Plants have transformed the surface of the earth and the contents of our atmosphere. To do this they’ve developed elaborate systems of roots and branches which (sometimes) follow uncanny mathematical patterns such as the Fibonacci sequence. Sandy Hetherington leads Edinburgh’s Molecular Palaeobotany and Evolution Group, they take a no-holds-barred approach to understanding plant development by … Read more
Coffee table conversations with people thinking about foundational issues. Multiverses explores the limits of knowledge and technology. Does quantum mechanics tell us that our world is one of many? Will AI make us intellectually lazy, or expand our cognitive range? Is time a thing in itself or a measure of change? Join James Robinson as he tries to find out.
9| The Hunt for Hydrogen — Rūta Karolytė
byJames Robinson
Does the Earth contain enormous clean energy reserves? For many years the received logic was that hydrogen does not occur naturally in significant quantities without being bound to other atoms (such as in H20, water, or CH4, methane). To obtain the gas — whether as a fuel or for use in fertilizers — we need to strip it from those molecules, typically by electrolysis and steam reformation. But our understanding may be ripe for change.
Rūta Karolytė is at the vanguard of prospectors looking for large, naturally occurring reservoirs of hydrogen. She’s a researcher from Oxford specializing in the geochemistry of the Earth and she enlightens us to the mechanisms that are likely to be producing hydrogen in the crust: radiolysis and serpentinization.
In reviewing the evidence for naturally occurring hydrogen Ruta leads us through exotic terrain: a Soviet-era theory of hydrocarbon production, fairy rings, hydrothermal vents, and chemosynthetic life.
If Rūta and her colleagues are correct, the tapping of natural hydrogen could have transformative consequences for the Hydrogen economy such as cutting out the substantial fossil fuel emissions associated with deriving fertilizers from methane or creating a cheap basis for building synthetic fuels.
In the first half of the show, we also delve into carbon sequestration — another cool climate topic. But I’ve got so excited writing up the first half, that I’ll leave it here.
For many years scientific consensus has averred that hydrogen does not occur naturally in significant quantities without being bound to other atoms (such as in H20, water, or CH4, methane). To obtain the gas — whether as a fuel or for use in fertilizers — we need to strip it from those molecules — typically by electrolysis and steam reformation. But our understanding may be ripe for change.
Website of National Renewable Energy Laboratory from February 2023, following the publication of a New York Times article on natural H2, the text was changed to “Because hydrogen typically does not exist freely in nature” (emphasis mine)
Rūta Karolytė is at the vanguard of prospectors looking for large, naturally occurring reservoirs of hydrogen. She’s a researcher from Oxford specializing in the geochemistry of the Earth and she enlightens us to the mechanisms that are likely to be producing hydrogen in the crust: radiolysis and serpentinization.
In reviewing the evidence for naturally occurring hydrogen we pass through exotic terrain: a Soviet-era theory of hydrocarbon production, fairy rings, hydrothermal vents and chemosynthetic life. These organisms, remarkably, do not depend on the sun, plants, or any other life forms for their energy. Instead, they draw directly from the power stored in inorganic compounds. Their existence is testimony to the natural occurrence of hydrogen.
This does not guarantee that hydrogen is present in large quantities, but modeling of the processes that produce it — particularly serpentinization — suggests it is. Serpentinization is a kind of rusting whereby rocks are oxidized and hydrogen is freed from water molecules, wherever water and the right kinds of rocks are present and the pressure and temperature are right, hydrogen will be produced. What is more this process could be sped up by the introduction of more water underground.
If Rūta and her fellow prospectors are correct, the tapping of natural hydrogen could have transformative consequences for the “Hydrogen economy” — such as cutting out the substantial fossil fuel emissions associated with deriving fertilizers from methane or creating a cheap basis for building synthetic fuels.
In the first half of the show, we also delve into carbon sequestration — another cool climate topic. But I’ve got so excited writing up the first half, that I’ll leave it here.
Coffee table conversations with people thinking about foundational issues. Multiverses explores the limits of knowledge and technology. Does quantum mechanics tell us that our world is one of many? Will AI make us intellectually lazy, or expand our cognitive range? Is time a thing in itself or a measure of change? Join James Robinson as he tries to find out.
8 | Harald Wiltsche — Thought Experiments, Mach, Galileo & Phenomenology
byJames Robinson
Thought experiments have played a starring role in physics. They seem, sometimes, to pluck knowledge out of thin air. This is the starting point for my discussion this week with the philosopher Harald Wiltsche: what are thought experiments?
How do they function — are they platonic laboratories with no moorings in observations or a way of supercharging our reasoning about phenomena?
What do they deliver? Much emphasis has been put on the paradigm-shattering insights of Einstein where thought experiments appear like midwives in the production of new theories. But they can also function in explaining those theories, in ensuring they are understood.
This leads to the question: what is understanding? Harald argues that it’s the ability to manipulate or deploy knowledge backed up by a mental model. He reasons that thought experiments can help us to make sense of the abstraction of mathematical models.
We discuss many topics: the mathematization of science with Galileo, where thought experiments go wrong, transcendental arguments, the danger of losing sight of physical phenomena, and the links between Husserl and Mach. The theme that we dance to is this: there are lots of forms of reasoning that can work well within physics and we need equal pluralism in our philosophy of science to understand its startling, uncanny success in modeling nature.
Harald’s website haraldwiltsche.com where you can find many of his papers and the introduction to his book with Phillipp Berghoffer on Phenomenological Approaches to Physics
Thought experiments have played a starring role in physics. They seem, sometimes, to pluck knowledge out of thin air. This is the starting point for my discussion this week with the philosopher Harald Wiltsche: what are thought experiments?
