Aaronson's Latest Lecture on Quantum Computers

Dr. Quantum Supremacy has posted a new lecture:

Title: The TRUTH About Quantum Computing
Date: 2026-05-13 @5:00PM

Abstract: Yes, scalable quantum computing should actually work! Sooner than many expect, which will create a huge headache when it breaks the encryption currently used to protect the Internet. But no, we don't think quantum computing can do most of what the popular articles promise in AI and optimization and so forth. Come to this talk to learn about why!

Somehow he has gotten to be the academic authority on whether quantum supremacy has been achieved, so I always check his latest opinion. He seems to be getting more confident, but it is still just a prediction. He says it may or may not be achieved. And that not to trust your RSA keys.

And another one:

Title: Scott Aaronson - Theoretical Computer Science and AI Alignment
Date: 2026-05-14 @1:00PM

Abstract: I'll survey some areas where I think theoretical computer science, math, and statistics can potentially contribute to the urgent quest to align powerful AI with humane values. These areas include: the watermarking of AI outputs, mechanistic interpretability (including Paul Christiano's "No-Coincidence Principle," and succinct digests of the training process to aid interpretability), and theoretical guarantees for out-of-distribution generalization.

Also on the subject, Dr. Bee dropped a new one today that starts:

In Einstein’s theory of general relativity, the time an object experiences depends on its acceleration. But time in quantum physics works more intuitively – it’s a universal parameter experienced by every object in the same way. In a new paper, physicists say they want to use a special type of clock to test that difference. Let’s take a look.

0:00 Quantum physics says that objects can be in two places at the same time. A group of physicists now says that they can also be at two times at the same time, ...

No, quantum physics does not say that objects can be in two places at the same time. It does not say that cats can be alive and dead at the same time.

Quantum computers are often explained this way, but QM really just estimates probabilities for different place. Once you observe the object, it is in just one place. Her statement is like saying: probability theory says that a tossed coin can be heads and tails at the same time.

Aaronson is an AI enthusiast: [11:40] AI is what "I would regard as, you know, maybe the most consequential technology, uh, that humans are ever going to be building."

Update: At the other extreme, Brian Greene released a new interview with an AI skeptic. The guy says that the AI LLMs are just a stupid trick of little value.

Sean M. Carroll Lectures on Many Worlds

NewScientist just posted a marathon series of math lectures, but almost half of it is from a 5-year-old lecture, Sean Carroll: The many worlds of quantum mechanics, that is not even on math. He gave a similar lecture last year, The Many Worlds of Quantum Mechanics | Dr. Sean Carroll.

My disagreements start early. Carroll says:

Why does 7:14 quantum mechanics have this reputation of being so hard? Here's the answer. There's an amazing feature of quantum mechanics that was nowhere to be found in classical mechanics which says that what you observe when you look at a system is not what you see.

What you see and what is really there are two different things. There's a difference between what a thing is when you're looking at it and when you're not looking at it. What you can possibly see is much less than what really exists. This sounds weird. This sounds bizarre. like it's very very different than what we had in classical mechanics.

He is trying to say that reality is the wave function, which is not directly observable.

The word see and observe are synonyms. I do not get his explanation. Even in classical physics, there are things we cannot see. We cannot see the center of the Earth.

You might think that in that 14:03 circumstance, since quantum mechanics is the foundational theory for all of modern physics, you might think that the quest to understand quantum mechanics at a deep level would be recognized as one of the most important things we could possibly do in physics. The people who devoted their lives to these would be academic superstars. You would have different universities trying to steal them away with highpriced packages and salaries and so forth. and it would be the highest prestige occupation you could have in physics.

Sadly, no, that is not what we do. It is the opposite of that. We have adopted a strategy of denial where if you're a physicist and you think hard about answering these questions, you are labeled not a physicist or a physicist who is too old to do important work anymore and you're sent off to retirement.

That is because the important issues were settled in 1930. People like Carroll want to be paid to do research on many-worlds, and real physicists consider it a complete waste of time.

