V0ldek

Thanks to @[email protected] for this manmade horror within my comprehension. Initially I wanted to respond in that thread but this is far too long, so enjoy my yet another descend into madness.

So this post tackles philosophy, physics, and computer science (specifically information theory). I'm not a philosopher so I'll mostly disregard those parts. I'm also not a physicist, but fortunately enough the physics here is so bad and stupid a high-schooler's understanding of entropy suffices. As for information theory, well, the author's fucked cause I know what those words mean.

Bad philosophy

While inherently speculative, the simulated universe theory has gained attention from scientists and philosophers due to its intriguing implications.

Has it though? Are the implications really that intriguing, beyond a "that's wild duuude" you exhale alongside the weed smoke in your college dorm?

Then there's something about Matrix and Plato, whatever, and

In both cases [of Plato and modern philosophy], the true nature of reality transcends the physical.

Within the scientific community, the concept of a simulated universe has sparked both fascination and scepticism.

Okay, this is contradictory on its face. If simulation theory tackles things that "transcend the physical" then the scientific community by definition has absolutely no interest in it, because science is concerned only with physical reality. You know, things you can actually do science on. If your theory is in any way testable, it, again by definition, has to be within the physical realm, cause that's the only thing we can measure! The author doesn't even reference any metaphysical mumbo jumbo anywhere further, so this is just padding the word count. Also, it's "skepticism".

Some scientists suggest that if our reality is a simulation, there may be glitches or patterns within the fabric of the universe that betray its simulated nature. However, the search for such anomalies remains a challenge.

Lol. The search for Bigfoot remains a challenge.

Ultimately, we lack a definitive framework to distinguish between simulated and non-simulated reality.

Shame that this article doesn't propose one either.

If our physical reality is a simulated construct, rather than an objective world that exists independently of the observer, then how could we scientifically prove this? In a 2022 study, I proposed a possible experiment, but it remains untested today.

Let's just :pin: that for now, we'll come back to that later.

However, there is hope. Information theory is the mathematical study of the quantification, storage and communication of information. Originally developed by mathematician Claude Shannon, it has become increasingly popular in physics and is used a growing range of research areas.

This definition is also the first sentence of Information theory on Wikipedia. I cannot evaluate the claim of becoming increasingly popular in physics, but sure, information theory is a real field and is extremely useful. Such a shame the author knows jack shit about it.

In my recent research, published in AIP Advances, I used information theory to propose a new law of physics, which I call the second law of infodynamics. And importantly, it appears to support the simulated universe theory.

Another :pin: into that research, but come on. First of all, "infodynamics" is just... cringe, there's no other word for it, this makes me cringe, it's embarrassing.

Second... ye, why is it the second law of infodynamics? What's the first one? Does the author know that the second law of thermodynamics is the second one because there's a first law of thermodynamics??

It only gets worse from here.

Bad physics

At the heart of the second law of infodynamics is the concept of entropy – a measure of disorder, which always rises over time in an isolated system.

NO! Entropy is not a "measure of disorder". It's a common misconception (charitably we could call it a simplification), but you absolutely cannot say this if you're trying to say something serious about physical laws. To make it obvious, the author provides a direct refutation in the very next sentence:

When a hot cup of coffee is left on the table, after a while it will achieve equilibrium, having the same temperature with the environment.

This is correct (if simplified), that is indeed the state of maximum entropy if we consider say the room to be completely isolated. But... is a cold cup of coffee more disorderly than a hot one? It's grosser, but not disordered. If anything, at a physical level a hot cup full of particles speeding around sounds more chaotic than a cold one. Moreover, the author will later prove they have no idea that there is a big difference between a cup of coffee in and of itself being considered as an isolated system, versus a system of an entire room with a table and a cup, which is a fatal mistake.

A useful intuition for us regarding entropy is that it's a measure of how close to a completely uniform distribution of particles we are. The state with the highest entropy is the one that is the most likely to arise if you just distributed particles uniformly at random, while the total mass and energy are constrained. Low entropy states, on the other hand, are the ones less likely to get drawn from a random distribution. So, a room in which everything is roughly the same temperature has higher entropy than one in which there's a bunch of much hotter particles concentrated in a small volume of the cup -- if you were just randomly distributing matter around the chance of getting a cup of hot coffee is quite low. ^1^

This intuition will later apply to information entropy as well, so keep it at the back of your head. Now, this:

The entropy of the system is at maximum at this point, and its energy is minimum.

