but it does depend on assumptions such as that the universe is eternal — wonderer1

This isn't just an assumption. Rather:

The preponderance of evidence to date, based on measurements of the rate of expansion and the mass density, favors a universe that will continue to expand indefinitely, resulting in the "Big Freeze" scenario below.

The heat death of the universe, also known as the Big Freeze (or Big Chill), is a scenario under which continued expansion results in a universe that asymptotically approaches absolute zero temperature. Under this scenario, the universe eventually reaches a state of maximum entropy in which everything is evenly distributed and there are no energy gradients—which are needed to sustain information processing, one form of which is life. This scenario has gained ground as the most likely fate.

In this scenario, stars are expected to form normally for 10¹² to 10¹⁴ (1–100 trillion) years, but eventually the supply of gas needed for star formation will be exhausted. As existing stars run out of fuel and cease to shine, the universe will slowly and inexorably grow darker. Eventually black holes will dominate the universe, which themselves will disappear over time as they emit Hawking radiation. Over infinite time, there could be a spontaneous entropy decrease by the Poincaré recurrence theorem, thermal fluctuations, and the fluctuation theorem.

That final sentence is what entails Boltzmann brains.

This isn't just an assumption. Rather:
— Michael

The preponderance of evidence to date, based on measurements of the rate of expansion and the mass density, favors a universe that will continue to expand indefinitely, resulting in the "Big Freeze" scenario below...

BB speculations are scientifically self defeating.

We only take such evidence seriously on the assumption that humans actually make empirical observations rather than experience phantasms occuring in a BB. Given the bigger picture, resulting from empirical observations considered more broadly, the evidence points towards us being the result of biological evolution. Do you think the majority of physicists would disagree?

BB speculations are scientifically self defeating. — wonderer1

Why? They're entailed by our best scientific theories.

Given the bigger picture, resulting from empirical observations considered more broadly, the evidence points towards us being the result of biological evolution. Do you think the majority of physicists would disagree? — wonderer1

See modern reactions to the Boltzmann brain problem:

The consensus amongst cosmologists is that some yet to be revealed error is hinted at by the surprising calculation that Boltzmann brains should vastly outnumber normal human brains. Sean Carroll states "We're not arguing that Boltzmann Brains exist—we're trying to avoid them." Carroll has stated that the hypothesis of being a Boltzmann brain results in "cognitive instability". Because, he argues, it would take longer than the current age of the universe for a brain to form, and yet it thinks that it observes that it exists in a younger universe, this shows that memories and reasoning processes would be untrustworthy if it were indeed a Boltzmann brain. Seth Lloyd has stated, "They fail the Monty Python test: Stop that! That's too silly!" A New Scientist journalist summarizes that "The starting point for our understanding of the universe and its behavior is that humans, not disembodied brains, are typical observers."

Some argue that brains produced via quantum fluctuation, and maybe even brains produced via nucleation in the de Sitter vacuum, do not count as observers. Quantum fluctuations are easier to exclude than nucleated brains, as quantum fluctuations can more easily be targeted by straightforward criteria (such as their lack of interaction with the environment at infinity).

Carroll believes that a better understanding of the measurement problem in quantum mechanics would show that some vacuum states have no dynamical evolution and cannot support nucleated brains, nor any other type of observer. Some cosmologists believe that a better understanding of the degrees of freedom in the quantum vacuum of holographic string theory can solve the Boltzmann brain problem.

Brian Greene states: "I am confident that I am not a Boltzmann brain. However, we want our theories to similarly concur that we are not Boltzmann brains, but so far it has proved surprisingly difficult for them to do so."

The general gist seems to be:

1. our scientific theories suggest that we are most likely Boltzmann brains
2. we are not most likely Boltzmann brains
3. therefore, our scientific theories are mistaken

The point I am making is that, by this very argument, (2) is not supported by the scientific evidence. Rather it's something like "common sense" or "intuition" or "faith".

I'm then asking if it's reasonable to favour common sense, intuition, or faith over scientific evidence.

Of course, if you admit that we can sometimes be justified in believing that the scientific evidence is mistaken then you open yourself up to arguments for idealism or theism, as it would certainly be hypocritical, or special pleading, to argue that we must believe in an external material world because there is scientific evidence for it but that we must not believe that we are Boltzmann brains even though there is scientific evidence for it.