How do they function — are they platonic laboratories with no moorings in observations or a way of supercharging our reasoning about phenomena?
What do they deliver? Much emphasis has been put on the paradigm-shattering insights of Einstein where thought experiments appear like midwives in the production of new theories. But they can also function in explaining those theories, in ensuring they are understood.
This leads to the question: what is understanding? Harald argues that it’s the ability to manipulate or deploy knowledge backed up by a mental model. He reasons that thought experiments can help us to make sense of the abstraction of mathematical models.
We discuss many topics: the mathematization of science with Galileo, where thought experiments go wrong, transcendental arguments, the links between Husserl and Mach — it was the latter’s emphasis on grounding physics in phenomenona that inspired the phenonomenological tradition in philosophy.
While there are many notes we touch on, the theme that we dance to is this: there are lots of forms of reasoning that can work well within physics and we need equal pluralism in our philosophy of science to understand the its startling, uncanny success in modeling nature.
How well does ChatGPT do with thought experiments?
Pretty well.
This question came up when discussing understanding. Large language models are certainly adept at manipulating symbols in ways that sound convincingly human, but how well do they in reasoning (or appearing to reason) about physics?
I go through two sets of prompts here, the second — where I prompt it with a thougth experiment that gets increasingly bizarre — is the more intriguing. It’s possible in all of these cases that a similar experiment has somewhere been discussed and ChatGPT is esstially parroting someone else’s understanding, however, the setup is rather complex: a helicopter magnetically levitating a butterfly in a plastic plane — has that really been dicussed before? I think one is forced to concede that it appears to have a good grasp of the physics.
Asking ChatGPT (GPT4) to think up a thought experiment
User Can you construct a thought experiment to explore the issue of whether space is absolute or relative, the ingredients in the experiment are two brass balls, scissors and a ribbon
ChatGPT Absolutely, let’s consider a thought experiment, that could potentially show how to understand the difference between the concepts of absolute and relative space.
First, let’s define these terms for clarity:
Absolute Space: This refers to the Newtonian concept of space, which exists independently and objectively, as an unchangeable and infinite background where all physical events occur.
Relative Space: This refers to the Einsteinian concept of space, where space doesn’t exist independently of the things within it. Instead, space and time are interwoven into a four-dimensional fabric known as spacetime, and the presence of mass and energy can distort this spacetime fabric. This is the basis of Einstein’s theory of General Relativity.
Now, let’s proceed to the thought experiment:
Imagine you’re in a spaceship with no windows, floating in deep space, far away from any celestial bodies. In this spaceship, you have two brass balls, a ribbon, and a pair of scissors.
You tie the two balls together with the ribbon and hang them in the middle of your spaceship. Since you’re in deep space with no other forces acting on your spaceship, the balls just float there, not moving relative to the spaceship.
Experiment 1: Now, you give your spaceship a slight spin. After a while, you notice that the balls are now rotating around the center of the spaceship, the ribbon taut, maintaining a fixed distance from each other due to the centrifugal force caused by the rotation of the spaceship. In this case, from the perspective of Newton’s absolute space, you’ve imparted a rotation on the spaceship, and the balls are simply responding to this by moving in a circle.
Experiment 2: Now, imagine an alternate scenario where your spaceship remains stationary, but all the universe around it starts to spin instead. According to the principle of relativity, you wouldn’t be able to tell the difference between these two situations from inside the spaceship. The balls would behave in exactly the same way, spinning around the center due to what appears to be the centrifugal force. However, this time, according to the relative space concept of Einstein’s General Relativity, the mass-energy of the universe spinning around the spaceship would distort the spacetime around it, creating a frame-dragging effect which leads to the balls’ circular movement.
This experiment illustrates that whether space is absolute or relative can dramatically change our interpretation of the same phenomena. Although this is just a thought experiment and not a practical one (we can’t spin the entire universe), it highlights the difference between the Newtonian concept of absolute space and the Einsteinian concept of relative space.
User If a butterfly is inside a plane, but flying — so not on the seats — does the plane need to generate more thrust to maintain altitude than if the butterfly were absent?
Asking ChatGPT (GPT4) to reason through a thought experiment
ChatGPT The plane doesn’t need to generate any additional thrust to maintain altitude whether a butterfly is flying or resting within the airplane cabin. This is due to the principle of conservation of momentum.
In the closed system of the airplane, the mass and the momentum are conserved. This means that the butterfly’s presence, flight, or rest doesn’t change the total momentum of the plane. When the butterfly is flying, it pushes air downwards to generate lift. The air pushes back on the butterfly, but it also pushes (very slightly) on the plane. The sum of these forces and reactions remains constant, so no extra thrust from the plane’s engines is necessary to maintain altitude.
In other words, when the butterfly takes off from a perch inside the airplane, it imparts a slight force to the airplane in the opposite direction. But as it flies around, all the movements it makes, the flapping of its wings, the changes in direction, etc., just redistribute the mass and momentum within the plane. The net effect on the plane is zero.
The situation would be the same whether the object in question is a butterfly, a bird, or a passenger walking down the aisle. As long as the action takes place within the closed system of the plane, it won’t affect the thrust needed to maintain the plane’s altitude or direction.
User But if the butterfly were absent, wouldn’t the plane weigh less and therefore less thrust would be required?
ChatGPT You are correct that if the butterfly were not present at all, the total weight of the airplane would be marginally less by the weight of the butterfly. The plane would therefore need a tiny amount less lift to maintain altitude, and consequently a tiny amount less thrust to maintain a particular speed.
