Google to Crack Bitcoin

Yahoo reports:

Google recently issued two warnings in a span of a few days.

First, quantum computers will be able to crack cryptography encrypting cryptocurrencies like Bitcoin (BTC) by 2029. In fact, hackers might try stealing encrypted financial details right now and wait until 2029 for quantum computers to become powerful enough to decrypt those details.

Google recommended transition to post-quantum cryptography (PQC) to address the threat.

Second, a quantum system could crack a real-time Bitcoin transaction in about nine minutes. Here is how it could happen.

When a Bitcoin transaction is executed, the public key is revealed for a brief period. A quantum computer powerful enough can use the public key to find out the private key and steal the crypto assets.

It takes approximately 10 minutes for a Bitcoin transaction to confirm; the probability of success is only slightly less than 41%, the paper estimated.

The paper also revealed that it could take fewer than 500,000 qubits — far less than millions of qubits cited earlier — to crack Bitcoin's cryptography. It's a 20-fold reduction in the number of qubits needed to crack the encryption.

If there is a quantum computer, it would have to crack someone's key in that 10-minute window to steal money. The computers would have to be millions of times more efficient than they are now.

If the quantum computers get close, the Bitcoin community could change their protocols to resist the attack. It might be difficult to get everyone to agree to a new protocol. But as long as they did agree, the attack would be easily defended.

Dr. Quantum Supremacy has his take on the new announcements. I am skeptical, as usual.

In particular, the Caltech group estimates that a mere 25,000 physical qubits might suffice for this, where a year ago the best estimates were in the millions.

Here is a new PBS tv video on The Truth About Quantum Computers.

4:47 Microsoft claimed not only had they observed Majoranas, they also figured out how to control them. And they said they'd be able to use them to build reliable qubits that would be able to hold up in ways that other qubits can't. This breakthrough would provide a much faster pathway to quantum computing at a much larger scale than anyone else has been able to achieve. Microsoft was faced with an avalanche of skepticism. And as of filming, the data hasn't firmly established everything they claimed.

But some are optimistic that Microsoft can improve its chip and provide the breakthrough the industry has been waiting for. If they do, the whole world will change fast as we gain the ability to solve all kinds of problems we can't currently fully explore. For example, we might be able to create computer simulations of our world, down to the molecular level. That would open the door for incredible breakthroughs in chemistry and medicine. Or we could develop new battery technology, which could be key for mitigating climate change.

So this "truth" is all speculation.

A River is now a Science Journal Co-author

Centuries ago, scientists might thank God, or cite Christianity for their belief in an orderly world. No science journal would tolerate that today, right?

Actually the leading science journal, Nature, has publish an article praising a river god.

Biology professor Jerry Coyne reports:

Conservationist Anne Poelina has a deep connection to the fresh water that runs through the dry red-rock landscape of the Kimberley region in Western Australia. Poelina identifies as a Nyikina Warrwa woman, and her people are the Traditional Custodians of the Martuwarra Fitzroy River. ...

Poelina explains that “in terms of property rights, the river owns me. So, I have a duty of care and the fiduciary duty to protect this river’s right to life.” ...

In 2020, she started including the Martuwarra River of Life as the first author on her publications. ...

When asked why the river should be listed as first author, she responded: “Because it’s the authority. It’s where I get my authority.”

This is not religious tolerance. This is a Wokeness statement.

China has taken over Science

T. Greer argues China is the future of science:

The scientific publisher Nature makes a similar catalog on a slightly more granular level, looking at specific fields of science. According to Nature’s most recent rankings, 18 of the top 25 most productive research institutes in the physical sciences, 19 of the top 20 in geosciences, and a full 25 out of 25 in chemistry are Chinese. Only in the biosciences do American scientists still have a lead—but even on that list three of the top ten are Chinese.6

The kicker is, none of that was true even just a decade ago.

The QWERTY Keyboard was not Designed to be Slow

I need to watch Youtube with an AI LLM to fact check it.

Physicist Brian Keating posted a cosmology interview, and started making a false analogy about keyboard. My AI advises:

While Brian Keating is an astrophysicist and not a historian of technology, he is repeating a very common popular myth. The claim that the QWERTY layout was designed specifically to "slow down" typists is technically incorrect, though it is based on a grain of truth regarding mechanical limitations.

According to historical research into the origins of the typewriter:

The "Jamming" Problem: In early mechanical typewriters, if a typist hit two keys that were physically close to each other in rapid succession, the "typebars" (the hammers that hit the paper) would collide and jam.

The Real Purpose of QWERTY: The layout was designed to separate frequently used letter pairs (like "TH" or "ST") so their physical hammers were on opposite sides of the machine. This allowed the hammers to fall back into place before the next one rose, actually allowing the user to type faster without the machine seizing up.

The "Slow Down" Misconception: The myth likely arose because the layout is not "ergonomically optimal" for modern electronic keyboards. Since we no longer have mechanical hammers to worry about, the QWERTY layout seems unnecessarily difficult compared to alternatives like the Dvorak Simplified Keyboard.

In the video, Keating uses this as an analogy for "technological lock-in", arguing that even if a system is no longer the most efficient, it becomes so widespread that it is nearly impossible to replace—much like he fears is happening with current AI architectures.

The truth is that the qwerty keyboard is not significantly slower than the Dvorak. It just reduces jamming on a mechanical typewriter.

I am wary when some expert tries to make a point using some ridiculous myth that was debunked decades ago. He could have just googled it, and seen that he was wrong.