So if the world around me is somehow a construct of my mind, it is very different to other mental constructs. — Banno

I think the difference you are trying to draw is between a voluntary and an involuntary construct. Our mind has many involuntary aspects to it that we know of, hallucinations, emotions, tiredness, belief — you may reject some, but you can't reject all of these as involuntary constructs —, so the distinction is not useful to tell the real from the mental.

So different that one might be tempted to call it "real"? — Banno

That would be somewhat my argument against solipsism, but it works, in my view, because I redefine mind to exclude involuntary aspects. It works because it satisfactorily counters solipsism in its semantics. It does not defeat idealism or pan-psychism or open individualism or a blend of all those, because the world could still be fundamentally made of mind-stuff, or we and the world are the mind of god a la Spinoza; but it pretty much defines solipsism as very unlikely as soon as there is stuff that is not "my mind" aka a voluntary mental action. You may complain that that is not the way the word "mind" is used, but I don't write in English, I am just translating, so I don't have that concern. I don't write in Latin, but as an illustrative example ănĭmus means roughly "the rational soul", so I think we would agree that it implies a voluntary aspect, so surely there are things outside of my animus. On the other hand, mēns can mean a bunch of things including the "faculty of understanding", surely there are things outside of my mēns, but it can also mean "character", and in that case we don't know whether there is something outside of it as it is ill-defined.

Still it does not rule out the possibility that I am in fact some sort of Spinozean God imagining all this and not even realising it through some unknown convoluted mechanism, because it does not show the idea is logically impossible, but I reckon that any argument that explicitly has an ad hoc "unknown convoluted mechanism" may be discarded, as it is badly written fiction instead of philosophy, and it could be that upon investigation we realise that any possible mechanism is actually contradictory.

Edit: It does rule out the possibility if we keep the semantics of "mind" as everything that I am aware of, but then in the sense invented here the semantics of "mind" would be different.

No, it doesn't, but it might reduce the solipsist to the status of a mere object of ridicule. — Banno

That would be the case if it did defeat solipsism.

That is, in both these cases, as in the case of the existence of the world, there may be a point at which one's credulity is strained a bit too far. That point will be different for different folk, some of whom never participate in philosophy fora, some who treat it as an amusement and a very few who take it seriously enough to find themselves in an asylum.

So perhaps all up it is not unreasonable to take things at face value? — Banno

For sure it is not unreasonable. It is good to distinguish rational belief from practice. Many deterministic, physicalist atheists (broadly speaking) like me will rationally, based on evidence and logic and whatnot, conclude that there is no ultimate point to life since the universe will die one day and blah blah blah. Is there a point to living like that? Nope, because among other things I could be wrong.

Solipsism is a philosophical idea. It is a language construct. — creativesoul

The idea that all ideas boil down to language seems to suggest strong Whorfianism (improperly called Sapir-Whorf hypothesis), which is something that has been widely rejected. See: https://plato.stanford.edu/entries/linguistics/whorfianism.html

Related: imagine a bright red apple, which one do you see in your head?

Solipsism cannot be defeated with certainty, but it is defeated by plausibility. You say, "in the case that I think there is no world", but no one or almost no one thinks that due to its implausibility. The issue of solipsism only gets raised because we cannot be, as with many other things, absolutely certain it is not the case. — Janus

Agreed, we cannot be 100% sure of most things, or perhaps any. Though to rule something as less likely we need some successful arguments against it, I am pointing out that many of the arguments raised in this thread are not successful as they seem.

In any case, I remember this thread being about solipsism, but it seems the OP was edited to mean something more like object permanence and the problem of induction, or perhaps I misread the first time.

In any case, I remember this thread being about solipsism, but it seems the OP was edited to mean something more like object permanence and the problem of induction, or perhaps I misread the first time. — Lionino

The OP was not edited at all. But due to misunderstanding of many folks in their posts (including Banno), there had been extra posts added by me for clarifying and broadening the OP into any possible exploratory discussions on the elementary concepts in the OP title as well as general epistemological, sceptic, ontological and logical issues in perception.

Why? They're entailed by our best scientific theories. — Michael

They are entailed by extrapolation of some scientific theories to a future universe we don't find ourselves in a position to observe. There are lots of theories outside of physics that have a lot of evidentiary support as well.