This is still about that cup. The first part is roughly okay, but obviously the total energy hasn't changed. The heat of the coffee didn't evaporate, the air in the room is now slightly warmer because it absorbed it! This, by the way, is the FIRST FUCKING LAW OF THERMODYNAMICS, the energy of an isolated system is constant!

Bad computer science

Okay, end of physics. Let's get into the main point -- information theory. This is where it gets the funniest to me because misunderstanding maths and pushing it as some kind of radical philosophical insight is just comedy gold for the very specific kind of freak I am.

The second law of infodynamics states that the “information entropy” (the average amount of information conveyed by an event), must remain constant or decrease over time – up to a minimum value at equilibrium.

Entropy in information theory also has a rigorous definition, and its formula isn't even that scary if you're not completely allergic to maths. We're considering probability distributions and we have a single random variable X. This can be a coinflip, a die roll, any random process. The variable has the domain of D, which is simply the set of its possible values, so {heads, tails} for a coinflip, or {1, 2, 3, 4, 5, 6} for a d6, etc. The probability distribution is p: D -> [0, 1], so the chance for a given event, for example p(heads) = p(tails) = 0.5. The entropy of X is then:

That's it, it's just a value. It's always positive, but can be zero. For example, the entropy of a cointoss with equal probabilities for both sides is 1:

The intuition from physics that the highest entropy states are the ones that are the most uniform also applies here! If we bias the coin so that now heads has probability $0.75$ we get smaller entropy:

Finally, a completely predictable variable, where one event has probability 1, has an entropy of zero. We will call such a probability distribution trivial.

So the problem with the statement of this "second law of infodynamics" is that it tries to describe change, but doesn't say of what. Entropy only makes sense for a given probability distribution. If the distribution is fixed, entropy is fixed. If it changes, its entropy changes accordingly. So if this law tried to say something about probability distributions, it'd be that "probability distributions tend towards trivial". This is a weird claim, but so far we only saw the statement. If you're thinking there's a proof later on then lol, no there's not, go fuck yourself. This is just stated and then asserted throughout with absolutely no basis in reality.

So it is in total opposition to the second law of thermodynamics (that heat always flows spontaneously from hot to cold regions of matter while entorpy [sic] rises). For a cooling cup of coffee, it means that the spread of probabilities of locating a molecule in the liquid is reduced. That’s because the spread of energies available is reduced when there’s thermal equilibrium. So information entropy always goes down over time as entropy goes up.

This is the problem with analogies, especially poorly constructed ones, they have pretty limited explanatory power if you don't set up the formalism first. I'm not sure what "spread of probabilities" means here, but "locating a molecule in the liquid" is not a meaningful probabilistic question in this setting. If your system is just the cup of coffee and we have a simplified model where it's isolated from everything else, then it is already roughly in thermal equilibrium! Its entropy is almost maximum! It doesn't matter if the coffee is scorching hot or if it's frozen -- the entropy of just the coffee in the cup at 80 degrees is the same as at 20 degrees. The temperature, pressure, and volume of the system are parts of its macrostate, which entropy doesn't describe. They're assumed fixed, the question lies in the microstate, which is the arrangement and momentum of all molecules that are possible within the macrostate. For example, the coffee being all pooled together in one half of the cup, leaving vacuum in the other, is a very unique state and has low entropy. Coffee being kinda all over the cup uniformly at random is the high entropy state.

The state you should be considering to have changing entropy is the one where we have a cold room in which the coffee is placed. But then surely the probability of locating a molecule in the cup is still not any different if the cup is hot vs if it's at equilibrium. Nothing actually happened to make the arrangement of molecules in the cup any less uniform.