In the video, Keating shares another classic bit of "technological lock-in" lore, claiming that modern railroad gauges (the distance between the tracks) can be traced back to the width of a Roman chariot, which was designed to fit two horses' butts.

While it’s a great story for a podcast, historians and engineers generally categorize this as a "spurious correlation"—it's mostly a myth, though it has a tiny thread of logic.

The Fact vs. The Fiction

• The Claim: Roman chariots created ruts in European roads. Wagons were built to fit those ruts so they wouldn't break their wheels. Early tramways used those same wagon dimensions, and English trains followed suit, eventually leading to the Standard Gauge (4 feet 8.5 inches) used in the U.S. and much of Europe.

• The Reality: While the standard gauge is roughly the width of an ancient wagon, the specific measurement of 4' 8.5" was actually popularized by George Stephenson, the "Father of Railways." He chose it because it was the width of the existing pre-steam coal tramways in North England where he worked.

• The "Horse's Butt" Part: There is no evidence that Romans measured horses' rear ends to build chariots. Chariots were built to be wide enough to hold two people and stable enough not to tip over. The fact that two horses fit in front of that width is a matter of practical spacing, not a design blueprint that dictated the Space Shuttle's dimensions (another common layer of this myth).

Why Keating Uses It

Keating’s broader point at isn't necessarily about Roman history; he's using it to explain Path Dependence. He argues that once a standard is set—whether it's QWERTY keyboards, railroad widths, or GPU-based AI architectures—it becomes "locked in" because the cost of changing the entire infrastructure is too high, even if a better way exists.

He is probably also wrong with his predictions about AI architectures. He also compares AI to a cockroach, and I think his point is that our AIs could suffer a technological lock-in at a sub-cockroach lever.

I assume that Keating is more accurate when he talks about cosmology experiments. But he says this:

0:30 If you said there's one galaxy, you're stupid. If you said there's one planet, you're stupid. If you said there's one. So why say there's one universe?

I am sticking to one universe. Maybe I am stupid.

WSJ Hypes Quantum Computers

new WSJ article has a glowing account of the future of quantum computing:

Microsoft, International Business Machines, Google and a host of other tech companies are in a race to disrupt the nature of computing.

Collectively in the U.S., these companies have spent hundreds of millions in the past few years to develop a new type of computer—known as a quantum computer—that leverages the principles of quantum physics to solve problems far beyond the capabilities of today’s best supercomputers.

And the companies say they could do it in the next two to five years.

When this point is reached, some problems that would take a traditional computer more than trillions of years to solve could take a quantum computer mere minutes, changing business as usual for industries involved with financial trading, shipping logistics, pharmaceuticals, scientific discovery, data encryption, insurance, internet delivery and more.

No, none of this is going to happen in five years.

It gives the usual explanation, even though Dr. Quantum Supremacy hates it:

A quantum computer, however — because of entangled qubits’ ability to calculate many probabilities at once — can evaluate all options simultaneously.

He says this is misleading, because if that were true, then the quantum computer could solve NP complete problems like the traveling salesman problem.

The article is paywalled. It has some nice graphics, if you can get it.

Dr. Bee Pushes Spooky Action and Superdeterminism

Sabine Hossenfelder posted a new video on causality.

I want to talk today about an issue that bothers me a lot, it’s that most physicists believe the speed of light is an ultimate, absolute, and impossible to overcome limit. Indeed, I think it is THE biggest mistake that physicists are making, that our entire species is making. ... 11:45 I am making this video to save mankind from its biggest mistake

Causality is the idea that if events A and B are separated, then A can only affect B by some sort of signal or interaction being transmitted from A to B. Relativity realizes this by putting a non-euclidean geometry on spacetime, so that everything propagates at the speed of light or slower.

She goes on the explain how she believes in the arrow of time, but that faster-than-light signals ought to be possible. She says we should not be constrained by relativity, because we know it is wrong.

2:14 I don’t know any physicist who thinks that Einstein’s theories are ultimately correct because they don’t include quantum effects, we are missing a theory of quantum gravity. So why should the limitation of the non-quantum theory continue to hold when we know it ultimately isn’t correct?

No, we are very sure the non-euclidean local structure of spacetime is correct. Her hypothetical quantum gravity only applies to the first second of the big bang and the center of a black hole, both far outside any scientific observation.

Next she talks about entanglement. Just where you might expect her to say that entanglement proves spooky action at a distance, she correctly explains that it does not.

This is the supposed non-locality. You make 9:51 a measurement here and you infer information about the properties of something elsewhere. This is nonlocal in some sense, but there is no information actually traveling anywhere, it’s just that you learned something about what is going on elsewhere. And this is the only way in which quantum physics is non-local. ... Because the measurement doesn’t affect the probability of either of the measurement outcomes.

This point trips up many physicists. The measurement does affect your knowledge, and hence how you calculate your expectations, but does not violate the causality being limited by the speed of light.

Then she goes off the rails.

11:53 It’s like this. Suppose that you think the collapse of the wavefunction is NOT a physical process. That actually the particles did have some specific state before you measured them, you just don’t know which. This is what’s called a “hidden variables theory”. In the simplest case the hidden variable just directly encodes which side is up. And the only way to make a hidden variables theory compatible with Einstein’s theory is by using what has been called “superdeterminism”.

Superdeterminism is the only local explanation for all the observations of quantum physics. This is why I think it’s trivially correct, and I am waiting for the rest of physicists to wake up to that. Which means that now we are properly crossing over into the range where most physicists would try to disagree with me, meaning they would be wrong. Physicists have mostly dismissed superdeterminism because of social reinforcement. The majority doesn’t even know how it works, they never thought about it, they just heard someone else say it’s wrong and they decided to believe this.

