-chip?CMP=oth_b-aplnews_d-5

53 qubits, (which I had to go to Reuters to find).

It's an improvement, but still not able to outpace classical computers.

The inflection point is on the order of 64-96 qubits.

It's the projected slope of improvement that is key.  If they hit the top of the logistics s-curve soon, it'll prove to be a useless technology.  If they can steadily grow to 1000 qubits, then they'll have something amazing.

I thought IBM has the lead in this race -- aren't they supposed to be close to coming out with 1024 qubits and the like?

https://www.livescience.com/technology/computing/ibms-newest-156-qubit-quantum-processor-runs-50-times-faster-than-its-predecessor-equipping-it-for-scientific-research

Also, there's a race on to cultivate the largest user install base, to leverage the network effect of that, like Nvidia did with CUDA.

[Star One]

Wouldn’t this be useful to spaceflight and engineering in general as it should be good for fluid dynamics calculations?

[Twark_Main]

This seems to have baffled those in the industry.

Although quantum computers theoretically have the potential to threaten national security by breaking encryption techniques, even the most advanced quantum computers currently in public existence are too small and too error-prone to achieve this, rendering the bans seemingly pointless.

Not too baffling, really. Presumably you want to control the tech well before it advances enough to become a threat. To do so afterwards is pointless, the horse is already out of the barn!

If adversary nations are only 1 generation behind the earliest "weaponizable" generation of a technology, it won't be too hard (or take too long) to reproduce the latest advancement and become weaponizable. If they're instead 3-4 generations behind, it will take a lot longer.

[Star One]

Google apparently made the claim that their new quantum chip carried out its calculations across many universes.

That may seem like a strange thing to say, but it is made necessary by a strange claim tucked away in Google's announcement. According to Neven, the fact that the computer can perform such a calculation "lends credence to the notion that quantum computation occurs in many parallel universes, in line with the idea that we live in a multiverse, a prediction first made by David Deutsch."

…

While some, including Max Tegmark, have suggested that working quantum computers would prove the existence of the multiverse, this is really jumping the gun. Quantum computers rely on quantum mechanics, and not any specific interpretation of it, as far as we have evidence. They work under the Copenhagen interpretation, and are possible in hidden variable theories too.

Though what Google has done with quantum computers is pretty neat, it is far from practical, and by no means proof that it performed calculations across many, many universes.

https://www.iflscience.com/google-suggests-its-quantum-computer-may-use-other-universes-to-perform-calculations-77155

[sanman]

Google apparently made the claim that their new quantum chip carried out its calculations across many universes.

Meh, that's one interpretation out of many. Sort of like the blind men feeling the elephant, then writing news articles about it, based on whatever sells more copy.