To quote Sean Carroll from The Big Picture:

Is it possible that you and your surrounding environment, including all of your purported knowledge of the past and the outside world, randomly fluctuated into existence out of a chaotic soup of particles? Sure, it’s possible. But you should never attach very high credence to the possibility. Such a scenario is cognitively unstable, in the words of David Albert. You use your hard-won scientific knowledge to put together a picture of the world, and you realize that in that picture, it is overwhelmingly likely that you have just randomly fluctuated into existence. But in that case, your hard-won scientific knowledge just randomly fluctuated into existence as well; you have no reason to actually think that it represents an accurate view of reality. It is impossible for a scenario like this to be true and at the same time for us to have good reasons to believe in it. The best response is to assign it a very low credence and move on with our lives.

The general gist seems to be:

1. our scientific theories suggest that we are most likely Boltzmann brains
2. we are not most likely Boltzmann brains
3. therefore, our scientific theories are mistaken

The point I am making is that, by this very argument, (2) is not supported by the scientific evidence. Rather it's something like "common sense" or "intuition" or "faith". — Michael

I've been pointing out that there is science outside of physics, and on the basis of sufficient knowledge of the diversity of scientific findings we have reasons to reject 1.

I'm then asking if it's reasonable to favour common sense, intuition, or faith over scientific evidence. — Michael

I'd say it is human nature for us to favor intuition regardless of whether it is reasonable to do so. Regardless, I've pointed out that there are multiple lines of scientific evidence to consider, and one speculative extrapolation in physics doesn't provide a basis for dismissing the larger scientific picture that allows for the existence of this forum.

Of course, if you admit that we can sometimes be justified in believing that the scientific evidence is mistaken then you open yourself up to arguments for idealism or theism, as it would certainly be hypocritical, or special pleading, to argue that we must believe in an external material world because there is scientific evidence for it but that we must not believe that we are Boltzmann brains even though there is scientific evidence for it. — Michael

I'm a fallibilist and I haven't argued that "we must believe" anything.

Is it possible that you and your surrounding environment, including all of your purported knowledge of the past and the outside world, randomly fluctuated into existence out of a chaotic soup of particles? Sure, it’s possible. But you should never attach very high credence to the possibility. Such a scenario is cognitively unstable, in the words of David Albert. You use your hard-won scientific knowledge to put together a picture of the world, and you realize that in that picture, it is overwhelmingly likely that you have just randomly fluctuated into existence. But in that case, your hard-won scientific knowledge just randomly fluctuated into existence as well; you have no reason to actually think that it represents an accurate view of reality. It is impossible for a scenario like this to be true and at the same time for us to have good reasons to believe in it. The best response is to assign it a very low credence and move on with our lives. — Sean Carroll

1. If we are not Boltzmann brains then we can trust our scientific knowledge
2. Our scientific knowledge strongly suggests that we are most likely Boltzmann brains
3. Therefore, if we are not Boltzmann brains then we are most likely Boltzmann brains

There's certainly some "cognitive instability" in his position, too.

So it's back to what I said here. Either we are most likely Boltzmann brains or we cannot trust our scientific knowledge.

There are lots of theories outside of physics that have a lot of evidentiary support as well. — wonderer1

So which theories outside physics are evidence against the eventual heat death of the universe and/or the fluctuations/nucleations that will give rise to Boltzmann brains? And how do we determine which evidence is stronger?

Of course, one solution to all of this is to abandon scientific realism and favour instrumentalism instead.

How about a Boltzmann universe?

1. If we are not Boltzmann brains then we can trust our scientific knowledge
2. Our scientific knowledge strongly suggests that we are most likely Boltzmann brains
3. Therefore, if we are not Boltzmann brains then we are most likely Boltzmann brains

There's certainly some "cognitive instability" in his position, too. — Michael

I think number 1 is upside down, what Sean Carroll seems to suggest is that:

1. If we are Boltzmann brains, we cannot trust our scientific knowledge.
2. Our scientific knowledge strongly suggests that we are most likely Boltzmann brains.
3. Therefore, if we are indeed Boltzmann brains, we cannot trust our scientific knowledge.
4. If we are Boltzmann brains, we cannot trust that we are Boltzmann brains.

So from that, and that is me speaking, there are five options here:

A. If we are Boltzmann brains, we can believe that we are Boltzmann brains, but even if right we cannot be justified in believing so because our science is a random fluctuation, thus unreliable.
B. If we are Boltzmann brains, we can believe that we are not Boltzmann brains but we would be wrong.
C. If we are not Boltzmann brains, we can believe that we are Boltzmann brains and be justified in believing so if we believe our science is right, and we would be wrong.
D. If we are not Boltzmann brains, we can believe that we are not Boltzmann brains and be justified in believing so if we believe our science is right and we got in very low probability, and we would be right.
E. If we are not Boltzmann brains, we can believe that we are not Boltzmann brains and be justified in believing so if we believe our science is wrong, and we would be right.

