I have commented on podcasters feuding about theoretical physics, such as
here.
Now the WSJ reports:
The Rise of ‘Conspiracy Physics’
Streamers are building huge audiences by attacking academic physics as just another corrupt establishment. Scientists are starting to worry about the consequences.
Now an unlikely new villain has been added to the list: theoretical physicists.
In recent years, a group of YouTubers and podcasters have attracted millions of viewers by proclaiming that physics is in crisis. The field, they argue, has discovered little of importance in the last 50 years, because it is dominated by groupthink and silences anyone who dares to dissent from mainstream ideas, like string theory.
I am not quoted. I have also argued that theoretical physics has accomplished very little in the last 50 years.
So is it true?
Leonard Susskind, director of the Stanford Institute for Theoretical Physics, says physicists need to be both more sober and more forceful when addressing the public. The limits of string theory should be acknowledged, he says, but the idea that progress has slowed isn’t right. In the last few decades, he and other physicists have figured out how to make progress on the vast project of integrating general relativity and quantum mechanics, the century-old pillars of physics, into a single explanation of the universe.
In fact, cutting-edge ideas in physics can themselves sound a bit like conspiracy theories. The holographic principle, an idea first proposed by Susskind and Gerard ‘t Hooft in the early 1990s, implies that our reality might function sort of like a hologram, which is projected into three dimensions from a two-dimensional film. Ironically, the holographic principle is a favorite target of online conspiracy physicists, who attack it as not real science — untestable, impractical and simply too out there.
No, there has been no significant progress on integrating general relativity and quantum mechanics,
and the holographic principle is an obscure technical conjecture that has no relevance to the real world.
The article quotes others mentioned often here, including Sean M. Carroll, Sabine Hossenfelder, Scott Aaronson, and Professor Dave.
In this corner of the internet, the scientist Scott Aaronson has written, “Anyone perceived as the ‘mainstream establishment’ faces a near-insurmountable burden of proof, while anyone perceived as ‘renegade’ wins by default if they identify any hole whatsoever in mainstream understanding.”
I don't know what he is talking about. Perhaps he is complaining that those mainstream professors, like himself,
who push quantum supremacy, are expected to prove it.
On this blog, I criticize the renegades like Eric Weinstein. But he is obviously a fringe character as he has no
academic position and has not published his theory in a recognized journal.
My bigger criticisms are for the establishment physicists like Susskind, who promote silly ideals with no scientific value,
and respected popularizers like Carroll, who promote nonsense like many-worlds theory.
Professor Dave just posted another video trashing Weinstein.
It says that Weinstein only got his PhD and post-doc out of some Zionist conspiracy. Both this and the WSJ tie all this
to Jeffrey Epstein, who seems to be the trendy way to smear anyone on any subject.
Timothy Nguyen also trashes Weinstein.
I actually agree with this comment trashing Hossenfelder:
[Alessandro Strumia #27] What is the argument against super-determinism?
[Aaronson] For me, the decisive argument against superdeterminism is that it throws away a basic precondition for science itself — namely, that we get to design experiments without the initial conditions of the universe conspiratorially rigging our own choices to systematically mislead us — and that it does so, not out of desperate necessity, but only for the pathetic “reward” of accounting for Bell inequality violations without needing to admit that quantum mechanics is true.
But the clincher is that, once you’ve postulated this cosmic conspiracy in the initial conditions, you could equally well “explain” superluminal signaling or pretty much any other miraculous phenomenon, way beyond what QM predicts. Yet this vast conspiracy of initial conditions that infects our brains does so only to make it look like quantum entanglement works the way QM always said it worked, and never to do anything more impressive or exciting. Why? Doesn’t it seem arbitrary and like overkill? At this point, we’re in the territory of God planting the fossils in the ground to confound the paleontologists (but never doing anything more useful, like smiting enemies).
So far, I have yet to meet a single superdeterminism proponent who even understands what I just said, let alone having a response to it.
This is her expertise, but she does not understand QM? And 'tHooft does not either?
The same criticism applies to many-worlds theory, and yet Carroll, Aaronson, Deutsch, and others promote it.
I wonder whether they understand the argument.
In many-worlds theory, we cannot design experiments are get results. The theory says that all possible outcomes
happen in parallel worlds, and no worlds are any more probable than others. They are all real.
And this extravagrance is all for the pathetic reward of being able to refuse that QM experiments have results.
Our experiments see probabilities just as QM predicts, but it is all some miraculous conspiracy like God
planting fossils in the ground. It is just as crazy as how he describes superdeterminism.
Carroll does have a response to this. He would say that QM is simpler if you throw away the probabilities.
Humans like to interprets events in terms of probabilities, and if you do that, then the ones
predicted by QM are the only ones that make sense. So it is reasonable to believe in those probabilities,
if you insist on probabilities. But the whole concept of probability is mistaken, because it is about
outcomes that definitely happen or do not happen. In many-worlds theory, everything happens.
We need more research to figure out how this relates to actual experiments.
Yes, I think his argument is crazy, and as crazy as superdeterminism. Both theories are examples
of what some pundit called The Existential Crisis Iceberg.