However, once the butterfly is on board the plane, whether it is flying within the cabin or resting doesn’t affect the thrust required to maintain the plane’s altitude. This is because the weight of the plane system (including the butterfly, passengers, seats, etc.) is the same whether the butterfly is in flight or at rest.
In simpler terms, the energy required to lift the butterfly against gravity is still accounted for within the closed system of the plane, whether the butterfly is using its own wings to stay aloft or if it’s sitting on a seat.
So, to summarize, the plane does weigh less if the butterfly isn’t there at all, which would mean slightly less thrust is required. However, if the butterfly is present in the plane, whether it’s flying or not doesn’t make a difference to the thrust required.
User What happens if the inside of the plane were a vacuum and the butterfly could levitate (perhaps magnetically) inside the plane, would it contribute to the weight of the plane’s contents then?
ChatGPT Your scenario is a fascinating one. If we’re assuming the butterfly can somehow levitate magnetically, in a vacuum, inside the plane, then the answer to your question is yes, the butterfly still contributes to the total weight of the plane.
In this case, even if the butterfly is levitating, it doesn’t escape the pull of gravity. The butterfly still has mass, and the Earth’s gravity still acts on it, exerting a force (its weight). That gravitational force doesn’t disappear when it levitates; instead, it’s just counterbalanced by another force (in this case, a magnetic one).
This means that the butterfly’s weight still contributes to the overall weight of the plane. So if the butterfly weren’t present at all, the plane would be marginally lighter by the weight of the butterfly, regardless of whether it’s levitating or not.
The important point here is that gravity acts on all mass, regardless of its state or position. A levitating object in a gravitational field is still subject to gravity and still contributes to the total weight of the system it’s part of.
User What if the plane were made of plastic, and the magnetic force holding the butterfly in place was one due to a helicopter flying above the plane, would it still contribute to the weight of the plane and thus lead the plane to require a tiny amount more thrust than if the butterfly were absent?
ChatGPT If the magnetic force attracting the butterfly is not coming from the plane itself, but from an external source like a helicopter above it, then the situation changes.
In this case, the force that’s supporting the levitating butterfly is not being applied by the plane, but by the helicopter. So, the weight of the butterfly (which is the force of gravity acting on its mass) is essentially being “transferred” to the helicopter, not the plane.
Therefore, in this specific scenario, the butterfly’s weight would not contribute to the total weight of the airplane while it’s levitating. As a result, the plane would not require more thrust to maintain altitude than if the butterfly were completely absent.
However, remember that this situation is based on quite a few assumptions that would be very difficult to realize in the real world, and it doesn’t take into account other potential factors that could affect the plane’s flight.
Coffee table conversations with people thinking about foundational issues. Multiverses explores the limits of knowledge and technology. Does quantum mechanics tell us that our world is one of many? Will AI make us intellectually lazy, or expand our cognitive range? Is time a thing in itself or a measure of change? Join James Robinson as he tries to find out.
7| Anna Lewis — Genomics, polygenic risk scores, genetic ancestry, race & ethics
byJames Robinson
Genomics is leading a revolution in our understanding of disease. But the ways we pursue genomics research and the use we make of that knowledge demand careful thinking.
Anna is a researcher at The Edmond & Lily Safra Center for Ethics at Harvard, she holds a PhD in Systems Biology from Oxford (where we met) and has worked in medtech startups. As someone who has looked at genomics from multiple perspectives, she’s an excellent guide to this rocky terrain.
Anna emphasizes the challenges and importance of polygenic traits and Polygenic Risk Scores (PRS). While they are key tools in understanding and predicting traits, they are subject to misinterpretation and misuse if not properly defined. The concept of ‘race’ and more recently ‘continental ancestry group’ often used in the calculation of PRSs can lead to misguided or even harmful assumptions, potentially propagating racist ideologies. Instead, Anna suggests the use of Ancestral Recombination Graphs (ARG) to better represent an individual’s genetic ancestry.
Through ARG, we can achieve a more scientifically accurate and ethically sound basis for research. As we continue to make leaps in genomics and potentially influence traits like intelligence or strength, the importance of ethical, legal, and social implications becomes increasingly crucial. As we learn to wield our scientific tools, we need to understand how we should use them.
Over the past two decades, the cost of sequencing a whole human genome has fallen ten million-fold. However, the advances in sequencing have not equally progressed our understanding of the genetic code. Alongside the scientific struggle to interpret the Book of Life, we must also confront the ethical and social issues brought up by ongoing research.
Anna Lewis, a researcher at the Edmond & Lily Safra Center for Ethics at Harvard, guides us through some of the most complex issues in this field in this week’s episode. She discusses the use of polygenic risk scores, and how a poor choice of scientific framework can hinder medical advances, or even worse, lend support to racist ideologies.
In 2003, the Human Genome Project announced it had sequenced the 3.2 billion base pairs that constitute the human genetic code, more precisely the genetic code of a few humans, on just one-half of each chromosome. This project cost around $3 billion and took thirteen years. In 2023, it takes less than 24 hours and under $300 to sequence a whole genome. The learning rates for renewable technology and computing (Moore’s law) pale in comparison, making genomics a leading candidate for the technology that has seen the steepest price declines in history.
Proteomics and gene editing have also witnessed revolutionary advances in recent years:
Protein folding: Google’s DeepMind unveiled AlphaFold in 2021, a deep learning model that can predict the shapes formed by proteins with speed and accuracy, thus enhancing our ability to understand their functions.
CRISPR: a technology that adopts the mechanism by which bacteria splice in DNA from their predators (phages) to remember them. CRISPR allows for low-cost copy-paste editing of DNA.
