MV#15: What is philosophy? — Simon Critchley

From what human need does philosophy emerge? And where can it lead us?

Simon Critchley is Hans Jonas professor of Philosophy at the New School in New York, and a scholar of Heidegger, Pessoa, Football (Liverpool FC), humour. He crosses over between analytic and continental traditions and freely draws on quotes from Hume and British pop bands.

Simon argues that philosophy begins in disappointment, not wonder. But it does not end there, its goals can be wisdom, knowledge, enlightenment, and freedom. Its concerns can be yet more varied: it can work as a tool for developing scientific theories, for exposing ideology, or for tracing the underpinnings of language and experience. Anywhere where other fields fear to tread, that’s where philosophers step in.

Since recording with Simon, one question has kept turning over in my head: how important is context to the understanding of philosophical ideas? An issue we discussed towards the end of the interview and did not quite have sufficient time to loop around as many times as I would have liked.

On the one hand, I believe in such things as facts and truth. I believe that science and some philosophical reasoning can deliver us these — although I recognize that belief cannot be justified beyond doubt. It is an act of faith. However, certain types of things, for example, facts concerning the laws of physics, I take to be impervious to our attitudes and human concerns. Why we believe them, and why we even look for them, are valid sociological and phenomenological questions. Yet the evidence for these facts can be produced usefully without any reference to historical context and the facts themselves do not depend on human factors.

In this way, to the question of whether the sun existed before humans — the subject of a heated discussion between Maurice Merleau-Ponty, Georges Bataille and A J Ayer in a Parisian bar — my answer is yes.

And yet.

There are questions that philosophy asks about issues that have no basis in fact. Impossible objects.

I recently asked ChatGPT to produce some predictions about the future for a project I am working on (What Year is Now? A Hallucinatory Horological Mapping). There are some obvious errors with the below — the tercentenary of the first interdimensional travel falling in 2307 would imply we first made that leap back in 2007. I suppose that’s possible if the dimension in question is time.

More interesting is what is predicted for 2306:

2306: Interdimensional exploration reveals the nature of existence itself


I do not think that will happen. I don’t think it can. Determining the nature of existence is a question we cannot solve, even though there is value in turning it over, the value is not to get to an answer. It’s a means justify the ends (and btw there are no ends) sort of question.

For questions like this, and more particularly questions about the meaning of existence, context is important. Consider also questions in ethics and meta-ethics. There are no truths to be had here, and what is right for society — perhaps even the right way of thinking for society — will depend on that society. For example, in times of high uncertainty, where predictions are costly and inaccurate (perhaps this moment?) we might have reasons to consider virtue ethics over consequentialist frameworks.

Does it matter that I write this on Sunday morning, in 2023, in a stony city, that the sun — prehistoric or not — is hidden by several layers of cloud? It’s not for me to say.

Some links


(00:00) Intro
(3:00) Beginning of conversation: disappointment as the start of the journey
(7:55) Punk & Philosophy
(11:20) Trauma and tabula rasa
(12:30) Not making it in a band, becoming a philosopher
(19:30) Wittgenstein as a bridge between analytic and continental philosophy
(21:50) Mill and the origin of the label “continental philosophy”
(24:30) Philosophy has a duty to be part of culture
(28:00) The difficulty with philosophy being an academic tradition
(29:30) The Stone
(32:30) Football as a phenomenon for study that invites people in to philosophy
(35:00) Philosophy as pre-theoretic & Pessoa’s Ultimatum
(39:00) Will analytic philosophy run out for road and be subsumed into science?
(41:00) Two lines of human imagination
(42:00) Should philosophy ever be a single honours subject, or should it always aid other realms of thought?
(43:00) Philosophy as pre-science
(44:30) Phenomenology as reflection on the lived world
(47:00) Alberto Caeiro (Pessoa) and anti-poetry
(48:50) The saying of ordinary things to fascinate angels
(54:00) Impossible objects will keep philosophers busy
(57:00) The task of philosophy as deflationary, as not making progress
(1:00:00) Should philosophy of physics be part of physics?
(1:04:30) Context: What can’t I read Descartes like I’m talking to your right now?
(1:06:00) Is context colour or is it inseparable from ideas?
(1:15:30) Rorty: Continental philosophy as proper names vs problems in analytic philsophy
(1:19:20) Trying to walk the line between two traditions of philosophy
(1:20:00) Obscurantism vs scientism
(1:23:00) Permission to think on their own, to expose ideology
(1:26:00) The internet has been good for philosophy
(1:26:30) Audio as a new platform or agora for philosophy

MV#8 — Thought Experiments, Mach, Galileo & Phenomenology — Harald Wiltsche

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

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.

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

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.

But if the butterfly were absent, wouldn’t the plane weigh less and therefore less thrust would be required?

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.

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?

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.

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?

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.

MV#5 — QBism: The World is Unfinished — Ruediger Schack

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:

  1. A cat in a box can be in states of being alive and dead simultaneously …
  2. …  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 quantum states 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.

From Can Quantum-Mechanical Description of Physical Reality be Considered Complete? — Einstein, Podolsky, Rosen

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. 


Ruediger’s article on QBism in The Conversation

Wikipedia and The Stanford Encyclopedia of Philosophy offer good introductions to QBism.

A QBist reads Merleau-Ponty — Ruediger discusses the parallels between QBism and phenomenology

The Reality of the Wavefunction: Old Arguments and New — Harvey Brown’s paper reasoning that QBism fails to capture the explanatory power of the wavefunction

“Was There a Sun Before Men Existed?”: A. J. Ayer and French Philosophy in the Fifties — an entertaining paper by Andreas Vrahimis that contrasts the thinking of phenomenologists and the analytic philosopher A.J. Ayer.

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.