When she assumes that the particles had some "specific state", she means that the state could be completely described by hidden variables. Such hidden variables contradict quantum mechanics, and that is why no one believes in them.

When she says superdeterminism is the only local explanation for quantum observations, what she really means is that it is the only local hidden variable explanations. That is just a fancy way of saying that quantum mechanics is not a classical theory. Everyone has agreed to that for a century.

If you did believe in a hidden variable theory, as well as local causality, then she is correct that you are led to superdeterminism. Physicists dismiss it because it is philosophically absurd, anti-science, and no one knows how it would work. I have criticized it several times, such as here.

Another new video lists 10 Theories That Suggest Our Universe Is Not Real. It describes simulations and Boltzman brains, but superdeterminism is not respectable enough to make the list.

Quantum Crypto Wins Turing Award

Quanta magazine announces:

Bennett and Brassard have now been named the winners of the A.M. Turing Award, one of the highest honors in computing, for “their essential role in establishing the foundations of quantum information science and transforming secure communication and computing.” The award comes with a $1 million prize.

No, they did not transform secure communications. Their work has no practical applications.

Scott Aaronson says:

This is the first-ever Turing Award specifically for quantum stuff (though previous Turing Award winners, including Andy Yao, Leslie Valiant, and Avi Wigderson, have had quantum among their interests).

As a practical proposal, BB84 is already technologically feasible but has struggled to find an economic niche, in a world where conventional public-key encryption already solves much the same problem using only the standard Internet—and where, even after scalable quantum computers become able to break many of our current encryption schemes, post-quantum encryption (again running on the standard Internet) stands ready to replace those schemes. Nevertheless, as an idea, BB84 has already been transformative, playing a central role in the birth of quantum information science itself.

The BB84 protocol suffers several technical flaws.

The most important thing in secure communications is authentication. This is currently done with digital signatures and certificates, using RSA or ECDSA. This underlies everything. It is the most important part of ubiquitous protocols like https and ssh. But the quantum crypto cannot do it. That makes it useless for anything serious.

The next fatal defect is that it depends on hardware quirks. You have to have analog equipment that may or may not have the required precision, and may have analog vulnerabilities. This makes is subject to hardware attacks.

This makes is vastly inferior to the math-based crypto methods, because the math is not subject to hardware attacks. If a digital crypto device outputs bits that do not have the desired voltage or frequency, no info is leaked.

Another flaw is that the main BB84 security guarantee is that an attacker can probably be detected, so that transmission can be terminated. This has no value. In today's internet, systems get attacked all the time, and no one wants to shut down a communication because it is being attacked. Conventional cryptosystems are designed to be immune to such attacks.

Another flaw is that the internet is run on millions of routers. Using quantum crypto requires that all those routers be quantum computer routers. The quantum router has not even been invented, and even if it is possible, it will never be economical or have the necessary throughput.

All this has been known for decades, and that is why no one uses it, except for a few research demo projects.

New Survey Article on Many-Worlds

I regularly bash many-worlds theory as unscientific and nonsensical, but it is useful to see how it is defended by its proponents. Here is a new encyclopedia article on the subject.

The Everett or Many Worlds interpretation is claimed to be the only realist interpretation that can recover the empirical success of quantum theory in its relativistic and non-relativistic variants, its advocates suggest that it does so without any additions to the physics.

Yes, it claims that, but it has never recovered any empirical success. None.

Probability within Everettian theories is strongly contested and it’s un- clear whether the many distinct resolutions in the literature are mutually incompatible and thus undermine one another ...

EQM [Everettian Quantum Mechanics, ie many-worlds theory] is taken to face two major problems: the preferred basis problem and the probability problem. The preferred basis problem concerns how the universal wavefunction is decomposed, leading to different classical-like branches. ...

The second major problem is the probability problem, which asks how probability can make sense in a deterministic theory where all possible outcomes occur.

Yes, those are two big problems. They cannot define the branches or the probabilities.

The article also discusses other approaches like Bohmian mechanics, and how they do not work either. The obvious inference is that the textbook Copenhagen interpretation of 1930 works better than any of these more modern ideas.

Has Quantum Supremacy been Achieved?

Dominik Hangleiter writes in a new paper:

Recently, I gave a couple of perspective talks on quantum advantage, one at the annual retreat of the CIQC and one at a recent KITP programme. I started off by polling the audience on who believed quantum advantage had been achieved. Just this one, simple question.

The audience was mostly experimental and theoretical physicists with a few CS theory folks sprinkled in. I was sure that these audiences would be overwhelmingly convinced of the successful demonstration of quantum advantage. After all, more than half a decade has passed since the first experimental claim [AAB+19] of “quantum supremacy” as John Preskill called the idea “to perform tasks with controlled quantum systems going beyond what can be achieved with ordinary digital computers” ...

I could not have been more wrong: In both talks, less than half of the people in the audience thought that quantum advantage had been achieved.

After several pages describing the experiments, he concludes:

I hope that I could convince you that quantum advantage has been achieved. There are some open loopholes, but if you are happy with physics-level experimental evidence, then you should be convinced that the RCS experiments of the past years have demonstrated quantum advantage.

No. The whole point of quantum supremacy, aka advantage, is to do an experiment that convincingly demonstrates that super-Turing computers are possible. If most of the experts have not been convinced, then the principle has not be demonstrated.

I am a skeptic, and will be hard to convince. But they have not even convinced the experts who work in the field.

But read the paper, and make up your own mind.