36:37 Another what I think incorrect objection is that this idea cannot be tested. Can it be tested Right? It's important in science that we not just have good ideas, but that we compare these important ideas to data. Right? that we experimentally probe our ideas and people say you've invented all these new worlds. How do you ever test that idea?

The response to that is, I didn't invent any new worlds. I just took quantum mechanics seriously. The entirety of the assumptions that go into the many worlds theory is there are wave functions and they obey the Schroinger equation. That's it. Everything else is a consequence, a prediction and implication of those assumptions.

And are those assumptions testable? Hell yes they are. Of course they are. Whenever we do a quantum mechanical experiment, we're implicitly testing the many worlds interpretation.

If you want to falsify the many worlds interpretation, remember that the prediction of many worlds is wave functions don't collapse. They never do. They appear to collapse because of decoherence.

So there is no way to test many-worlds. He says it is logically correct, so everything you see confirms it. That's all.

As he admits, we see wave functions collapses. They would contradict many-worlds, except that he does not believe that they are really collapsing. He calls that a test.

This is all nonsense. I don't know why anyone takes him seriously.

Carroll also has to answer this new survey:

World's largest ever survey of physicists, results & reaction

May 12, 2026
What do physicists really think about the biggest mysteries in the universe?

In this video, leading voices in theoretical physics come together to unpack the results of the Big Mystery Survey—the largest survey ever conducted of professional physicists, prepared in collaboration with the American Physical Society's Physics Magazine." Featuring reactions from experts like Sean Carroll, Niayesh Afshordi and ,Ghazal Geshnizjani we find out what physicists really think about topics such as: What should we think about fine tuning ? What is dark matter? What is dark energy? How should we truly understand the Big Bang?What the right approach to quantum gravity ?

Whether you’re a physics enthusiast or just curious about the universe, this conversation offers a rare glimpse into how experts think about the unknown.

It reports 11% for many-worlds, 6% for Bohm pilot wave. These are the two crackpot interpretations. It is amusing to see how the leading popularizers of theoretical physics have views that are rejected by most physicists.

Carroll also has a lecture in this newly-released video on the physics of time and the history of relativity.

[4:50] All you have to do is entirely jigger your thoughts about what space and time are. And in fact, it wasn't until two years later when Hermann Minkowsky, who was a mathematician who had been one of Einstein's professors, said, "You know, the right way to think about Einstein's theory is to say that space and time aren't separate anymore. To imagine there's one thing called spacetime, and different people, different observers moving in different ways through the universe will divide it up into space and time differently.

There's no objective true fact about when I snap my fingers now what's happening light years away. That's going to depend on who's doing the observing and who is doing the measuring. ...

It can all be explained very beautifully by imagining a single four-dimensional spacetime instead of separate space and time. Einstein himself was not impressed by this move. ...

And when Minkowsky says, "I have some new math that unifies space and time based on Einstein's theories," Einstein himself is like, "I don't need that. That's like extra mathematical nonsense."

Minkowski never referred to "Einstein's theory", but got that 4D spacetime from Poincare. That 1907 Minkowski paper cited Poincare's 1905 paper with the 4D spacetime.

Yes, people like to credit Einstein for spacetime, but that was published by Poincare and Minkowski, and Einstein rejected it.

Carroll wrote a whole book on relativity, so he surely knows the history. It is weird that he gets it so wrong.

Update: The survey has just been posted in a paper.

We present results from the Big Mysteries Survey, a large-scale survey conducted through the American Physical Society's Physics Magazine on foundational and controversial topics in contemporary physics. The survey provides a snapshot of physicists' views on issues in cosmology, black-hole physics, quantum mechanics, quantum gravity, and anthropic coincidences. A central finding is that several positions often described publicly as field-wide ``consensus'' views are, in practice, supported by much narrower majorities or by pluralities rather than majorities.

19% believe string theory is the best hope for quantum gravity. 30% believe that information dropped in a black hole is preserved in Hawking radiation. 24% believe in the dark energy cosmological constant. No consensus on dark matter. 51% believe in cosmological inflation.