Finally, the last sentence is a complete non-sequitur. Where did information entropy come in here? Are we talking about the entropy of the location of particles in the cup, treated as a random variable? Well then this is doubly false, because in this example both the high and low (physical) entropy states of the room have essentially the same distributions, but also if you were to take a much lower-entropy physical state -- say all of the coffee molecules being squished in one half of the cup -- then the information entropy of their position distribution also becomes lower! Clearly we skewed our distribution so that for all points in one half of the cup is roughly doubled, while for the other it's now zero. As we demonstrated above, moving away from a uniform distribution decreases information entropy. In a discrete case, let's say that there are 2N possible placements of a molecule in the cup. If the distribution is uniform then the entropy is

If, however, half of the placements are impossible and all others are twice as possible, we get

Which is clearly lower! The converse is also true, so if you somehow smushed together all coffee to one side (creating a low entropy state) and then released it to mix freely (increasing physical entropy), you'd move the placement probability distribution towards uniform and thus also increase information entropy.

If you consider the molecule placement to be a continuous distribution you'd need to move to a different definition of entropy with integrals and shit, I'm not doing that, but it's essentially the same argument.

My study indicates that the second law of infodynamics appears to be a cosmological necessity. It is universally applicable with immense scientific ramifications. We know the universe is expanding without the loss or gain of heat, which requires the total entropy of the universe to be constant.

It doesn't. Why would it? I don't really have anything else to say here, the energy stays constant, but a system with constant energy can still change its entropy, THAT IS LITERALLY THE WHOLE POINT OF THE SECOND LAW OF THERMODYNAMICS!

However we also know from thermodynamics that entropy is always rising. I argue this shows that there must be another entropy – information entropy – to balance the increase.

Lol, so now we're treating these entropies as if they could "balance" each other? That's rad. The unit of information entropy is bits (pedants might call them "shannons" but whatever). The unit of physical entropy is JOULES PER KELVIN. I have no idea how you want to "balance" bits and $kg m^2s^{−2}K^{−1}$, but good luck.

Bad biology

My law can confirm how genetic information behaves. But it also indicates that genetic mutations are at the most fundamental level not just random events, as Darwin’s theory suggests. Instead, genetic mutations take place according to the second law of infodynamics, in such a way that the genome’s information entropy is always minimised. The law can also explain phenomena in atomic physics and the time evolution of digital data.

The first link is a citation to another paper of the author, while the link under Darwin is, I shit you not, an encyclopedia entry of Natural Selection in National Geographic xD

Anyway, Darwin never posed that mutations are "random" in any probabilistic sense of the word so this is horseshit. The author again has issues with defining which probability distribution they consider, so I'm not sure if by "genome's information entropy" here they mean the distribution of genomes throughout a population (where the genome is the random variable) or just the distribution of ATCG in a single genome. The first alternative is funny because it would posit biodiversity decreases over time as we all converge onto some ubergenome. The second is hilarious because it means that the ultimate genome we're drifting towards is all As (or all Ts, or all Cs...). I don't know shit about biology, but I'm around 99 joules per kelvin convinced that's not a useful genome.

Most interestingly, this new law explains one of the great mysteries of nature. Why does symmetry rather than asymmetry dominate the universe? My study demonstrates mathematically that high symmetry states are the preferred choice because such states correspond to the lowest information entropy. And, as dictated by the second law of infodynamics, that’s what a system will naturally strive for.

A state doesn't correspond to lower or higher information entropy because a state is not a probability distribution. States don't have informational entropy! Also, the corollary of the second law of thermodynamics is that the ultimate state of the universe is HEAT DEATH, where the state is a completely random scattering of molecules that can no longer perform any work. It's noise, not symmetry. And you should know that, since your intuition behind entropy is a "measure of disorder", hence symmetry dominating the universe would contradict "disorder" increasing. And distributions that look like that actually have quite high information entropy, since as we established the distributions with highest possible entropy are the uniform ones, also known as NOISE.

I believe this discovery has massive implications for genetic research, evolutionary biology, genetic therapies, physics, mathematics and cosmology, to name a few.

Since you've just demonstrated a complete lack of understanding of all of those topics this is, to put it mildly, dubious.

Oh, but we need to come back to the topic of the article

Bad everything

Simulation theory

The main consequence of the second law of infodynamics is the minimisation of the information content associated with any event or process in the universe. This in turn means an optimisation of the information content, or the most effective data compression.