Scott Aaronson seems to be still on the fence. His recent postings have been either about how he hates Pres. Trump, or how he agrees with Trump's pro-Israel foreign policy.

Science Papers are now mainly read by AI LLMs

Alexander Kustov, with Claude AI assistance, writes Academics Need to Wake Up on AI and Part II:

1. AI can already do social science research better than most professors.

2. The academic paper is a dead format walking.

3. The commercial journal system may not survive this.

4. Academics hold AI to absurd double standards.

In particular: Most papers are already mostly read by AI, not humans. Your primary audience is increasingly LLMs.

Physics Lifetime: 1820 to 1970

Popular tweet:

Many people don't understand just how brutal diminishing returns in theoretical physics were.

Physics barely existed before 1820. After 1970, there was essentially nothing left to discover.

In 1819 there were probably less than 100 full-time paid physicists in the whole world.

By 2026 there are probably about a million physicists across academia and industry, and that number was already huge in the 1970s when physics sort of "ended" with QCD and electroweak unification.

A small, brave band of gentlemen-scholars and amateurs worked out the most important parts of physical law in the 1800s. People doing it as a hobby!

Today, vast armies of professionals equipped with supercomputers toil away in the quantum gravity dungeon, unable to make progress.

Diminishing returns are brutal.

my point is that the low hanging fruits of physics were all picked in a brief window from about 1820 to 1970.

Before that, it was difficult to get anything done at all, there was no funding

Quantum Computing and National Security

The Wash. Times reports:

One of the most advanced technologies intersecting with U.S. national security today is quantum computing. Quantum has arrived in 2026, and how it ultimately gets implemented will impact America’s standing in great power geopolitical competition, especially with U.S. adversaries. National Security Editor Guy Taylor sits down with industry leaders at “Qubits26 Quantum Realized,” a conference hosted by D-Wave Quantum, for a wide-ranging discussion on what quantum computing is and how it stands to change the world.

The rest of the article is paywalled, and I do not need to read it. It is all a scam. Quantum computers will not affect national security.

Good Wlll Hunting

SciAm reprints an article on Why mathematicians hate Good Will Hunting.

With the award ceremony for the Oscars this month, many people are thinking back on past winners—including Good Will Hunting. It’s worth taking a closer look at the blackboard in a film that, in 1997, took nine nominations and won for both original screenplay and actor in a supporting role. ...

But I still think the filmmakers chose this particular math problem poorly, even for a Hollywood film.

No, that is not why mathematicians hate the movie.

The hero is a fictional exceptionally talented math prodigy. Supposedly he enjoys math so much that he gets a job as an MIT janitor, and eavesdrop on the research there.

But he never spends any of his free time doing math. Instead he goes drinking with his non-math buddies, and getting into fights. In the end, he decides that math is for losers, and he abandons a wonderful math opportunity in favor of chasing a girlfriend.

Nobody gets that good at math unless he enjoys it very much. The movie fails to portray that at all.

Nature Deepseek Article may be Exaggerated

The 17 September 2025 Nature cover story was this article by China AI company Deepseek. Supposedly it had a hot new AI model trained at low cost.

They aRe widely accused of using pirated Nvidia chips that were illegally imported.

Now Anthropic claims that Deepseek and other China AI companies have been using thousands of bogus accounts to steal data from Anthropic models.

Deepseek has made some decent AI LLMs, but maybe not the scientific advance they claimed. Nature said that it investigated the validity of the Deepseek claims, but I don't know how it could know what was going on in China.

Anthropic could be lying. It really hates Chinese competition. So I am not necessarily drawing any conclusions here.

Why Chance make no sense in Many-Worlds

I have argued here that many-world (Everettian) theory is incoherent because it fails to make any sense out of probability. To believe in the theory, you have to reject probability as widely understood, and then to reject all of science.

No one admits this, of course, but see how a new paper dances around the subject.

Everettian chance in no uncertain terms

The current landscape of views on chance in Everettian quantum mechanics is a curious one. On the one side, longstanding critics of many-worlds theories maintain that probability is needed to make sense of the machinery that Everettians use to derive chance values, resulting in circularity (Baker 2007, Dawid and Thébault 2015, Mandolesi 2019). On the other side, Everettians seem to agree that chance values should be derived in terms of agents’ uncertain or partial beliefs—but they cannot agree on how.1

Perhaps the most famous of these uncertainty-based approaches is the decision-theoretic program explored by Deutsch (1999) and Wallace (2012): they purport to prove that a rational Everettian agent must order their preferences over acts in a way that recovers the Born rule. Sebens and Carroll (2018) take issue with one of the principles of rationality in Wallace’s approach and instead aim to derive Everettian probabilities from principles governing self-locating uncertainty. McQueen and Vaidman (2019) offer yet another self- locating uncertainty approach, taking issue with Sebens and Carroll’s metaphysical view of branching. Notably, all three approaches claim that symmetries of quantum states are central to their arguments, but none attempt to characterize the symmetries at play.2

The most common defense of many-worlds here is to give up on probabilities directly, but to argue that it could be rational to believe in them anywy, as some sort of subjective way of trying to make sense out of nonsense.

Any sort of scientific outlook requires saying that some things happen, some do not happen, and some things are more likely than others. Many-worlds is unable to deal with any of this. Just look at the above nonsense. It essentially says that many-worlds researchers are trying to make sense out of chance, and not succeeding.

Cannot make Decisions without Free Will

Dr. Bee rants about Why I fear for the future of mankind:

0:24 You all know that I don’t believe in free will, which is why I don’t talk about what we “should” do. I’m just here to observe what we do. And this doesn’t look good for the future of our species. ...