The Most Cited Physicist Alive

Brian Keating interviews Juan Maldacena, The Most Cited Physicist Alive.

Juan Maldacena is a theoretical physicist at the Institute for Advanced Study whose 1997 paper remains the most cited in the history of theoretical physics.

We cover:
-why wormholes and quantum entanglement may be the same thing
-what actually happens to information when you throw something into a black hole
-the reason Hawking radiation accidentally gave cosmologists the equation that explains why the universe has structure
-whether science-fiction wormholes are ruled out by the laws of physics
-the one unsolved problem Juan says matters more than black holes.

The most important problem in quantum gravity is understanding the beginning of the Big Bang — not black holes.

And also the Holographic Principle, AI, complex numbers, etc.

Someone from 50 or 100 years ago would really be disappointed at what a dead-end theoretical physics. He rambles from one absurdity to another, with barely any relation to the real world.

The universe is not locally real

AI has risen Feynman from the dead, and explained Bell's theorem:

The Universe May Not Be Locally Real – Feynman Explains Bell’s Paradox

What if everything you believe about reality is wrong? In this mind-bending 23-minute exploration, Richard Feynman walks you through one of the most unsettling discoveries in the history of science — Bell's Theorem and the Nobel Prize-winning experiments that proved the universe is not locally real. From Einstein's stubborn belief in hidden variables to the groundbreaking work of Aspect, Clauser, and Zeilinger, this video breaks down quantum entanglement, the EPR paradox, and what it truly means when particles separated by miles somehow "know" what the other is doing — with no signal, no instructions, and no classical explanation.

It concludes:

[20:05] Let me bring it all together. Now we started with a simple idea that the world is locally real that things have definite properties that distant objects can't affect each other instantly. John Bell took this idea and turned it into a testable prediction. He said if local realism is true then the correlations between entangled particles must obey a mathematical limit. experiments culminating in the Nobel Prize winning work of aspect, Clauser, and Zelinger showed that the correlations exceed that limit. Local realism is violated. The universe is not locally real.

This means one of two things, or possibly both. Either particles don't have definite properties before they're measured, meaning reality isn't real in the way we thought, or distant particles can somehow affect each other instantly, meaning the universe isn't local in the way we thought. We don't know which. We don't have a complete agreed upon interpretation of quantum mechanics that resolves this.

I think we do have an agreed QM interpretation. It is the first option. Nobody thinks distant particles can somehow affect each other instantly.

The QM textbooks say that under Heisenberg uncertainty, it makes no sense for a particle to have a definite position and momentum at the same time. Particles only get definite values for position and momentum when they are measured, and you cannot measure both at the same time.

So yes, QM says particles don't have definite properties before they're measured. And I think that is what Feynman would have said, and not that this is an unsettled question.

Not everyone agrees with this, as maybe 10% of physicists subscribe to goofy interpretations like Bohm pilot wave or many worlds. But the mainstream textbook QM view is pretty clear on this point.

Hassabis likes a Wacky Book

Demis Hassabis says:

[25:41] well, my favorite book is The Fabric of Reality by David Deutsch. So, I think that still holds. I'd hope to answer the questions in that book with with the AGI. That's my post AGI work.

Hassabis is a genius, and certainly one of the world's leading AI researchers. But I am lowering my opinion of him, if this is his favorite book.

At first glance, the book is a celebration of modern science. It is enthusiastic about science, theory, the scientific method, explanations, and testability. It explains what science is all about.

Except that it is really anti-science. For all his talk about the merits to testing theories, he mostly promotes theories that cannot be tested at all. For all his talk about reality, he mainly believes in things that are not real.

His favorite ideas are Popper's falsification, Darwin's evolution, and many-worlds quantum mechanics. He raves about their explanatory power.

These are so bizarre, because many-worlds is just an unscientific belief that cannot be falsified.

Darwin evolution has some explanatory power, but the main principle -- survival of the fittest -- is a tautology. Fitness is defined as what survives.