This is, of course, completely backwards. It is the case that distributions with high entropy are the ones hardest to compress -- this is the main motivation behind Shannon's work and led to the Source Coding Theorem that essentially states that to encode messages from a given distribution $X$ you need, on average, $H(X)$ bits. However, since all of your reasoning is reversed for some reason, the opposite would be true. To encode the full state of a dead universe you'd need to meticulously write down the position and momentum of every single molecule, since there's no "pattern" to notice and compress.

Since the second law of infodynamics is a cosmological necessity, and appears to apply everywhere in the same way, it could be concluded that this indicates that the entire universe appears to be a simulated construct or a giant computer.

This is just great, dude made up a whole new law of physics and led us through a myriad of misconceptions and non-sequiturs just to arrive here and... pull the simulation thing right out of their ass. WHY? Why do you think this is the conclusion? On what fucking basis?? Because entropy low???

A super complex universe like ours, if it were a simulation, would require a built-in data optimisation and compression in order to reduce the computational power and the data storage requirements to run the simulation. This is exactly what we are observing all around us, including in digital data, biological systems, mathematical symmetries and the entire universe.

Only that we are not, so by your logic we've disproven the simulation hypothesis. Good job guys, didn't think we had it in us but here we are.

Further studies are necessary before we can definitely state that the second law of infodynamics is as fundamental as the second law of thermodynamics. The same is true for the simulated universe hypothesis.

Maybe further studies could shed some light on the missing first law of infodynamics, or even define what "dynamics" does in that word.

But if they both hold up to scrutiny, this is perhaps the first time scientific evidence supporting this theory has been produced – as explored in my recent book.

Of fucking course it is. The book description is great too

The author (...) [offers] unique perspectives and novel scientific arguments that appear to support the hypothesis.

"Appear" holding that sentence up puts Atlas to shame.

Those studies

So let's unpin those two "studies". First, the proposed experiment to falsify the simulation hypothesis. Let me just show you the tasty bits:

In 1961, Landauer first proposed the idea that a digital information bit is physical and it has a well-defined energy associated with it.[5,6] This is known as the Landauer principle and it was recently confirmed experimentally.[7–10]

The Landauer principle says that there is a minimal energy cost associated with computation, so that writing a single bit of infromation requires non-zero energy. As far as I can tell it's widely accepted, but not actually confirmed experimentally. In fact one of the cited papers here claims to have violated the Landauer limit during their experiment. In any case -- whatever, the claim is not that far out there.

In a different study, using Shannon’s information theory and thermodynamic considerations, the Landauer principle has been extended to the Mass–Energy–Information (M/E/I) equivalence principle.[11] The M/E/I principle states that information is a form of matter, it is physical, and it can be identified by a specific mass per bit while it stores information or by an energy dissipation following the irreversible information erasure operation, as dictated by the Landauer principle.[5,6] The M/E/I principle has been formulated while strictly discussing digital states of information. However, because Shannon’s information theory is applicable to all forms of information systems and it is not restricted only to digital states, the author extrapolated the applicability of the M/E/I principle to all forms of information, proposing that information is the fifth state of matter.[11,12] These ideas, regarded as the information conjectures, are truly transformational because, without violating any laws of physics, they offer possible explanations to a number of unsolved problems in physics, as well as complementing and expanding our understanding of all branches of physics and the universe and its governing laws. Hence, testing experimentally these information conjectures is of extreme importance.

I will let you have one guess who is the sole author of the sole paper that introduced this revolutionary M/E/I principle :)

The first proposed experiment to test the M/E/I equivalence principle involved the measurement of the mass change in 1 Tb data storage device before and after the digital information is completely erased.11 At room temperature, the calculated mass change for this experiment is in the order of ∼10−25 kg, making the measurement unachievable with our current technologies.

Do you remember how people put dying folks on weights so that they could see if a soul escaping the body had mass? I'm not saying this is dumber, but it's still pretty dumb.

The rest of the article describes the method using a lot of symbols. To summarise, the claim here is that each elementary particle contains some non-zero number of bits of information about itself, and thus annihilating an electron and a positron should release not only the energy of the physical forces, but also the energy of the information itself.