6:13 This is why I am of two minds about the current developments. On the one hand, I see a return to sanity, a recognition on a country level about what we can realistically expect and achieve. And this will probably mean that more climate policies will be rolled back in the coming years. It’s not great, but we will cope.

On the other hand, it demonstrates that we have a much bigger underlying problem, our inability to make collectively intelligent decisions. That will come back to haunt us and that’s why I’m worried about the future of our species.

She rejects free will because of a belief in superdeterminism. That is a fallacy that I have criticize previously.

Here, I am just wondering how she thinks that anyone will make intelligent decisions, if there is no free will. Free will is the ability to make decisions. No free will, and we are trapped in the consequences of some ancient initial value problem.

Most philosophers have become compatibilists, meaning that you can have the illusion of free will, even though all your decisions are determined. Whether that is true or not, if our decisions are determined, there is no use complaining about lousy decisions. No one can make any decisions. We are doomed to live out a preprogrammed life.

Once she says that she has no free will, why would anyone listen to her opinions? They are not her opinions. They are just sentences that have been programmed to come out of her mouth. She is not applying her personal knowledge and judgment. She cannot expect us to draw our own conclusions. It is all like a big artificial simulation. She is like a movie character who says she is worried about the future. It means nothing. It is just a line in the script.

Update: Here is evolutionist Jerry Coyne on a rant against free will, attacking Michael Shermer for saying:

Determinists like Harris and Sapolsky have physics envy. The history of science is littered with the failed pipe dreams of ever-alluring reductionist schemes to explain the inner workings of the mind

Coyne is a hard-core determinist. He does say that we can learn from experience, but it is involuntary evolution at work.

Quantum Computers will be Useless, even if they work

Dr. Bee's latest video:

As we continue to research quantum computing, quantum advantage – the supposed advantage that quantum computers theoretically have over regular computers – continues to dry up. Today we’re covering how more quantum computing use cases are disappearing, and an unexpected problem with quantum computing in general.

I have been arguing that quantum computers are impossible, and also that they will have no commercial utility, even if they do work.

In this video, Hossenfelder argues that quantum computers have made a lot of technical progress, such as on error correction. But they are too expensive, too slow, too power-hungry, and no one can find any useful applications.

On the Physical Effect of Potentials

Veritasium has a new video on the Aharonov–Bohm effect.

The object is to show that, in a non-simply-connected spacetime, a physical effect can depend on the potentials, and not just the fields.

Mathematically, the field is the curvature of a differential geometry connection, and a connection is the infinitesimal relation between nearby points. The physics depends on the connection, and not just the curvature.

This is portrayed as a great paradox, with physicists being split on how to explain it. Some resort to nonlocal nonsense.

Bohm himself was a Communist, as the video explains, and he had weird beliefs.

There are indeed a lot of papers on this subject, but it is all long-settled. Eg, see this paper claiming Impossibility of Gauge-Invariant Explanations of the Aharonov–Bohm Effect. I do not get what this paper is saying, as all the observables are gauge-invariant.

Lenny Susskind's AI impostor explains it somewhat in this video. These AI videos are amazingly good. I wonder what the real Susskind thinks about fake videos being better that his real lectures.

The point here is that curvature is a measure of something being curved. It should not be surprising or paradoxical that the something has physical significance.

The argument is given that the potential cannot be real, if two different potentials give the same fields.

The examples are not really two different potentials. The two potentials correspond to the same connection. The connection is what is real.

Besides, there are lots of physical variables that depend on choices. Measuring height depends on choice of coordinates. Measuring momentum depends on a reference frame. Wave functions depend on a choice of phase factor.

No Truth in a Causal Universe

This guy argues that we should not accept any arguments from people who believe in determinism, and reject free will.

I agree with this. If a schizophrenic tells you that he obeys the voices in his head, then you would not accept his testimony on any subject. He is not even speaking for himself.

Sam Harris is one of those determinists. Physicist Brian Keating interviewed Harris, and trashes him in this video. Keating says Harris is a secular fundamentalist, has Trump (and Musk) derangement syndrome, lacks self-awareness, and has poorly thought out Bible criticisms.

One of the main arguments is that Harris says that anyone could write a better book than the Bible, because the Bible condones slavery. Keating says that the same word was used for slaves and servants, and the Bible says they must be treated well.

I agree that criticizing the Bible because it has slavery is lazy. Everyone had slavery. Better economic systems had not been invented.

Harris appears to have lost his grip on reality by taking illegal psychodelic drugs. He says he does not even have a feeling of free will.

Here is a new video with Harris and Penrose, on consciousness.

Physicists Defend Free Will

The issue of free will is mostly a philosophical one, with the main arguments being understood by the ancient Greeks.

In the last century, most intellectuals have turned against free will. They all accept some variation of the following argument.

(1) The fundamental laws of physics are deterministic. The whole concept of a rational outlook towards the world requires determinism. Maybe there is some randomness coming from quantum mechanics, but then the laws are determinism-plus-randomness such that the randomness does not matter for free will.

(2) Free will is just an illusion. All our actions are determined. It may be helpful to imagine that you are making choices, and such imagining might be good for society and your peace of mind, but free will is how you rationalize being a pre-programmed robot.

For a recent example, see this video discussion:

Robert Sapolsky, Paul Bloom, and Lucy Allais debate whether free will exists and the deterministic nature of our lives.

Can we escape our destiny?