Deutsch starts the book by attacking Steven Weinberg for saying an instrumentalist remark: "The important thing is to be able to make predictions". Weinberg's point was anti-geometry, not instrumentalism, and he later changed his mind when geometry proved crucial for theoretical physics.

For a more up-to-date description of Deutsch's opinions, see this new interview of him. He says that he now believes in free will, because we have the ability to create novelty.

[1:18:36] By the way, Bryce DeWitt said that he was sure that if Einstein had lived another few years, he would have come to like the Everett interpretation, because it's fully realistic.

I am pretty sure that Einstein would have hated many-worlds. Regardless, it is bizarre to say that many-worlds is "fully realistic". It is the opposite of realistic. Nothing is more unrealistic than postulating an infinity of parallel universes that have no interaction with ours.

Crypto Doom in 2029

Dr. Quantum Supremacy announces:

Will you heed my warnings NOW?

Holy crap … yesterday I was elected to the US National Academy of Sciences! ...

See, some of the most reputable people in quantum hardware and quantum error-correction — people whose judgment I trust more than my own on those topics — are now telling me that a fault-tolerant quantum computer able to break deployed cryptosystems ought to be possible by around 2029. ...

And I’d say that that makes my own moral duty right now ironically simple and clear: namely, to use my unique soapbox, as the writer of The Internet’s Most Trusted Quantum Computing Blog Since 2005^TM, to sound the alarm.

So, here it is: if quantum computers start breaking cryptography a few years from now, don’t you dare come to this blog and tell me that I failed to warn you. This post is your warning. Please start switching to quantum-resistant encryption, and urge your company or organization or blockchain or standards body to do the same.

He co-authored a paper on the threat to Bitcoin.

I say the opposite. There is no need to switch, and there is no chance of a break by 2029. [corrected] But I am not a member of NAS. You have been warned. Check back in four years to see who is right.

Update: I looked at the consensus white paper, to see if it endorses the idea that quantum supremacy is inevitable or has already been proved. It does not:

A few distinguished mathematicians, computer scientists, and physicists, including Gil Kalai, Leonid Levin, Michel Dyakonov, and Gerard ‘t Hooft, have taken the position that quantum computing is impossible in principle—that what seem to others like engineering difficulties will in fact never be surmounted for some inherent reason. This could be true, for example, if quantum mechanics itself were to fail as we tried to scale up QC, or if we were to discover some new principle on top of quantum mechanics, which guarantees the existence of noise that violates the assumptions of the Threshold Theorem and therefore can’t be corrected by FTQC.

It’s important to understand that this was never a mainstream view among experts, at least since the discovery of FTQC in 1996. The mainstream view could be summarized by saying that, if quantum mechanics were to fail, or some new principle were to be discovered that “screens off” or “censors” QC, that would constitute a once-per-century revolution in physics, and would be vastly more surprising and exciting than “mere success” in building a QC that worked as the theory has long predicted. From a physics perspective, QC working as predicted is the conservative option.

So believing in QC is the conservative option, but it might not be possible.

How Hard Determinists Reject Free Will

New video:

Robert Sapolsky, Paul Bloom, and Lucy Allais debate whether free will exists and what this would mean for punishment and morality.

The deny free will, and are strong determinists.

0:33 [Host] So, Robert, um, do do you do you see your position as being driven by a defense of materialism or physicalism? Is that what is motivating you? That there's just no no alternative. you can't give any account of free will and therefore uh because you can't give an account of free will within the uh within the scientific framework uh you think that we have to then deny free will

[Sapolsky] basically I think by now the extent of scientific knowledge is such that it forms this matrix of explanation and that within that matrix um it is a purely materialistic one and every attempt to find free will lurking in there requires some sort of violation of show we know these matrices work. In that regard, I completely agree with Lucy um that trying to make sense of human behavior by going down to bosons is absurd.

I believe that this is just wrong as a matter of our scientific knowledge. There are no such completely deterministic matrices.

If you think I am wrong, tell me when did science prove determinism? Who wrote the paper? Who did the experiment? Who got the Nobel Prize? Why isn't this in textbooks?