Despite these breakthroughs, Anna points out that many problems remain partially understood. One of the deeper reasons for this is the highly complex interactions of genes. Prior to the sequencing of the human genome, scientists anticipated they would find 80,000 – 140,000 genes. Instead, depending on our understanding of the term ‘gene’, they found 20,000 – 30,000. This initial overestimate reflected an under-appreciation of the intricacies of how genes coordinate their functions.
Pathologies such as Huntington’s disease and hemophilia can be traced very clearly to single genes. In many cases, health outcomes depend on multiple genes; or single genes that lead to disease may not always be expressed (“switched on”), furthermore, non-human DNA can play a role in health. Epigenetics and hologenomics are two fast-developing fields that study, respectively, the mechanisms driving the expression of human genes and the importance to the health of non-human cells such as those in the gut microbiome.
We have transcribed The Book of Life, but we do not yet know how to read it. Not fully.
As a consequence, progress in medical technology has not kept pace with the improvements in gene sequencing. It should be conceded, however, that this lag is also due to the essential regulatory hurdles involved in bringing therapies safely to market. Undoubtedly, a similarly rigorous framework for AI would have prevented Language Learning Models (LLMs) such as ChatGPT from emerging as early as they did.
Nonetheless, there is cause for optimism in the treatments of monogenic diseases such as Huntington’s, hemophilia, and Duchenne’s muscular dystrophy. But for the many human traits, whether pathogenic or not, that are polygenic — and thus depend on the expression of multiple genes — progress is slower. Considering that 12,000 genetic variants influence height we can appreciate the difficulties of linking traits back to the genome.
One of the tools developed to cut through this complexity is the Polygenic Risk Score (PRS). By examining a population, researchers apply statistical methods to understand how the frequency of occurrence of a trait (for example, type 2 diabetes) correlates with the genes observed. This is used to predict the probability of a trait based on an individual’s genome, with varying results. One of the key factors in the efficacy of such scores is that the genome for which risk is being calculated is similar to those sampled in the population. But what does that mean?
Population, Anna argues, is a term with a dangerously confusing array of meanings. The population of New York is a number, but it also represents a group of people who do not necessarily share anything meaningful for the purposes of genomics. In the past, PRSs have relied on concepts of race for creating a sample set and understanding the portability of results from that set to other individuals. However, while race remains an important and valid variable for studies in sociology and economics—for example, in understanding and correcting for the historical and ongoing consequences of discrimination—it lacks a scientific basis. Race is a social construct subject to shifts and changes; who is considered “white,” for instance, has more to do with power structures than phenotype. A century ago, Southern European immigrants to the USA were not counted as such.
Recently, there has been a move away from race to the notion of genetic ancestry. However, Anna and her colleagues have observed that unless properly defined, this risks being no more than race renamed. In particular, if genetic ancestry is understood as simple continental groupings—East Asian origin, and so forth—it neither serves science nor society. On one hand, it fails because these groupings do not accurately represent genomically salient features. For example, a continental African grouping contains as much diversity as all other groups combined. On the other hand, by suggesting it has scientific meaning, the use of these groupings may inadvertently propagate racist ideologies.
It is crucial to correctly develop Polygenic Risk Scores. If done correctly, medical advice and interventions can be more effectively targeted. Anna and her colleagues argue that the most appropriate way to understand genetic ancestry is through the Ancestral Recombination Graph (ARG). Unlike continental ancestry groupings, which are flat in time and wide in extent, the ARG looks at how an individual’s DNA has been traced back from various different points and places in time. It traces how an individual’s genome branches out back in time among ancestors.
The ARG is much more specific than continental groupings. However, because genes tend to be passed down in chunks rather than individually, it offers sufficient coarse-graining to highlight where variations are significant and apply metrics for grouping people such that highly predictive PRSs can be calculated. The ARG is a precisely defined and scientifically meaningful object, lacking the connotations of race. As Anna and her colleagues put it in their recent paper, this gets genetic ancestry right for science and society. So far the research community is yet to combine ARGs and PRSs, Anna and her colleagues’ paper is a rallying call to do so.
To make the most of this window of opportunity to move away from race as a biological variable, we would urge the adoption of a multidimensional and continuous conceptualization of ancestry, free wherever possible of population categories, and not relying on continental labels that bear striking resemblance to prior racist groups.
Anna Lewis et al, Getting genetic ancestry right for science and society. Science. 2022 Apr 15
Anna and I studied together at Oxford, starting our degrees in 2003, just as the human genome was first sequenced. It has been a pleasure to follow her career since then, through a PhD in systems biology, medtech startups, and back into academia. More technological and medical breakthroughs are on the horizon—perhaps polygenic CRISPR edits will allow us to influence intelligence, strength, and tendency towards violence. The work that Anna and others are doing in the ELSI field (Ethical, Legal & Social Implications) is crucial to the choices we will make as a species.
We are learning how we can use our tools, we need to be mindful of how we should use them.
Coffee table conversations with people thinking about foundational issues. Multiverses explores the limits of knowledge and technology. Does quantum mechanics tell us that our world is one of many? Will AI make us intellectually lazy, or expand our cognitive range? Is time a thing in itself or a measure of change? Join James Robinson as he tries to find out.
6| Christian Bök — Poetry, Constraints, DNA & The Xenotext
byJames Robinson
Christian Bök is an award-winning poet pushing the boundaries of the medium and exploring the capabilities of language itself. Rather than focusing on self-expression, Christian uses poetry as a laboratory for understanding language — probing its plasticity and character.