An individual "is responsible for everything he does," claimed Sartre. And from criminal justice to creative expression, free will and responsibility are central to our culture and our personal lives. Yet neuroscientists and materialist thinkers commonly maintain that freedom is an illusion. And it remains unknown how the core principles of freedom and responsibility can be reconciled with this outlook. Many attempts have been made to argue that the two seemingly contradictory frameworks can be made compatible. But critics say these "compatibilist" arguments are unconvincing and are driven merely by the attempt to make scientific materialism acceptable. Furthermore, whilst surveys suggest most materialist philosophers believe we can reconcile the two, the majority of us reject the idea that an action can be both determined and free. ...

Joining us from California is Robert Sapolsky. Sapolsky is a distinguished neuroscientist, primatologist, and author, best known for his research on stress and its impact on behaviour and health. He is also a professor at Stanford University.

Sapolsky confidently tells us that science proved an essential determinism, and that it is nonsense to say that we make any choices. He says a lot of other things that are completely false.

I have argued against this view many times, and now I find a new paper explaining it well:

Reframing the Free Will Debate: The Universe is Not Deterministic

Henry D. Potter, George F.R. Ellis, Kevin J. Mitchell

Free will discourse is primarily centred around the thesis of determinism. Much of the literature takes determinism as its starting premise, assuming it true for the sake of discussion, and then proceeds to present arguments for why, if determinism is true, free will would be either possible or impossible. This is reflected in the theoretical terrain of the debate, with the primary distinction currently being between compatibilists and incompatibilists and not, as one might expect, between free will realists and skeptics. The aim of this paper is twofold. First, we argue that there is no reason to accept such a framing. We show that, on the basis of modern physics, there is no good evidence that physical determinism of any variety provides an accurate description of our universe and lots of evidence against such a view. Moreover, we show that this analysis extends equally to the sort of indeterministic worldviews endorsed by many libertarian philosophers and their skeptics, a worldview which we refer to as determinism plus randomness. The papers secondary aim is therefore to present an alternative conception of indeterminism, which is more in line with the empirical evidence from physics. It is this indeterministic worldview, we suggest, that ought to be the central focus of a reframed philosophy of free will.

I wonder if I am being duped by AI slop. Maybe some AI put together these podcasts based on Susskind's lectures and writings. Here is Roger Penrose on Quantum Mechanics Is NOT Random. It is a very good summary of Penrose's view on the subject, and rendered in his own voice. In the end, he argues that humans have free will, based ib quantum gravity collapse, and that AI will never be conscious.

Are the Laws of Nature Ugly?

Dr. Bee rants about beauty in physics:

4:02 In my book 10 years ago I argued that when we understand the laws of nature better, we will eventually come to find them beautiful. Not because the maths is so pretty but because it describes nature. And because it has happened in the past.

4:18 Astronomers originally thought that planets should move in circles around the sun. When it turned out that this didn't quite work, they added circles around circles, the infamous epicycles, just because circles are so pretty. Today we just use ellipses and no one thinks that’s ugly.

4:37 Quantum mechanics is another example. It faced a lot of resistance initially because it was supposedly ugly. Not just the early versions, but also later extensions to quantum field theory which required getting rid of infinites. Physicists today have just gotten used to it. No one calls it ugly anymore.

4:57 And Maxwell’s theory of electrodynamics too, didn’t live up to the beauty standards of the day, which were based on a mechanistic world view. It seemed odd that electric and magnetic fields would just exist on their own, rather than being a property of something else, some underlying substrate, an aether, little gears, something. Today we just accept fields as fundamental.

5:24 Einstein’s theory of special relativity interestingly enough was originally not rejected because it was ugly but largely for philosophical reasons.

These are some strange arguments. The infamous epicycles are the ones related to retrograde motion, not approximating ellipses.

I guess some people said renormalization theory is ugly, and I have heard some say the standard model is ugly. But compared to what?

Special relativity was very rapidly accepted around 1908-10. At the time, no one thought of it as Einstein's theory. It was hard to accept because it seemed so strange that motion would distort space and time. But what were the philosophical reasons? Maybe we will hear in another podcast.

Susskind says Universe is not Real

Another respected physicist has gone off the deep end. In a new video:

Why the Universe Is Not Real | Leonard Susskind

At first glance, the idea sounds absurd. The universe feels undeniably real. Galaxies exist. Space stretches outward. Matter occupies locations and evolves over time. How could the universe not be real?

In this video, we explore what physicists actually mean when they challenge the reality of the universe. “Not real” does not mean “does not exist.” It means something far more precise — that the universe we experience may not be fundamental. ...

0:00 The universe is not real. I know how that sounds. It sounds like philosophical nonsense, like something a stoned undergraduate would say at 3:00 in the morning. But I'm serious. After spending decades studying quantum mechanics, black holes, and the foundations of reality, I've come to a conclusion that would have shocked my younger self. The universe, as we experience it, is not fundamentally real.

He gives several arguments: (1) Schroedinger Cat is dead and alive simultaneously; (2) We only see one world of many-worlds theory; (3) Physical states are sometimes determined by a boundary condition, so we are a hologram; (4) At the Planck scale, quantum gravity teaches that spacetime breaks down; (5) Observations depend on what observers do.

Let me connect this to black holes again 13:16 because that's where these ideas become most concrete. When you fall into a black hole, you experience crossing the event horizon smoothly. From your perspective, the interior is real. You fall through space toward the singularity. But from the perspective of someone outside, you never cross the horizon. You appear to freeze at the horizon. ...

The fundamental 14:03 reality is the quantum state of the black hole,

He ends up concluding that the universe is not real. So what is real? The Tegmark mathematical universe and consciousness.