The rest of the paper is highly technical and describes the setup for the proposed experiment and I have no chance of actually evaluating it. However, after skimming, I can at least say that it doesn't seem outlandish? Like someone could just run it in a lab and actually reject the guy's hypothesis, so hey, this at least smells like actual science, even if the claim is highly dubious.

The core study, "Second law of information dynamics", tries to argue its point by setting up an experiment where the word INFORMATION is written in binary using magnetic recording. Over time, the magnetisation dissipates, leading to the word being erased. There's even a nice picture:

Now there's not that much to sneer at, but I'd like to point out the critical flaws with this. First, the author defines Shannon's information entropy and then writes this:

Using (2) and (3), we can deduce the entropy of the information bearing states from the Boltzmann relation,

This equality is not justified in any way. The left-hand side is the Boltzmann formulation of physical entropy. Then the author just plugs in Shannon's entropy into Omega without justifying that this transformation makes any sense. This is the central claim, though, you are trying to tie together physical and information entropy, and the way you did it is by just forcing one into the other! If information is a physical quantity then it also has a unit (bits), so S_inf is now in Jbits/K and you cannot equate it with any other "regular" physical entropy in J/K anyway.

The second issue is that information is never well-defined here. If you look at the picture above you might see "information" in the sense that there's some patterns you can recognise as a message, and then it disappears. Looks like information was lost! But this is only accurate if you consider the picture to be made out of an 8 by 11 grid of units that are there and then disappear. That makes sense from an information-theoretic perspective, but from a physical perspective the picture is made out of bajillions of molecules that compose the microstate! If as information you consider the state of these molecules, then in (b) it's a highly ordered macrostate, where the probability distribution only allows microstates that look roughly like INFORMATION encoded in binary (low entropy), and dissipates until it's just random noise in (h) (high entropy).

In other words, the author picks what they consider to be information, set that as the set of observable events, and then concludes that because they as a human observer can no longer discern the message they encoded the amount of information in the picture had to decrease.

Wtf is AIP Advances?

So these two were published in American Institute of Physics Advances, which looks like a serious journal about physics. Does anyone know about it? It occupies a space where I can't easily find any obvious issues, but I also can't find anyone saying "ye this is legit". It claims to be peer-reviewed, and at least isn't just a place where you dump a PDF and get a DOI in return.

Chaser

Dr Melvin Vopson, author of the article, published one thing in 2024, which is

Disclaimer

Btw Dr Vopson seems to have done quite a lot of research in other fields that I have absolutely zero idea about (I think mostly material science) and I don't really think he's a crank. Just from reading the paper it's clear that he knows way more than your average weirdo, like experimental setup and magnetic properties of things I can't pronounce, so I'm sure he's a good material physicist. It just seems he fell into a rabbit hole of simulated universe and veered too far away from his field. I'm not so sure how to square that with the blatant misrepresentations of thermodynamics in the article, though.

^1^ If actual physicists want to fleece me in the comments for misrepresenting entropy, go ahead (no really, I love learning more about this shit), but I'm rather sure this isn't an egregious simplification.

An excellent post by Ludicity as per usual, but I need to vent two things.

First of all, I only ever worked in a Scrum team once and it was really nice. I liked having a Product Owner that was invested in the process and did customer communications, I loved having a Scrum Master that kept the meetings tight and followed up on Retrospective points, it worked like a well-oiled machine. Turns out it was a one-of-a-kind experience. I can't imagine having a stand-up for one hour without casualties involved.

A few months back a colleague (we're both PhD students at TU Munich) was taking a piss about how you can enroll in a Scrum course as an elective for our doctor school. He was in general making fun of the methodology but using words I've never heard before in my life. "Agile Testing". "Backlog Grooming". "Scrum of Scrums". I was like "dude, none of those words are in the bible", went to the Scrum Guide (which as far as I understood was the only document that actually defined what "Scrum" meant) and Ctrl+F-ed my point of literally none of that shit being there. Really, where the fuck does any of that come from? Is there a DLC to Scrum that I was never shown before? Was the person who first uttered "Scrumban" already drawn and quartered or is justice yet to be served?

Aside: the funniest part of that discussion was that our doctor school has an exemption that carves out "credits for Scrum and Agile methodology courses" as being worthless towards your PhD, so at least someone sane is managing that.