Sapolsky just babbles gibberish when asked this question:

Isn't there still the question of well you presumably have made a decision uh at some level to take part in this debate. you you uh wrote a book trying to convince people of uh the idea that we should see free will as an illusion. And you were presumably doing that because you wanted to change their minds. But what was the point if they couldn't change their minds in the first place?

Sapolsky is probably the leading academic opponent of free will, and he is a crackpot.

Keating Sells Out for Quantum Hype

Great progress in quantum computers was announced a couple of weeks ago, and I posted comments by Scott Aaronson and Sabine Hossenfelder. Now another popular physicist channel has weighed in, attacking her:

Quantum Computers Are Useful. You're Using Them Wrong.

Dr Brian Keating
338K subscribers

Sabine Hossenfelder says quantum computers are only useful for breaking codes. She's wrong — and my undergraduates are building the proof. What's happening in my lab right now has nothing to do with cryptography, and everything to do with the future of AI.

I'm a cosmologist at UC San Diego teaching undergraduates to build, program, and eventually launch quantum computers — possibly to the Moon via Artemis!

We cover: why Sabine's code-breaking verdict misses the real story, how free tools like Quantum Rings are closing the education gap Sabine thinks is a hardware problem, why Q-Day just got moved up to 2029, what my students are actually doing with quantum computers in my lab, and why the next generation of quantum physicists won't need a billion-dollar facility to train.

The bottleneck isn't the hardware. It's what we're teaching — and who we're teaching it to.

The whole video seems like a paid infomercial for a startup called Quantum Rings. He even shows a clip of a class teaching:

[7:25] Another thing I think is fun is that we can more intuitively see how I squared equals minus 1.

He argues:

[4:45] What are they actually good for these quantum computers? Sabine said, and I'm paraphrasing, that apart from the codebreaking, nobody has figured out how to turn quantum computing theoretical advantage into a real world. Quantum chemistry, material science, optimization, financial modeling. She says not much there has happened. And again, if you're looking at published breakthroughs, she's not wrong.

And see above, as I said, quantum computers are awesome, unrivaled at simulating how quantum computers work. But Sabine is looking perhaps at the wrong metric. The revolution isn't in the papers. It's in the tooling.

5 years ago, if you wanted to run a quantum circuit, you needed to access IBM's cloud. You'd wait in a huge long queue. You'd get a noisy result on maybe 20 cubits, even if you could figure out how to use it, and you'd spend more time debugging the interface than doing actual physics. Today, I'm going to show you something, a free tool where you can use and learn about quantum computing. It's called Quantum 101. It's by Quantum Rings, a quantum computer circuit simulator that runs on your laptop. Not 20 cubits, hundreds of them. Millions of gate operations, high fidelity on your desktop, on your laptop for free. They replicated Google's quantum supremacy experiment.

So there is no published research that show quantum computers are good for anything, but you can just prove it for yourself on a laptop and a free demo account from a startup?

Oh wow, I thought Keating was more honest than this.

There is a Nobel Prize waiting for the first person to prove quantum supremacy. The idea is comical that you can do it on your laptop but no one has bothered to publish it.

Physicist Angela Collier posts a video on physicists don't know how planes work, largely about some predictions Lord Kelvin made in a 1900 interview. In particular, he said that heavier-than-air-flight would never work. She says we should not have expected him to be wise outside his specialty, and he had no expertise in flight.

Here is another example of an expert predicting outside his expertise:

Live Science spoke with physicist David Gross, who today received the $3 million "Special Breakthrough Prize in Fundamental Physics". He was part of a trio that won the 2004 physics Nobel prize for research that helped complete the Standard Model of particle physics. But when asked if physics will reach a unified theory of the fundamental forces of nature within 50 years, Gross has a surprising answer. "Currently, I spend part of my time trying to tell people... that the chances of you living 50 [more] years are very small."

Live Science: So what do you suggest as remedies to lower that risk?