His notable work, the bestseller Eunoia, draws inspiration from the avant-garde rules of Oulipo and takes it a step further by restricting each chapter to only one vowel. This constraint leads to the creation of such singular phrases as “Writing is inhibiting. Sighing, I sit, scribbling in ink this pidgin script.”
For the past two decades, Christian has pursued an even more ambitious project, The Xenotext. This project involves enciphering an “alien text” within the DNA of a resilient bacterium, Deinococcus radiodurans. One goal of The Xenotext is to create a text that could outlast human civilization. To add to the genomic challenge Christian has set a remarkable rule: the symbols of the text should be interpretable in two different ways, resulting in two poems that are encoded within the same string.
Christian combines scientific techniques, trial and error, and computer programming to construct his poems, adhering to the rules he has established within his own poetic universe. Furthermore, he transforms art back into science by employing gene-editing to inscribe his poetic creation into the “book of life,” the DNA of a living organism.
Instead of looking back and inwards (the ideal of “emotion recollected in tranquility”, Christian looks outwards and to the future, fusing science and art to produce uncanny, unforgettable verse.
Poetry is a game that can be played in many ways. Perhaps the most traditional and popular is “emotion recollected in tranquility” as Wordsworth termed it, whereby the poet’s feelings are carefully expressed. Christian Bök is a bestselling poet who plays a very different game. To use his turn of phrase, he fights with icosahedra, not swords.
Above: the four games of poetry that Christian outlines. The two dimensions are self-expression (seeming to say something) and self-consciousness (meaning to say something).
Christian imposes tight sets of constraints on his writing. His bestseller Eunoia, for example, uses univocalic lipograms — each chapter can only make use of a single vowel. This produces such gems as “Writing is inhibiting. Sighing, I sit, scribbling in ink this pidgin script.” But that’s not all. That would be too easy:
Eunoia abides by many subsidiary rules. All chapters must allude to the art of writing. All chapters must de- scribe a culinary banquet, a prurient debauch, a pas- toral tableau and a nautical voyage. All sentences must accent internal rhyme through the use of syntactical parallelism. The text must exhaust the lexicon for each vowel, citing at least 98% of the available repertoire (although a few words do go unused, despite efforts to include them: parallax, belvedere, gingivitis, mono- chord and tumulus). The text must minimize repeti- tion of substantive vocabulary (so that, ideally, no word appears more than once). The letter Y is suppressed.
— Eunoia, Christian Bök
For the past two decades, Christian has pursued an even more ambitious project, The Xenotext. This project involves enciphering an “alien text” within the DNA of a resilient bacterium, Deinococcus radiodurans. One goal of The Xenotext is to create a text that could outlast human civilization. To add to the genomic challenge Christian has set a remarkable rule: the symbols of the text should be interpretable in two different ways, resulting in two poems that are encoded within the same string.
Christian combines scientific techniques, trial and error, and computer programming to construct his poems, adhering to the rules he has established within his own poetic universe. Furthermore, he transforms art back into science by employing gene-editing to inscribe his poetic creation into the “book of life,” the DNA of a living organism.
Instead of looking back and inwards (the ideal of “emotion recollected in tranquility”, Christian looks outwards and to the future, fusing science and art to produce uncanny and unforgettable (and perhaps ineradicable) verse.
Coffee table conversations with people thinking about foundational issues. Multiverses explores the limits of knowledge and technology. Does quantum mechanics tell us that our world is one of many? Will AI make us intellectually lazy, or expand our cognitive range? Is time a thing in itself or a measure of change? Join James Robinson as he tries to find out.
5| QBism: The World is Unfinished — Ruediger Schack
byJames Robinson
Is the fate of the universe predetermined? Many physicists and philosophers argue it is, particularly those who adopt the Many Worlds interpretation of quantum mechanics.
Our guest this week is Ruediger Schack. With Christopher Fuchs and Carlton Caves, he is one of the originators of a new way of interpreting quantum mechanics, QBism, according to which we — as agents — are co-creators of the world. Destiny is shaped by our hands.
Ruediger is a professor of mathematics at Royal Holloway, University of London, and works on problems in quantum information and quantum cryptography, but also seeks to understand what the equations say about the world.
One of the central claims of QBism is that the wavefunction is a representation of knowledge, not physical reality, as such the “collapse of the wavefunction” due to agent interactions is nothing more than Bayesian updating: observations lead us to update our knowledge.
We unpack the ideas of QBism — that reality is not objective, but inter-subjective, using ideas from phenomenology best summarised in Merleau-Ponty’s comment “there is no world without a being in the world”. We also dive into some of the objections to QBism.
This was a foray into foreign waters for me, I hope you enjoy it as much as I did.
Quantum mechanics is a powerful tool. It allows us to manipulate matter and make predictions with unparalleled precision. But we typically ask more of our theories than instrumental capabilities, we’d like them to give us an account of nature.
In order to extract such an account from quantum mechanics we need to confront the measurement problem. A specific, and famous instance of this problem can be served up like so:
A cat in a box can be in states of being alive and dead simultaneously …
… until opening the box to observe the cat causes one state to be picked.
Neither portion of this is palatable. With David Wallace, we have previously discussed the Everett interpretation which disputes the first and emphatically denies the second. According to this view, the world branches at events causing macroscopic things (like cats) to develop into superpositions of very different states (like the superposition of being dead and alive). To Everettians there is not one cat that is alive and dead. The live and dead are plural: the cats exist in different branches of a multiverse, they are counterpart cats inhabiting counterpart boxes. Observation tells us the branch we are in but has no privileged role.
Our guest this week is Ruediger Schack. With Chris Fuchs and Carlton Caves, Ruediger is one of the originators of a very different framework for understanding quantum mechanics, QBism. He’s a professor of mathematics at Royal Holloway, University of London working in the fields of Quantum Information and cryptography.