So there are two scenarios where we are right and have justification, one being that we got lucky (unlikely). So it is not "impossible for a scenario like this to be true and at the same time for us to have good reasons to believe in it", it is just a very unlikely scenario. But the justification of something generally bears no weight on its actual truth-value, so "best response is to assign it a very low credence" is no good, as it is still possible that we are Boltzmann brains without justification, so I will settle for 50% chances, but I am willing to concede that number.

How about a Boltzmann universe? — Michael

You posted this as I was finishing my post above. Enough brain-twisters for today.

I think number 1 is upside down, what Sean Carroll seems to suggest is that: — Lionino

I was presenting the inverse of his argument to show that his position suffers from that same cognitive instability.

I was presenting the inverse of his argument to show that his position suffers from that same cognitive instability. — Michael

His argument is if P, not Q (if we are Boltzmann brains, we cannot trust our scientific knowledge); you showed how {if not P, Q} (if we are not Boltzmann brains, we can trust our scientific knowledge) entails a contradiction. How does that show his position has the same issue? If anything, it entails his position is true: ¬◇(¬p→q) → □(p→¬q).

It seems you use "perceive" were you might better use "interact".

That might be all that is problematic with this thread.

I think the difference you are trying to draw is between a voluntary and an involuntary construct. — Lionino

I don't think so. There is for me a clear difference to be made between the apple on the table and an imagined apple. That is, after all, why we have the language around imagination. Same goes for dreaming - if we could not tell whether or not we are dreaming, we would not have the word "dream".

There are lots of things of which we are certain.

That just begs the question by assuming that our scientific theories show that we are most likely Boltzmann brains, it doesn't explain how a random fluctuation like a Boltzman brain could come up with consistent and coherent scientific theories that show that it is most likely a Boltzmann brain, nor does it answer the questions I posed about memory.

Agreed, we cannot be 100% sure of most things, or perhaps any. Though to rule something as less likely we need some successful arguments against it, I am pointing out that many of the arguments raised in this thread are not successful as they seem. — Lionino

The way I see it is that something should be thought to be less likely if it is less plausible in light of our experience, less consistent with that experience, and to my way of thinking solipsism seem way less likely, in fact improbable in the extreme, in light of that experience.

Which arguments in this thread do you see failing and on what basis do you assess them as failures?.

it doesn't explain how a random fluctuation like a Boltzman brain could come up with consistent and coherent scientific theories that show that it is most likely a Boltzmann brain — Janus

I think that would also be up to randomness, a Boltzmann brain with those specific theories would be magnitudes more unlikely than an ordinary Boltzmann brain. I didn't see what the memory question was.

The way I see it is that something should be thought to be less likely if it is less plausible in light of our experience, less consistent with that experience, and to my way of thinking solipsism seem way less likely, in fact improbable in the extreme, in light of that experience. — Janus

That works in practical everyday life. But if we are to go by that, we would simply do away with the problem of induction, for one; we would do away with so many things that are still considered worthwhile in philosophy. Experience is not the goal to end all goals.

Which arguments in this thread do you see failing and on what basis do you assess them as failures? — Janus

All the ones I rebutted to and that at the end of the discussion I did not acquiesce to the person's point.

I didn't see what the memory question was. — Lionino

The question wasn't addressed to you, but it was this: apparently the theory of Boltzmann brains entails that our memories are illusory, cannot be trusted; if this is so how could we trust our scientific theories, or even trust that we remember them correctly, or that they were ever really formulated? The other question was as to how distant do your memories have to be to be illusory: a year, a month, a day, an hour, a minute, a second?

That works in practical everyday life. But if we are to go by that, we would simply do away with the problem of induction, for one; we would do away with so many things that are still considered worthwhile in philosophy. Experience is not the goal to end all goals. — Lionino

There is no "problem of induction"; Hume merely showed that induction is not deduction, that inductive inferences are no necessary. All we have to go on is experience, on what other criteria could we ever justifiably decide to place our faith? You might say logic or mathematics, but they don't tell us anything definite about things, except insofar as their pronouncements and predictions are found to obtain.