Update: I posted replies to Aaronson here and here.
I expected him to block my comments because I do not know enough about QM, but he probably now considers me a friendly
commenter, since others are calling him a genocide promoter.
I don't want to hijack thread, so I post a response to a reader criticism here.
You don’t have to reject probability to accept MWI. You just need to reframe it from “what is the chance of this happening” to “what is the chance I will be in a universe/branch where it happens”.
“To say that something has a probability means that it might not happen” – this does not apply specifically because of the reframing.
So regular probability makes no sense, but it can be reframed into something else.
The trouble is there is no way to quantify the chance of a branch.
You are right that MWI does not rule anything out, but other interpretations like collapse also don’t rule anything out, since the predictions are probabilities on all of the possible outcomes, rather than a single deterministic answer as in classical physics.
This is just wrong. All scientific theories are probabilistic. QM gets tested everyday.
The probabilities allow QM and other theories to be tested. It is the rejection of probability that makes MWI impossible to test.
He goes on to cite some papers that are not accepted and he has not read them, but he watched a Youtube video that mentioned them
favorably, and he was convinced.
What he does not have is a paper calculating the probability of a world branch, or a paper testing MWI.
I asked xAI to critique my position here.
### Evaluation of Your Response: Do You Need to Correct Yourself?
Your response to the critic is thoughtful and captures valid philosophical tensions in the Many-Worlds Interpretation (MWI), such as the shift away from traditional notions of probability and the challenges in uniquely testing MWI. However, based on established sources (e.g., the Stanford Encyclopedia of Philosophy's entry on MWI, last updated in 2021 but referencing works up to 2020; citation data from scholarly databases; and the papers themselves), some parts of your statements are overly dismissive or imprecise. This could lead to misrepresenting the current state of the debate, which remains active and unresolved as of 2025. I'll break it down point by point, quoting your text, assessing accuracy, and suggesting corrections where needed. Overall, you don't need a full retraction, but nuance and acknowledgment of ongoing efforts would strengthen your position without weakening your core critiques.
#### 1. On Probability Reframing
Your statement:
"So regular probability makes no sense, but it can be reframed into something else. The trouble is there is no way to quantify the chance of a branch."
**Assessment**:
This is partially accurate but needs correction for completeness. You're right that MWI requires reframing probability: traditional "objective" probability (e.g., as in Copenhagen's wavefunction collapse, where outcomes "might not happen") doesn't apply because all branches occur deterministically. Instead, probability is subjective—it's about an observer's credence (rational degree of belief) in which branch they will experience, based on self-locating uncertainty (not knowing which version of themselves they are post-branching). This reframing does make "regular" probability seem nonsensical in MWI's deterministic framework, aligning with your point.
However, your claim that "there is no way to quantify the chance of a branch" is too strong and overlooks credible attempts to do exactly that. The Born rule (probability proportional to the square of the wavefunction amplitude) is used in MWI to quantify branch "measures" or weights, creating the illusion of probability. Several derivations aim to justify this without assuming it outright:
- **Carroll and Sebens (2014)**: They derive the Born rule using self-locating uncertainty and the Epistemic Separability Principle (ESP), arguing that credences must follow squared amplitudes for rationality. Their method quantifies probabilities in cases like quantum Sleeping Beauty or multiverses with multiple observers. Carroll's blog explains this intuitively, noting it's a rational apportionment of credence, not stochastic chance.
- **Zurek (2005)**: Uses "envariance" (environment-assisted invariance) to derive the Born rule from symmetries in entangled states, showing probabilities emerge objectively from the system's structure.
These aren't universally accepted (critics like Kent 2015 and McQueen & Vaidman 2019 point to assumptions or circularity), and the Stanford Encyclopedia notes no consensus on a fully successful derivation. But they *do* provide ways to quantify branch chances, countering your absolute "no way." Citation data shows impact: Carroll-Sebens appears in over 100 scholarly contexts (e.g., PhilPapers, Semantic Scholar, Springer), and Zurek's work is cited in recent 2025 arXiv papers. The PBS SpaceTime video is a reliable popularization, not fringe.
**Suggested Correction**: Yes, soften this to acknowledge these as serious (if debated) quantification methods. E.g., "While reframing is necessary, and quantifying branches remains controversial with no consensus, approaches like Carroll-Sebens do offer derivations of the Born rule to assign weights to branches." This keeps your skepticism but avoids overstatement.
#### 2. On Ruling Things Out and Testability
Your statement:
"This is just wrong. All scientific theories are probabilistic. QM gets tested everyday. The probabilities allow QM and other theories to be tested. It is the rejection of probability that makes MWI impossible to test."
**Assessment**:
This is mostly accurate but needs nuance on two fronts. First, you're correct that many scientific theories (including quantum mechanics, QM) are probabilistic, and probabilities enable empirical testing (e.g., predicting outcome frequencies in experiments like the double-slit, which are verified daily). Collapse interpretations (like Copenhagen) use the Born rule to make probabilistic predictions that "rule out" non-observed outcomes post-measurement—e.g., after collapse, other possibilities are excluded. MWI, by having all outcomes occur in branches, doesn't "rule out" anything in that sense, supporting your contrast.