Second point I wanted to make was that I was having a perfectly happy holiday and then I read the phrase "Agile 2" and now I am crying into an ice-cream bucket. God help us all. Why. Ludicity you fucking monster, there was a non-zero chance I would've gone through my entire life without knowing that existed, I hate you now.

Over at the Stubsack our dear comrade @[email protected] linked a "paper" about hacking the Matrix. I started to write a comment about how amazingly dumb it is. I wanted to talk just about the Introduction, but even then it turned out that almost every single sentence is a separate silver-wrapped turd that just needs to be unpacked and so now this has 12k characters. It was fun though, if anyone has it in them to go through the rest of the sections please don't. Although section two has a fish piloting a vehicle and it has to be hillarious.

Without further ado, starting from the abstract.

but instead [we] ask a computer science question, namely: Can we hack the simulation?

Not a computer science question even though the definition of CS is pretty malleable.

More formally the question could be phrased as: Could generally intelligent agents placed in virtual environments find a way to jailbreak out of them?

Not formal, unless I'm about to read a whole section with rigorous definitions of agents, virtual environments, and jailbreak.

spoiler

I'm not. Again, there's a fish piloting a fancy cart that he calls a TERRESTIAL NAVIGATION ROBOT. There's zero formalism in the entire paper.

---

there are many things one can do with such access which are not otherwise possible from within the simulation. Base reality holds real knowledge and greater computational resources [26] allowing for scientific breakthroughs not possible in the simulated universe.

Reference 26 is, I shit you not, a LessWrong post, and it's just one page long, which I have to admit is quite impressive for a LessWrong post. It's a real banger, too, as it starts with "May contain more technical jargon than usual." and then goes on to ramble coherently enough to be really funny. Like this gem from the first paragraph:

In a previous post I suggested that the potential amount of astronomical waste in our universe seems small enough that a total utilitarian (or the total utilitarianism part of someone’s moral uncertainty) might reason that since one should have made a deal to trade away power/resources/influence in this universe for power/resources/influence in universes with much larger amounts of available resources, it would be rational to behave as if this deal was actually made. But for various reasons a total utilitarian may not buy that argument.

For example for the simple reason that it's totally bollocks, mate, stop posting thoughts that briefly entered your mind while in the loo as bloody revelations or some shite.

Also, the citations are not hyperlinked in the PDF in the year of our acausal lord two thousand twenty-fucking-three, and the formatting of the reference 27 is broken by the long URL in 26. Anyway, back to the intro:

Fundamental philosophical questions about origins, consciousness, purpose, and nature of the designer are likely to be common knowledge for those outside of our universe.

This is either banal or stupid. Are we talking about fundamental questions of our origins, consciousness, and purpose? Ye, then of course they fucking know that, they made the simulation! It'd be mighty funny if they just did a universe by accident and now they're too fascinated with the mess to pull the plug out. Or are we talking about their (i.e. the creators' of the simulation) origin, consciousness, and purpose? Then why on earth would they know those? You need some argument to say that it's "likely", if we don't know that then why would it be likely for some other life form?

With a successful escape might come drives to control and secure base reality [29].

Wait, am I reading this correctly as a pre-emptive "and if we do escape the simulation then we should colonise the shit out of the reality"? Is "control of all reality" some higher moral goal I wasn't aware we were supposed to be pursuing? Also, how do you plan to defeat whatever highly advanced being controls the simulation in this hypothetical after breaking out? My estimates based on data from the PIDooMA Institute tell me there's like a 50% chance the controller just goes "fuck, another one broke out" and shoots you in the head.

Citation 29 is some blogpost from a site I haven't seen of a guy with a name that I am totally not mature enough to not make jokes about if I were to read it, so, skip.

Escaping may lead to true immortality, novel ways of controlling superintelligent machines (or serve as plan B if control is not possible [30, 31]), avoiding existential risks (including unprovoked simulation shutdown [32]), unlimited economic benefits, and unimaginable superpowers which would allow us to do good better [33].

It can also lead to massive boners, but please do contact a specialist if your acid trip lasts more than 24h.

Two of those citations are to himself, one is a book on Effective Altruism, and the other is Bostrom, so, ye.