Under the QBist view cats can be in quantumstates of being alive and dead simultaneously and agents can provoke a collapse in the quantum state. Yet, to the QBist none of this is mysterious for under this interpretation the quantum state does not represent the world it represents our knowledge. To use some philosophical terms of art quantum states are epistemic and not ontic.
The original label for the QBist account was Quantum Bayesianism, which captured the notion that the collapse of the wavefunction is nothing more than Bayesian updating — the wavefunction is a representation of a user’s beliefs, as new evidence emerges it is trivial that this should change discontinuously.
The QBist project has outgrown its original label of Quantum Bayesianism, it has some fascinating features, at the core of which is that agents cannot be removed from reality. Reality is not, according to the QBists, independent of agents, it is not objective. But neither is it purely ideal — Berkleyan — nor dependent on one individual. Rather it is inter-subjective.
This swims against a strong current in Western science and philosophy within the analytic tradition where a “God’s eye view” (or, another term of art, sub specie aeternitatis) is accepted as conceptually meaningful. But within other philosophical traditions — specifically phenomenology — it does receive support. It was perhaps the French philosopher Maurice Merleau-Ponty who most captured the QBist spirit when he wrote:
“there is no world without a being in the world”
Maurice Merleau-Ponty
Merleau-Ponty implies that there is an external world, but it is dependent on the beings within it, just as they depend on it for their situation.
Another interesting facet of QBism is its use of a personalist Bayesian interpretation of probability, so all probabilities are degrees of belief — even 0 and 1. This enables their rejection of the EPR criterion of reality introduced by Einstein, Podolosky, and Rosen:
If, without in any way disturbing a system, we can predict with certainty (i.e., with probability equal to unity) the value of a physical quantity, then there exists an element of reality corresponding to that quantity.
The intuition here is that for cases where we can perfectly predict the position that (for example) a particle will be in when observed, it was in that position — whether observed or not.
The QBist replies: why should a person’s subjective beliefs imply the existence of any element of reality?
We dig a little into some of the challenges for the QBist — including the above. Harvey Brown outlines arguments for the reality of the wavefunction which go against the core QBist belief that quantum states are epistemic. The spirit of these arguments is thqt quantum states fundamental to the explanatory power of quantum mechanics, and that the best explanation of this is that they exist. This is the fundamental abductive argument that underpins much scientific thinking — it’s why we think particles are real.
I find it illuminating to contrast the hyper-realist view offered by the Many Worlds (or Everett) interpretation of quantum mechanics where quantum states and their evolution capture all of reality with the QBist for whom they are not an element of nature at all.
While I still count myself as a card-carrying Everettian this was an eye-opening excursion down another path of thinking. I particularly enjoyed Ruediger’s closing thoughts — because agents cannot be removed from the QBist picture, reality is not fully defined, it is being created by us. The world is not finished.
Chris Timpson is always worth listening to on the subject of the interpretations of QM, a self-described agnostic on this topic his discussion of QBism gives a characteristically thoughtful and even-handed critique. Here he is on YouTube
Chris Fuchs is a pleasure to listen to, even if one disagrees, his characterization of the philosophical critiques of QBism is irresistibly brilliant: “wah, wah, wah you’re not realist enough for us”. From this talk on YouTube.
Join me as I explore the limits of knowledge and technology in weekly interviews with academics, writers & entrepreneurs. In discussion with philosophers, poets, and physicists we’ll delve into foundational questions in arts and science.
Coffee table conversations with people thinking about foundational issues. Multiverses explores the limits of knowledge and technology. Does quantum mechanics tell us that our world is one of many? Will AI make us intellectually lazy, or expand our cognitive range? Is time a thing in itself or a measure of change? Join James Robinson as he tries to find out.
30| Thinking Beyond Language — Anna Ivanova on what LLMs can learn from the brain
byJames Robinson
It can be tempting to consider language and thought as inextricably linked. As such we might conclude that LLM’s human-like capabilities for manipulating language indicate a corresponding level of thinking.
However, neuroscience research suggests that thought and language can be teased apart, perhaps the latter is more akin to an input-output interface, or an area of triage for problem-solving. Language is a medium into which we can translate and transport concepts.
Our guest this week is Anna Ivanova, Assistant Professor of Psychology at Georgia Institute of Technology. She’s conducted experiments that demonstrate how subjects with severe aphantasia (large-scale damage to the language area of their brains) remain able to reason socially. She’s also studied how the brains of developers work when reading code. Again the language network is largely bypassed.
Anna’s work and other research in cognitive science suggest that the modularity of brains is central to their ability to handle diverse tasks.
Brains are not monolithic neural nets like LLMs but contain networked specialized regions.
Coffee table conversations with people thinking about foundational issues. Multiverses explores the limits of knowledge and technology. Does quantum mechanics tell us that our world is one of many? Will AI make us intellectually lazy, or expand our cognitive range? Is time a thing in itself or a measure of change? Join James Robinson as he tries to find out.
Science and poetry are sometimes caricatured as opposing paradigms: the emotional expression of the self versus the objective representation of nature. But science can be poetic, and poetry scientific. Our guest this week, Sam Illingworth, bridges these worlds. He’s researched scientists who were also poets, and organized workshops for scientists and laypeople using the medium of poetry to create an equitable and open dialogue.
In addition to being an Associate Professor at Edinburgh Napier University, Sam is the founder of Consilience, a peer-reviewed journal publishing poetry (which presents such beautifully titled gems as What You Don’t See on David Attenborough is All the Waiting) and hosts the Poetry of Science podcast where, each week, he writes a poem in response to recent scientific research.