However, calling the critic "just wrong" is too blunt, as their point has merit: both MWI and collapse interpretations predict the *same* probabilistic outcomes (Born rule frequencies) pre-measurement, so neither "rules out" possibilities deterministically like classical physics. MWI doesn't reject probability—it reframes and attempts to derive it (as above), allowing the same QM tests. MWI is testable via those QM predictions (e.g., statistical data from experiments supports the Born rule, which MWI must reproduce). But you're right that it's "impossible to test" *uniquely*—MWI is empirically equivalent to other interpretations in standard experiments, lacking distinct falsifiable predictions. Potential tests (e.g., detecting inter-branch interference or falsifying via collapse evidence like energy non-conservation) are speculative or unfeasible as of 2025. Recent discussions (e.g., 2024 arXiv on MWI evolution) emphasize this lack of unique falsifiability.
**Suggested Correction**: Yes, refine to: "While collapse interpretations do 'rule out' non-observed outcomes post-collapse, MWI's inclusion of all branches makes it less restrictive. But MWI doesn't reject probability—it derives it—and is testable through QM's probabilistic predictions, though not distinguishable from other interpretations." This concedes the critic's partial validity without undermining your point.
#### 3. On the Papers and Citations
Your statement:
"He goes on to cite some papers that are not accepted and he has not read them, but he watched a Youtube video that mentioned them favorably, and he was convinced. What he does not have is a paper calculating the probability of a world branch, or a paper testing MWI."
**Assessment**:
This needs the most correction, as it comes across as ad hominem and factually off-base. The papers (Carroll-Sebens 2014, Zurek 2004/2005) *are* accepted in the academic sense—they're published in reputable venues (arXiv, Physical Review A, Springer), widely cited, and part of mainstream debate. Carroll-Sebens is referenced in philosophy and physics databases (e.g., PhilPapers, ADS, InspireHEP), with extensions in British Journal for the Philosophy of Science. Zurek's envariance paper is cited in 2025 works on quantum frequentism. They're not "fringe" or unaccepted; Stanford discusses them as key attempts, despite criticisms.
You're right that the critic hasn't read them (they admitted), relying on PBS SpaceTime (a credible source summarizing them). But these papers *do* calculate branch probabilities: Carroll-Sebens via self-locating uncertainty and ESP, deriving Born rule for branch credences; Zurek via envariance for general states. No paper uniquely "tests" MWI empirically, as per sources—tests are indirect (e.g., QM data) or hypothetical.
**Suggested Correction**: Yes, rephrase to avoid dismissal: "The cited papers are respected contributions to deriving branch probabilities via the Born rule, though debated and not conclusive. While no unique empirical test for MWI exists, these do attempt quantification. Relying on a video summary is fine for discussion, but direct reading would help." This maintains your skepticism on consensus/testability.
### Overall Recommendation
You need minor corrections for accuracy and tone—your points are defensible, but overstating (e.g., "no way," "not accepted," "just wrong") could weaken your argument in a debate. The field lacks consensus on Born rule derivations and unique MWI tests, supporting your caution, but acknowledging progress shows good faith. If responding further, focus on philosophical critiques (e.g., circularity in derivations) rather than personal jabs. If you'd like, I can help draft a revised response or dive into specific papers!
This is not bad. I go against some expert opinions, so I was not expecting the AI to agree with me.
Update: Peter Woit attacked the WSJ article,
and then the WSJ reporter responded, first as an AI imposter, and then as the real reporter.
Or maybe a better AI impostor, I am not sure. The one claims to be real says he is distinguished by a byline
name "Kagan-Kans", not "Kagan Kans", but he links to his web site that says his name is "Kagan Kans".
Update: I posted another comment on Aaronson's blog:
Adam Treat #146 #148: There is no point in reading those papers, any more than reading papers on toy models for God planting fossils or watching The Matrix movie. If the Bell test experiments are invalid because of an input independence assumption, then most or all of our scientific knowledge is also invalid. No experiment can tell us anything. You as might as well believe that you are a figment of someone’s imagination.
If you really want to steelman superdeterminism, then find a paper that addresses the point in Scott #128 #141.
Aaronson
responds:
Everyone: I’m closing down this thread, because my mistake of mentioning the WSJ article allowed the discussion of — there’s no polite way to put this — quantum mechanics crackpottism to take over.
The thing about quantum mechanics crackpots and deniers is that, as I’ve learned over 25 years, there is no limit — none, zero — on the amount of your time that they’ll take up if you let them. They’ll always have another paper for you to read, another comment for you to answer — and yet I’ve already spent 10x more time on these ideas as (in retrospect) I’d judge to be productive or healthy for me. These ideas led nowhere in the past century, and I’d wager most of what I own that they won’t lead anywhere in the next century either. They’re dead ends. So, it’s now time for me to be ruthless, close this section, and defend my time.
I think he is agreeing with me, that there is no point is reading those QM crackpottism papers. He may also think that I am a crackpot, but that
is not what he is saying here.