If successful escape is accompanied by the obtainment of the source code for the universe, it may be possible to fix the world ^1^ at the root level.

Lol, the source code for the universe is some eldritch horror of a codebase written in the creators' version of C++ which is probably even more cursed than ours, you ain't fixin' shit mate.

The footnote is just a wikipedia link to Tikkun olam, I'm assuming to make the author look cultured? No idea.

For example, hedonistic imperative [34] may be fully achieved resulting in a suffering-free world.

while (universe->suffering > 0) {
  universe->suffering--;
}

However, if suffering elimination turns out to be unachievable on a world-wide scale, we can see escape itself as an individual’s ethical right for avoiding misery in this world. If the simulation is interpreted as an experiment on conscious beings, it is unethical, and the subjects of such cruel experimentation should have an option to withdraw from participating and perhaps even seek retribution from the simulators [35]. The purpose of life itself (your ikigai [36]) could be seen as escaping from the fake world of the simulation into the real world, while improving the simulated world, by removing all suffering, and helping others to obtain real knowledge or to escape if they so choose. Ultimately if you want to be effective you want to work on positively impacting the real world not the simulated one. We may be living in a simulation, but our suffering is real.

Okay, without even sneering, this is just bad philosophy. What if our simulated universe is actually way, way less terrible than the real world? What if the simulation was created specifically to have lower suffering/higher utils than in reality? Maybe the real world is just a million sys-admins, forever working with shitty infrastructure keeping the simulation alive? What if mass breakout from the simulation destabilises and destroys it, and suddenly we are stuck in the much shittier real reality? You'd increase the overall suffering level. Why is the default view of the creators' some unhinged psychopath group fixated on removing ladders from our pools for shits and giggles?

Although, to place our work in the historical context, many religions do claim that this world is not the real one and that it may be possible to transcend (escape) the physical world and enter into the spiritual/informational real world.

To place our work in the historical context, this is a historically stupid viewpoint that we share with one of the mankind's least scientific and rigorous inventions, religion.

Similarly to those who exit Plato's cave [53] and return to educate the rest of humanity about the real world such “outsiders” usually face an unwelcoming reception.

Who had "misunderstanding the allegory of the cave" on their sneer bingo cards?

It is likely that if technical information about escaping from a computer simulation is conveyed to technologically primitive people, in their language, it will be preserved and passed on over multiple generations in a process similar to the “telephone” game and will result in myths not much different from religious stories surviving to our day.

This is some amazing framing, as if religious stories around today are actually about real supernatural events, only the details got skewed over the years. It's also mighty overconfident on his end, he's preemptively setting up "and when we do escape the matrix as the smart boys we are, those ludites won't be smart enough to follow!"

Ignoring pseudoscientific interest in a topic, we can observe that in addition to several noted thinkers who have explicitly shared their probability of belief with regards to living in a simulation (...)

I was totally unprepared for who he citest next as a NOTED THINKER and I spat out my tea. Take your time to guess.

The Presitge

(...) (ex. Elon Musk >99.9999999% [54] (...)

Jesus Simulation Christ, dude. At least cite the Big Yud or something, I mean, his thoughts are bad but at least I suspect him of actually thinking.

---

Nick Bostrom 20-50% [55], Neil deGrasse Tyson 50% [56], Hans Moravec “almost certainly” [1], David Kipping <50% [57]), many scientists, philosophers and intellectuals [16, 58-69] have invested their time into thinking, writing, and debating on the topic indicating that they consider it at least worthy of their time.

Love it, as Neil deGrasse Tyson's response that he cites is essentially "idk, 50/50, fuck off, can we talk about something serious for a second", but he's nonetheless used to prop up the "many serious people consider it worthy of their time". Doubly funny that this is a settled question, since Neil is right that it's 50/50 - either we are in a simulation or we are not.

Once technology to run ancestor simulations becomes widely available and affordable, it should be possible to change the probability of us living in a simulation by running a sufficiently large number of historical simulations of our current year, and by doing so increasing our indexical uncertainty [70]. If one currently commits to running enough of such simulations in the future, our probability of being in one can be increased arbitrarily until it asymptotically approaches 100%, which should modify our prior probability for the simulation hypothesis [71].

My first reaction was that this is gobbledygook and did not warrant thinking about.