20:09 Everything you think is real, solid, definite, is actually quantum, abstract, probabilistic at the fundamental level. The classical reality is an illusion your brain constructs from quantum information. The universe is not real in the way you think it is. It's something uh far stranger. ...

Love is an emergent 21:23 phenomenon arising from brain chemistry, from evolutionary psychology, from social structures. Does that make it less real, less valuable? Of course not. ...

The 23:22 universe is not real in the naive sense. And that's one of the most important discoveries in the history of physics. It changes everything about how we understand reality and our place in it. ...

The universe is not real. 24:14 And that's the most profound truth about reality I've ever discovered.

He is a good illustration of how modern physics has gone wrong.

The Golden Age of Phyics was 1860-1935. Then everyone idolized Einstein for his foolish pursuit of unified field theory and rejection of quantum mechanics. Theoretical physicists studied quantum gravity, nonlocal interpretations, strings, holograms, black hole firewalls, many-worlds, landscape, etc., all to no end.

Susskind went through phases supporting all that stuff, and ends up denying reality.

He is now firmly in the existential crisis iceberg. Accepting what he says is the same as saying we live in a simulation, or that reality is a dream.

All his favorite theories -- hologram, many-worlds, Tegmark math universe -- leave no room for free will or scientific inquiry. He denies that it is nihilism, but that is exactly what it is. We are worse than rats in maze.

He goes wrong at the start, with the Schroedinger Cat. The Cat is just a simple example of uncertainty about two possible events. There is no deep math or physics involved. A child can understand that he might not know what is in a box. But it is very strange to make the leap from that to saying that the universe is not real. I do not think that I could convince a 4-year-old of that.

Susskind also has a new video:

Why Objects Don’t Really Exist | Leonard Susskind

Objects feel like the most basic elements of reality. Tables, chairs, planets, particles — the world appears to be built from things. It seems obvious that objects exist. But modern physics tells a very different story.

In this video, we explore why objects may not be fundamental at all. “Don’t exist” does not mean imaginary. It means that objects are not the deepest level at which reality is defined.

He talks about cats, fuzzy objects, ships with boards replaced, entangled particles.

Another video says:

Why Time Is a Byproduct | Leonard Susskind

We usually think of time as one of the most fundamental ingredients of reality. Everything seems to move through time. Causes come before effects. The universe appears to unfold moment by moment along an invisible timeline. But modern theoretical physics suggests a very different picture.

In this video, we explore the unsettling idea that time may not be fundamental at all. Instead of being the engine that drives reality, time may be a byproduct — something that emerges from deeper processes rather than causing them.

And another new video says black holes are not real:

Black holes are usually imagined as objects with a deep, hidden interior — a place where matter falls and disappears forever. This image is deeply ingrained in popular science. But modern theoretical physics suggests something far more surprising: black holes may not have an interior in the way we think.

In this video, we explore why physicists increasingly question the idea of a black hole interior. “No interior” does not mean nothing happens when something falls in. It means that the information describing that object is not stored inside the black hole as an internal structure.

He says he spent years trying to convince Hawking that if you throw a book into a black hole, then the information will eventually bubble out the surface. His main argument that there is no interior is that if the book fell down to the center, then it is hard to see how the info would ever get out.

He can get away with saying anything he wants about a black hole interior, because it is not observable. But he gets totally wacky and says wormholes are the same as quantum entanglement.

I see now that Susskind has just put out a lot of these videos. Have fun listening to erudite nonsense.

On second thought, I think I have been duped by AI slop. These podcasts have Susskind's voice and his his opinions, but they are more forcefully and coherently argued than he does in real life. I think some AI has scanned his lectures and writings, and made them more intelligible.

I semething similar with Roger Penrose. See Quantum Mechanics Is NOT Random. It is a very good summary of Penrose's view on the subject, and rendered in his own voice. Here is another on Gravity Isn't Pulling You Down — The Ground Is Pushing You Up, and one on Einstein Was Right: Past, Present & Future Are An Illusion — Here's The Proof.

These podcasts are the future of education, I am afraid. They are better than the real Susskind and Penrose, and faithful to their opinions and voices. Maybe we will not have live lectures anymore. Someone will give several lectures on a subject, and then an AI will distill, refine, and polish the material into a better lecture.

Getting back to the original topic, Susskind is not real. He is an AI reconstruction.

Has quantum advantage been achieved?

Dominik Hangleiter writes on his blog:

Recently, I gave a couple of perspective talks on quantum advantage, one at the annual retreat of the CIQC and one at a recent KITP programme. I started off by polling the audience on who believed quantum advantage had been achieved. Just this one, simple question.

The audience was mostly experimental and theoretical physicists with a few CS theory folks sprinkled in. I was sure that these audiences would be overwhelmingly convinced of the successful demonstration of quantum advantage. After all, more than half a decade has passed since ...

I could not have been more wrong.

In both talks, less than half of the people in the audience thought that quantum advantage had been achieved.

No, quantum supremacy has not been achieved, if most experts are not convinced. The whole was to do a public demonstration that convinces everyone that quantum computers are possible.

Dr. Bee Revives Nonlocal gravity

Sabine Hossenfelder posts a new video:

0:38 The laws of physics that we have discovered have one thing in common: they are local. This means that objects in two different locations cannot interact with each other. They don’t know anything of each other. ...

A bit like theorists and experimentalists. 0:53 It is only by sending some sort of signal from one object to the other that they can react to each other’s presence. We have no idea why the laws of nature are this way. There’s no particular reason why they should be. It’s just that it corresponds to our experience.

I would say that there are reasons. Locality is the whole basis of scientific reductionism. It allows us to do controlled experiments. Without it, we could never make sense out of the world.