Science and poetry are sometimes caricatured as opposing paradigms: the emotional expression of the self versus the objective representation of nature. But science can be poetic, and poetry scientific. Our guest this week, Sam Illingworth, bridges these worlds. He’s researched scientists who were also poets, and organized workshops for scientists and laypeople using the medium of poetry to create an equitable and open dialogue.
In addition to being an Associate Professor at Edinburgh Napier University, Sam is the founder of Consilience, a peer-reviewed journal publishing poetry (which presents such beautifully titled gems as What You Don’t See on David Attenborough is All the Waiting) and hosts the Poetry of Science podcast where, each week, he writes a poem in response to recent scientific research.
Instead of undertaking the perhaps foolhardy (and certainly arduous) task of attempting to summarise this conversation, I will share some of my favourite quotes from this conversation and Sam’s book, A Sonnet To Science:
… a poet essentially comprises and unites both these characters [legislator and prophet]. For he not only beholds intensely the present as it is, and discovers those laws according to which present things ought to be ordered, but he beholds the future in the present, and his thoughts are the germs of the flower and the fruit of latest time.
Miroslav Holub on the demise of his Lepidoptera collection, as quoted in A Sonnet to Science
Unfortunately the world is real. Unfortunately within ten years all my butterflies in their twenty-five boxes were eaten by museum carpet-beetles and other parasites which nurture a grudge agains human immortality. Unfortunately all that’s left is the pins the boxes and the labels. And so I started writing poems again. Poems aren’t eaten by anything, except stupidity.
Coffee table conversations with people thinking about foundational issues. Multiverses explores the limits of knowledge and technology. Does quantum mechanics tell us that our world is one of many? Will AI make us intellectually lazy, or expand our cognitive range? Is time a thing in itself or a measure of change? Join James Robinson as he tries to find out.
Space and time appear in charts as axes oblivious to the points they demarcate. Similarly, we may feel that we, and all the objects of our worlds, are like such points — and spacetime is a container in which we sit.
Julian Barbour is a physicist who has spent six decades arguing against this. He takes the relationist approach of Leibniz and Mach: there is no space without objects and no time without change. Rather space is just the geometric relationships between things.
Julian has pioneered theories that recover the predictions of Newtonian mechanics and General Relativity that drop their invocation of imperceptible space, time, and spacetime. Recently he has taken an iconoclastic approach to the arrow of time — looking to a new measure of structure, complexity, and the expansion of the universe instead of the traditional accounts in terms of entropy.
Space and time are intimately familiar, without them we experience nothing. In t’s and x’s and μ’s they suffuse the equations of physics. Yet their nature remains the subject of debate and conjecture. Are they entities in and of themselves, or do they simply represent relationships between objects or events?
Our guest this week is Julian Barbour, a physicist, and thinker who has led a program of work over six decades to champion the relationist position. According to this view, there is no space without objects — space is a codification of the geometric relationships between objects, likewise, there is no time without change — time emerges from the varied configurations of objects in different “nows”.
This is in direct contrast to a tradition going back to Isaac Newton:
Absolute, true, and mathematical time, in and of itself and of its own nature, without reference to anything external, flows uniformly and by another name is called duration.
For this claim, Newton provided scant arguments, however, he was able to make a case that space existed independently of particles. His law of inertia showed that rotating masses would experience angular momentum. This is easily measurable, for example, spinning a bucket of water leads to the surface of the liquid curving. What is it spinning relative to that should cause this? Newton reasoned it had to be absolute space.
Newton’s contemporary and arch-rival, Gottfried Wilhelm von Leibniz pushed back against this absolutist picture but although he offered many good arguments he was unable (or unwilling) to provide an answer to this bucket experiment. Two centuries later the physicist Ernst Mach was deeply uncomfortable with this intangibility of absolute space and proposed that the forces of angular momentum might be caused not by motion relative to the ethereal substance of space but by movement relative to ordinary stuff — in particular the fixed stars.
In 1977, with Bruno Bertotti, Julian made good on Mach’s principle for a universe of N (any finite number) particles and vanishing overall angular moment. That is, the predictions of Newtonian mechanics — including the water in the bucket — were completely recovered without any reference to absolute space. This was an extraordinary achievement.
Julian has gone on to show that, again with some constraints (that the universe is closed, roughly speaking that it curves back on itself), the predictions of General Relativity can also be recovered within a completely relational theory — Shape Dynamics, developed with collaborators Tim Koslwoski and Flavio Mercati. While in General Relativity space and time are presented as malleable substances with a starring role in determining motions, in Shape Dynamics they are gone.
In Julian’s latest work, presented in his book The Janus Point, he has turned to the question of the arrow of time. Why do processes seem to happen only in one direction even though the laws of physics are symmetric? Unsatisfied with the frequently given explanation in terms of entropy increase (and in particular the lack of explanation for the “past hypothesis” — that entropy of the universe needed to have been low) Julian had an insight into an alternative picture.
Once again he explored the Newtonian problem first to show that, for arrangements of particles interacting under gravity with a vanishing or negative total energy, there will be a moment of closest approach from which they will move away. Julian presents strong arguments that on either side of this moment of closest approach, there will be two arrows of time and provides a mathematical proof that a quantity he introduces — the complexity — that measures the amount of structure in the world will inexorably increase as a configuration expands relative to its earlier scale.
Physics is not settled. And Julian freely admits that there could be observations that scupper the relationist ship. But his intuitions and evidence are strong, let us suppose then that the relationists are right. What would it mean?