Gross: We had something called the Nobel Laureate Assembly for reducing the risk of nuclear war in Chicago last year.

His prize was for quark interactions. We have no reason to believe he is wiser about nuclear war than anyone else.

If he were correct, then I would expect him to favor nuking Iran, in order to stop them from developing a bomb. But I do not hear him saying that.

I am not criticizing these people for having opinions on quantum computing. They are physicists, and probably friends with some of the researchers in the field, even if they are not in the field themselves. I just want to hold them to their predictions. The Bulletin of the Atomic Scientists warned of nuclear war for years, and then moved its clock close to midnight just when everyone else thought that the chance of war was reducted. The fact is that nukes have kept keep the peace, so far.

Special Relativity was Announced in 1904

Relavity historians give 1905 for the theory's origin, but it was really 1904.

Hector Giacomini writes in a new paper, also here:

Henri Poincaré’s Saint Louis lecture, delivered on 24 September 1904 at the International Congress of Arts and Science, occupies a distinctive place in the pre-history of twentieth-century theoretical physics. In this text, Poincaré formulated the principle of relativity in explicit and general terms, not as a narrow empirical rule limited to electrodynamics, but as one of the major guiding principles of mathematical physics. The lecture also offered a principle-based conception of theory centered on invariance, least action, and general theoretical coherence.

Poincare and other great scholars made the trip all the way to St. Louis, Missouri, USA, where the World's Fair was being held. For a month, St. Louis was the center of the world.

The text of the lecture was widely published and distributed in 1904, and an English translation was published in a popular philosophical journal in Jan. 1905. The above paper documents the wide distribution.

Poincare's lecture did not have any formulas, but he clearly had the essence of special relativity.

He wrote two kinds of papers. Technical papers with formulas intended for mathematicians, and papers without formulas intended for a wider audience. He was probably the most widely-read intellectual in Europe. Perhaps some did not appreciate him because he did not attempt to explain the formulas to non-mathematicians.

In explicit and programmatic terms, Poincaré formulated the principle of relativity as follows: the laws of physical phenomena must be the same for an observer at rest and for an observer carried along in uniform translational motion. Consequently, no experiment should allow one to determine whether one is in such uniform motion or not. In the lecture this formulation appears within the canonical list of fundamental principles and is treated on the same conceptual level as energy conservation and the principle of least action.

The relativity principle is not introduced merely as an empirical summary of ether-drift experiments. Rather, Poincaré presents it as a structural requirement increasingly supported by the persistent failure of attempts to detect motion relative to the ether. He discusses in particular the negative results of Michelson-type experiments and emphasizes the remarkable stability of electromagnetic theory under uniform motion. The continued empirical confirmation of null results is interpreted as evidence that the invariance of physical laws under uniform translation may reflect a deep structural property of nature. ...

In this respect, Poincaré’s principle of relativity appears as the explicit crystallization of themes already articulated in his writings [11, 12, 13], and made accessible to German-speaking readers through the 1904 translation of La science et l’hypothèse [14]. Poincaré further analyzes the theoretical devices introduced to preserve this invariance. He discusses Lorentz’s notion of “local time”, obtained by synchronizing clocks through light signals ...

Importantly, Poincaré suggests that the situation may ultimately require a new mechanics in which no velocity could exceed that of light and in which inertia would increase with speed. Such remarks indicate that the principle of relativity is not treated as a peripheral correction within classical mechanics, but as a constraint capable of reshaping its conceptual structure.

Lorentz’s 1904 Theory

An important component of the lecture is Poincaré’s discussion of Hendrik Antoon Lorentz’s recent work. In May 1904 Lorentz had published a major paper [6]. In that work Lorentz presented a refined mathematical formulation of the transformations required to preserve the form of Maxwell’s equations in a moving frame.

Poincaré’s lecture demonstrates that by September 1904 he was fully aware of the structure and implications of Lorentz’s construction. He describes the introduction of local time, the contraction hypothesis — according to which bodies moving through the ether undergo a physical contraction in the direction of motion — and the modification of forces and masses required to reconcile theory with experiment.