Also, it is all a consequence of the non-euclidean geometry of spacetime.

1:09 Newtonian gravity is not local, this bothered Newton a lot back then. You see if you take Newton’s law of gravity, with the gravitational force proportional to the mass divided by the square of the distance, then if you move the mass, the distance increases and the force changes instantaneously, everywhere. Newton was greatly bothered by this. He called it “action at a distance” and that’s also what Einstein meant by the phrase.

1:39 Einstein’s theory of general relativity, which we use now to describe gravity, doesn’t have this problem. In Einstein’s theory, gravity is described by the curvature of space and time. And that curvature is caused by the mass and energy in spacetime. If you move the mass that causes spacetime to curve, then the curvature changes, but not instantaneously. The change spreads outwards at the speed of light

Actually it was Poincare who figured out that gravity propagates at the speed of light. Einstein did not accept or believe it.

And this nonlocal gravity just seems to do it. 4:18 Better still the idea that gravity isn’t entirely local is something you’d expect to naturally occur in a theory of quantum gravity because we know that quantum physics isn’t local. I really like the idea.

No, this is crazy talk. Quantum physics is just as local as general relativity. In cosmology, you could have a couple of orbits that are correlated, so that knowledge of one tells you something about the other. That's all people mean by quantum nonlocality.

A reader will surely say that no, quantum nonlocality means that a correlation could be quantitatively greater that what a believer in an alternative theory might expect. Yes, that is true, but it does not have a bearing on whether a theory is local or nonlocal.

In another video, she endorses the Einstein block universe.

Maybe this video more than anything explains why I've always been a bad 11:30 fit for academia. Because what really is this? Is it philosophy? Is it physics? It's neither here nor there. Yet for me, questions like this are the reason I studied physics because I want to understand how the universe works.

Academia has no need for her twisted ideas about how the universe works.

Elsewhere she expreses a belief in superdeterminism, but that contradicts some of what she says here. Maybe she has abandoned superdeterminism, but she ought to explain it.

quantum 9:43 physics has an indeterministic unpredictable element which is what happens the moment one makes a measurement. ... There seems to be a difference between the past and the future in quantum mechanics.

Most of the video is an argument that Einstein's relativity requires us to believe in the block universe, where the future is as real as the past. She says different coordinates are allowed, and so the meaning of "now" can be different for different observers.

This is a misunderstanding of relativity. Einstein was a determinist, and did believe in the block universe, but most physicists do not.

Yes, relativity does allow different coordinates, but that does not mean you have to accept another "now", or that the future is determined. Most physicists accept that the CMB radiation defines a universal now, without contradicting relativity.

Even if I accepted that there is no universal "now", and that my future is already in a past coordinate system for some other observer, it would not follow that my future is determined. She defines "now" by coordinate lines, not light cones, so an observer does not even see what is now for him.

Dr. Bee talks about many science topics outside her expertise. These two videos are squarely within her expertise, so I expect better.

Cantor's Diagonal Argument

Cantor's diagonal argument is famous for proving the uncountability of the real numbers. It is not so well known that Cantor's first set theory article proved it differently.

Here is the proof. First of all, we need to assume the completeness of the reals, in some form.

Theorem. If { A_k } is a collection of compact nested subsets of R, the real numbers, then the intersection is nonempty.

Compact means closed and bounded, like the interval [0,1], including the endpoints. Nested means each contains the next. The proof depends on how you have defined R. For example, you could get an intersection point as the least upper bound of the left endpoints.

This is a way of expressing the completeness of the reals. If we used the rationals instead, then we could have nested intervals about √2, and the intersection would not include any rational numbers.

To prove uncountability, suppose we have an enumeration { x_k } of R, and we seek a contradiction. We define a collection { A_k } with x_k not in A_k, and apply the theorem to get a real number in all the sets, and hence not in the enumeration.

Start with [0,1]. Let A₁ be a closed interval subset excluding x₁. Eg, if x₁ = 0.4, then A₁ could be [0,.3] or [.5,1]. Likewise, let A₂ be a subset of A₁ that excludes x₂, and so on, and thus A_k excludes x₁,..., x_k. Applying the theorem gives at least one real in all of the intervals, and hence not part of the enumeration.

This is really a diagonalization argument, and maybe less intuitive, so what's the point?

I like it better. The usual diagonal argument is deceptively simple, as it assumes facts about the reals, such as every decimal expansion converging to a real, and reals having unique decimal expansions, with certain exceptions. This is still a diagonal argument, gets more directly to the heart of the matter, and explicitly uses the completeness of the reals, without the distracting decimal expansions.

Cantor gave a similar diagonal argument to show that the cardinality of a set A is less than the set P(A) of all its subsets.

Suppose not, so that there is some onto function f: A -> P(A). That is, where f(A) = P(A). Then let B = { a in A : a not in f(a) }. If B = f(b) for some b in A, then b is in f(b) if and only if b is not in f(b), a contradiction. Thus the image of f cannot be all of P(A).

This shows that taking all subsets always gives a set of larger cardinality.

Scott Aaronson recommends a video on Cantor's diagonal argument.

Wild Enthusiasm for Quantum Computing

This new interview makes a lot of big claims for quantum computing:

Q-Day — when quantum computers crack all encryption — is coming. Quantum eMotion COO John Young breaks down the pros and cons of what’s to come.

It is all ridiculous. I could not even bear to listen to the whole thing.

I have gotten used to this sort of enthusiasm for AI. But a 100 million people use AI everyday. Quantum computing has very little hope of ever accomplishing anything.