Stand up, spin, and let your arms fly out. You are feeling the dust clouds, stars, and black holes of the universe.
Watch the unfurling of a leaf and the folding of a paper swan. That too is the cryptic touch of gravity.
Questions I’d ask if I had this conversation again
How did being an independent academicshape his research and collaboration?
Julian chose not to follow a typical academic path. He lives on a small farm near Oxford and has strong relations with members of the Physics and Philosophy faculties there, latterly being a visiting professor, but he has never been a fully paid-up member of the academy. He has commented that the “Publish or perish” culture does not encourage the sort of work he has done — which one may characterize as infrequent, but groundbreaking papers that challenge the foundations of physical thought. I wonder what challenges and opportunities this choice presented him.
What did you learn from translating seventy million words of academic texts?
For income, for many years Julian would translate physics texts from German and Russian for three days a week, the other two he would dedicate to his research. How did he find this rhythm, had he been given the means to spend five days a week on the questions of time and space, would he have taken it?
How would you compare the senses of wonder and insight you get from reading Kepler and Shakespeare?
In The Janus Point, there are more quotes from Shakespeare than from Newton, Leibniz, or Mach. Julian is somewhat unusual in that he is a physicist who reads the original works of natural philosophy — such as Newton’s Principia, Descartes’ The World — I believe he reads them for both pleasure and insight. Has Shakespeare also informed his thinking on time, space, and structure?
Coffee table conversations with people thinking about foundational issues. Multiverses explores the limits of knowledge and technology. Does quantum mechanics tell us that our world is one of many? Will AI make us intellectually lazy, or expand our cognitive range? Is time a thing in itself or a measure of change? Join James Robinson as he tries to find out.
We live in a branching universe. If it can happen, it does happen.
These are the almost incredible claims of the Many Worlds Interpretation of quantum mechanics. Yet today’s guest, David Wallace, makes a case that this is the most grounded way of reading our best theory of nature.
While at first sight quantum mechanics seems to say that things (famously, cats!) can occupy impossible states, David argues that a careful reading shows we can take seriously “superpositions” (these apparently weird states) not only at the microscopic level but all the way up to the scale of the universe.
This way of thinking about quantum mechanics was first proposed in 1957 by Hugh Everett, David has made important contributions — particularly in the “preferred basis” or “counting problem” which asks how many worlds are there; and also in understanding how a deterministic theory of the world appears indeterministic — probabilistic — to agents.
David has PhDs in both physics and philosophy from the University of Oxford and currently holds the Mellon Chair in Philosophy of Science at the University of Pittsburgh.
“When you come to a fork in the road, you should take it”
So goes the jocular advice of Yogi Berra.
But what if this is what the universe actually does? What if we live in a garden of forking paths, of events that can go one way or another and in fact do both?
This is the subject of today’s podcast with David Wallace. David holds the Mellon Chair in Philosophy of Science at the University of Pittsburgh. He is one of the leading advocates of the Everett interpretation of quantum mechanics.
Originally proposed in 1957 by Hugh Everett and also called the Many Worlds Interpretation it offers a way of unpacking the precise mathematical predictions of this theory.
The issue is this: quantum mechanics permits small things — atoms, electrons, photons — to be in frankly weird states. A single particle can be in many places at once, or traveling at many different speeds.
These superpositions are key to Quantum Mechanics. Integral to this theory which explains how stars work, has enabled us to build computer chips and, indeed, lies at the very foundations of our understanding of matter — the uninspiringly named “Standard Model” is a quantum mechanical theory.
Perhaps you have no issue with these tiny particles being in such weird states — you can’t see them. But quantum mechanics does not draw a qualitative distinction between small and big things. Like the rest of physics, it treats big things as agglomerations of small ones, the difference between them is of quantity, not kind. So quantum mechanics appears to tell us that big things like people, or (famously) cats can be in multiple places at once or even in seemingly contradictory states of being dead and alive. This is not what we observe.
The original attempt to explain this away was to say that when a measurement takes place these superpositions break down and crystallise into a single state. You might have come across phrases like “the collapse of the wavefunction” to describe this idea that things go from being spread out, or wavelike, to being localised. But what’s so special about measurement that it should provoke such a change of behaviour, what even is measurement if not just another physical process?
Other attempts propose modifying quantum mechanics — adding a new mechanism that would cause the crystallisation or collapse that doesn’t privilege measurement. However, it is no mean feat to try to modify a theory that has had such predictive success.
But what if we do not try to explain anything away?
What if we take seriously this idea of superpositions at all levels, not just the microscopic but all the way up to human and even universal scale?
Does quantum mechanics tell us we will observe something being in two states at once? No. Hugh Everett, David Wallace, and many others reason that quantum mechanics tells us that the world branches and that as the small superpositions become large those large ones represent worlds and each world looks much like the world we inhabit — where objects are one thing or another but never both at once.
When a photon can follow two different paths, it does, when the detection apparatus can observe it in two different places it will, when I can see that apparatus registering two different things, I will. But there is one me, and another me and neither sees anything extraordinary. The world has followed the fork in the road.
This is a theory with almost incredible consequences. But it has unassuming origins. It does not assume that there is anything special about measurement nor that quantum mechanics is incomplete. It is a radical theory for it goes to the roots of quantum mechanics, from these the branches emerge.
David was my tutor when I studied Physics and Philosophy as an undergraduate at Oxford, my thanks to him for giving his time to my curiosity once again.
References
The Yogi Berra line is one Harvey Brown used in his lectures on MWI.
The Emergent Multiverse — the most comprehensive book so far on the Many Worlds interpretation — if you’re still curious after listening to the podcast and reading this far, this book might be for you!