The paper makes no mention of Einstein, as he did not write anything on relativity until Summer 1905.

Poincare wrote his great relativity paper in 1905, but his 1904 lecture has the essence: the relativity principle, Lorentz transformations, length contraction, Michelson-Morley, clock synchronization, local time, and a new mechanics where nothing goes faster than light.

Previously I argued that the essence of relativity was the 4D spacetime, Lorentz group, non-euclidean geometry, covariant equations, and extending beyond electromagnetism. Poincare had all these in 1905, and Einstein did not understand them until years later.

Einstein sometimes denied that he knew about Lorentz's 1904 paper and Poincare's 1905 paper, although it is documented that he had access to both before submitting his own 1905 paper. I do not know if he was ever asked about Poincare's St. Louis lecture. It is hard to believe he could have missed it, as it was read by anyone with an interest in Mathematical Physics.

Einstein did not reference Lorentz or Poincare in his famous 1905 relativity paper. Even if he really did not know about these papers, he surely knew about them when he wrote survey papers on relativity a couple of years later.

You could also argue that relativity started in 1895, with Lorentz's paper. He had the approximate Lorentz transformations, Michelson-Morley to second order, local time, length contraction, and relation to Maxwell's equations. Lorentz got the 1902 Nobel Prize for his electromagnetic theory. He did not have the higher order theory he found in 1904, the symmetries as a group, and connecting local time to clock synchronization.

Ready to Warn Us about Broken Cryptography

Prof. Scott Aaronson really wants us to believe in quantum computing, and the press regularly asks him to comment on the latest developments, many of which are bogus. So now he posts:

Then one evening, you hear a howl in the distance, and sure enough, on a hill overlooking the town is the clear silhouette of a large wolf. So you point to it — and all the same people laugh and accuse you of “crying wolf.”

Now you know how it’s been for me with cryptographically relevant quantum computing.

No, the wolf not there yet. Some are predicting 2030. I say there is no chance of that.

A comment says:

I see you’re following in the footsteps of Eliezer Yudkowsky, getting so frustrated at people not understanding what you’re saying that you resort to explaining the basic principles of rationality in hope that this will help.

Meanwhile the NY Post reports:

The CIA used a futuristic new tool called “Ghost Murmur” to find and rescue the second American airman who was shot down in southern Iran, The Post has learned.

The secret technology uses long-range quantum magnetometry to find the electromagnetic fingerprint of a human heartbeat and pairs the data with artificial intelligence software to isolate the signature from background noise, two sources close to the breakthrough said.

It was the tool’s first use in the field by the spy agency — and was alluded to Monday afternoon by President Trump and CIA Director John Ratcliffe at a White House briefing.

I do not know anything about it.

Update: Sabine Hossenfelder Quantum Computers Just Got Much More Dangerous. She cites Google predicting Q-day for 2029, when quantum computers break popular cryptosystems.

Google has never realized its quantum predictions. I am glad to see it predicting 2029. That is only 3 years. We shall soon see. I say no chance.

Particles do not Pass Both Slits

The double-slit experiment is often explained as particles going through both slits. Supposedly this quantum mechanics interpretation was made rigorous by R.P. Feynman's path integral formulation, where particles take all possible paths.

This is not really correct, as explained in a new video: Debunking Veritasium: The “All Possible Paths” Myth & What Feynman Really Showed

Curt Jaimungal rigorously debunks the viral myth popularized by Veritasium (that quantum particles literally take “all possible paths” has been proved) and clarifies the true mathematical purpose of Feynman's formalism. Learn why this concept is a computational tool in configuration space rather than a physical map of reality.

People doing quantum computing are always talking about an electron being in two places at once, like the Schroedinger Cat that is alive and dead at the same time. The many-worlds fans especially like to talk this way. It these things do not happen in standard textbook quantum mechanics.

In textbook/Copenhagen QM, does not have a defined position until it is measured. It does not get observed in two places.

Update: A reader points out that the video is almost a year old.

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.