What are the "so many worthwhile things" you see in philosophy and why do think they are worthwhile? Is it just because they are still around, because some people are still arguing about them?

All the ones I rebutted to and that at the end of the discussion I did not acquiesce to the person's point. — Lionino

You mean all the ones you, in your opinion, successfully rebutted? That isn't helpful at all and you should be able to cite at least one or two of those arguments and explain why you think they didn't stand up to your purported rebuttals. I suspect you think you rebutted them simply because they did not achieve 100% certainty.

That just begs the question by assuming that our scientific theories show that we are most likely Boltzmann brains — Janus

I'm not assuming it. It's what physicists like Boltzmann, Eddington, Feynman, Sean Carroll, Brian Greene, and others say. I'm deferring to their expertise.

His argument is if P, not Q (if we are Boltzmann brains, we cannot trust our scientific knowledge); you showed how {if not P, Q} (if we are not Boltzmann brains, we can trust our scientific knowledge) entails a contradiction. How does that show his position has the same issue? — Lionino

It's right there in that post you first responded to:

1. If we are not Boltzmann brains then we can trust our scientific knowledge
2. Our scientific knowledge strongly suggests that we are most likely Boltzmann brains
3. Therefore, if we are not Boltzmann brains then we are most likely Boltzmann brains

Obviously (3) is problematic. Therefore we must reject either (1) or (2). As I said in my above post, many prominent physicists accept that (2) is true (even if they want to avoid the implication), and so I defer to their expertise.

So, as I said earlier, either we are most likely Boltzmann brains or we cannot trust our scientific knowledge.

But in that case, your hard-won scientific knowledge just randomly fluctuated into existence as well; you have no reason to actually think that it represents an accurate view of reality.

Also on this, the same argument I made to Banno earlier can be used.

Each of these is true (if our current theories are correct):

1. Most Boltzmann brains have inaccurate scientific knowledge
2. Most observers with accurate scientific knowledge are Boltzmann brains

It's right there in that post you responded to:

1. If we are not Boltzmann brains then we can trust our scientific knowledge
2. Our scientific knowledge strongly suggests that we are most likely Boltzmann brains
3. Therefore, if we are not Boltzmann brains then we are most likely Boltzmann brains — Michael

Sorry, me no understand.

if this is so how could we trust our scientific theories, or even trust that we remember them correctly, or that they were ever really formulated? — Janus

You are right, this wasn't addressed to me and I don't know the specifics, but what you are saying reminds me of the tidbits in this page about Sean Caroll. It seems the matter was discussed there to some extent, if that helps.

Hume merely showed that induction is not deduction, that inductive inferences are no necessary — Janus

The problem of induction is that there is no reason to be sure that the future will be like the past, or simply that we can't derive a "will be" from a "has been". We agree on that?
If we do, according to your proposal that "something should be thought to be less likely if it is less plausible in light of our experience", the problem of induction dissolves. As all our experiences have told us that X causes Y, anything else is completely inconsistent with our experiences, so anything else is completely unlikely; therefore, we could expect from all the "Y was from X" that "Y will be from X". Science works that way — and unlike many folks I for one don't think the logical positivists were crazy —, but we are dealing with metaphysics.
I understand what you say about consistency with our past experiences, but in this one case I don't think it applies, since we are questioning the background of our experiences.

Is it just because they are still around, because some people are still arguing about them? — Janus

For the most part, yes, people who are just as smart as or smarter than me are still arguing about it. And for them it is profession, not hobby. So it leads me to conclude it is not something that we can brush aside easily.

You mean all the ones you, in your opinion, successfully rebutted? — Janus

Well, yeah, naturally if my opinion were otherwise I would have granted everybody's point and left.
For one, I think I pretty successfuly showed here that there is no pragmatic contradiction in being a solipsist and engaging in discussions about solipsism. But it is not even an argument against solipsism proper, it is more of a gotcha.
Another, the argument from language is bad, and my rebuttal was the same as the one for pragmatic contradiction. I think the user is drawing from Wittgenstein's idea of private language, but he doesn't really make an argument for it, he just states it.

Sorry, me no understand. — Lionino

Consider this strengthened argument:

1. If we are not Boltzmann brains then our scientific theories are true
2. One of our scientific theories is that we are most likely Boltzmann brains
3. Therefore, if we are not Boltzmann brains then the scientific theory that we are most likely Boltzmann brains is true

Do you see the problem with (3)?

So it's back to what I said here. Either we are most likely Boltzmann brains or we cannot trust our scientific knowledge. — Michael

That's a false dichotomy, and things aren't nearly that black or white.

There are areas in which I can and do trust my scientific knowledge with my life (and the lives of other people) depending on it. There are other areas of scientific knowledge in which I can't trust my knowledge to nearly the same extent.

Perhaps the most relevant question in this discussion is the extent to which you can trust your scientific knowledge?

FWIW:

ChatGPT 3.5

User
are there any physicists who believe we are boltzmann brains

ChatGPT
The concept of Boltzmann brains is a speculative idea in physics proposed by Ludwig Boltzmann and later expanded upon by physicists like Sean Carroll and others. It suggests that it's statistically more likely for a conscious observer, like a human brain, to spontaneously fluctuate into existence in a high-entropy state rather than to arise through the natural process of evolution. While some physicists entertain this idea as a thought experiment to explore the implications of cosmology and the second law of thermodynamics, it's not widely accepted as a serious hypothesis. Instead, it raises questions about the nature of reality and our understanding of the universe.

User
do any physists claim to be a boltzmann brain

ChatGPT
It's unlikely that any physicist would claim to be a Boltzmann brain in a literal sense. The concept of Boltzmann brains is primarily a thought experiment rather than a literal assertion about the nature of consciousness or existence. Physicists who discuss the idea typically use it to explore the implications of certain cosmological theories and the second law of thermodynamics, rather than as a statement about their own existence.

That's a false dichotomy, and things aren't nearly that black or white. — wonderer1

Then to be more accurate: either we are most likely Boltzmann brains or we cannot trust the scientific evidence that entails that we are most likely Boltzmann brains.

There are areas in which I can and do trust my scientific knowledge with my life (and the lives of other people) depending on it. There are other areas of scientific knowledge in which I can't trust my knowledge to nearly the same extent. — wonderer1

Which is why I asked the question: given that we have scientific evidence that entails that we are most likely Boltzmann brains, what justifies our claim that we are not most likely Boltzmann brains?

Consider this strengthened argument:

1. If we are not Boltzmann brains then our scientific theories are true
2. One of our scientific theories is that we are most likely Boltzmann brains
3. Therefore, if we are not Boltzmann brains then the scientific theory that we are most likely Boltzmann brains is true

Do you see the problem with (3)? — Michael

3 is a contradiction, hard to disagree with that. My point was more that you seemed to agree with Sean Caroll, because his argument was the opposite of the premise that you refuted by probability in the original argument. Sean's point is about justification.

Which is why I asked the question: given that we have scientific evidence that entails that we are most likely Boltzmann brains, what justifies our claim that we are not most likely Boltzmann brains? — Michael

What scientist makes the claim that we have scientific evidence that we are most likely Boltzmann brains?

3 is a contradiction, hard to disagree with that. My point was more that you seemed to agree with Sean Caroll, because his argument was the opposite of the premise that you refuted by probability in the original argument. Sean's point is about justification. — Lionino

Carroll pointed out the paradoxical nature of this:

1. Assume that we are most likely Boltzmann brains
2. Most Boltzmann brains do not have accurate scientific knowledge
3. Therefore, we most likely do not have accurate scientific knowledge
4. Our scientific knowledge entails that we are most likely Boltzmann brains
5. Therefore, our scientific knowledge that entails that we are most likely Boltzmann brains is most likely inaccurate
6. Therefore, we are most likely not Boltzmann brains

He then uses this to reject (1).

I then simply offered an inverse of the argument:

1. Assume that we are most likely ordinary humans
2. Assume that we have accurate scientific knowledge
3. Our scientific knowledge entails that we are most likely Boltzmann brains
4. Therefore, our scientific knowledge that entails that we are most likely Boltzmann brains is most likely accurate
5. Therefore, we are most likely not ordinary humans

I then use this to reject either (1) or (2).

The "cognitive instability" applies to both sides of the issue.

What scientist makes the claim that we have scientific evidence that we are most likely Boltzmann brains? — wonderer1

Several are mentioned in the Wikipedia article, e.g. Boltzmann, Eddington, Feynman, Sean Carroll, and Brian Greene.

On ChatGPT, here is an example of it contradicting itself three times in a row.
https://chat.openai.com/share/96378835-0a94-43ce-a25b-f05e5646ec40
And don't ever ask it to do any engineering https://chat.openai.com/share/b5241b53-e4d8-4cab-9a81-87fa73d740ad