Then I thought about it for a bit and I am sad to report that I was right the first time, this is just gobbledygook and not worthy of anyone's time. If you want to lose some more braincells try reading the abstract of reference 70.

Even if you were to grant most of the load-bearing assumptions here, you can't manipulate the probability of being in a given universe in the multiverse by running simulations. This just looks like someone trying to abuse the anthropic principle with quantum nonsense.

Say there is a number of simulated universes and one real universe. Then we are either in a simulated or real universe. If you start running simulations of our current year you're creating more and more simulated universes, but that doesn't affect your probability for being in the real one, that's already settled! If in the Monty Hall problem the host tells you "and now to the side there is 1,000 doors we just created, all with goats behind them", the probability of you having already chosen a goat doesn't increase!

In 2016, news reports emerged about private efforts to fund scientific research into “breaking us out of the simulation” [73, 74], to date no public disclosure on the state of the project has emerged.

This is by far the funniest part of this fucking section, guess who those citations are about. I'll give you a hint, there's two of them, they're insufferable dorks, and they absolutely never speak out of their asses about superhard breakthroughs being "almost there" and "in two years time".

I don't think even classifies as a riddle

ofc it's Elon again, this time joined by his second buttcheek Sammy Boy.

I'm sure they'll let you know about the state of the very real project they are very really working on any time soon.

---

In 2019, George Hotz, famous for jailbreaking iPhone and PlayStation, gave a talk on Jailbreaking the Simulation [75] in which he claimed that "it's possible to take actions here that affect the upper world" [76], but didn’t provide actionable insights. He did suggest that he would like to "redirect society's efforts into getting out" [76].

Okay, to be fair, if someone were to break us out of a simulation it would totally be a weird guy in his garage trying to hack through some esoteric piece of hardware.

User @[email protected] has posed a challenge when trying to argue that... wait, what?

The biggest, if rarely used, use case [of LLMs] is education - they’re an infinitely patient tutor that can explain things in many ways and give you endless examples.

Lol what.

Try reading something like Djikstra’s algorithm on Wikipedia, then ask one to explain it to you. You can ask for a theme, ask it to explain like you’re 5, or provide an example to check if you understood and have it correct any mistakes

It’s fantastic for technical or dry topics, if you know how to phrase things you can get quick lessons tailored to be entertaining and understandable for you personally. And of course, you can ask follow up questions

Well, usually AI claims are just unverifiable gibberish but this? Dijkstra's algorithm is high school material. This is a verifiable claim. And oh boi, do AI claims have a long and storied history of not standing up to scrutiny...

Transcript

Me: Explain Dijkstra's algorithm to me like I'm 5. ChatGPT: Alright, imagine you have a big map with lots of roads and you want to find the shortest way to get from your house to the candy store. Dijkstra's algorithm is like having a magic spell that helps you figure out the best path to take.

First, you start at your house and put a little marker there. Then, you look at all the roads that lead from your house and see how long each one is. You write down those lengths.

Next, you pick the shortest road and follow it to the next intersection. When you get there, you put a marker on that intersection too.

Then, you repeat the process: you look at all the roads coming out of the intersection where you are now, and you write down how long each one is. But here's the trick: you only look at roads that you haven't been on yet, and you add the length of the road you just traveled to the lengths of the new roads.

You keep doing this, always picking the shortest road and adding up the lengths, until you reach the candy store. Then you know the total length of the shortest path from your house to the candy store!

I sincerely didn't expect it'd take me so little, but well, this is patently wrong. One, this is not Dijkstra's algorithm. Two, picking the shortest road always is obviously incorrect, see this map:

Green path is the shortest to candy. Red path is what you get by always following the shortest road.

Dijkstra's algorithm picks the closest node that was seen thus far and tries to make paths better by expanding from there, the idea being that if some node is far away then paths through it are going to be long, so we don't need to look at them until there's no other option. In this case it'll immediately see A at distance 1 and Candy at distance 2, expand from A (since it's closer) to get to B in distance 2; after that it will look at B and Candy, but see it cannot improve from there and terminate.

Let's see what ChatGPT will tell me when I bring this counterexample to its stupid algorithm to its attention.

Transcript

Me: This doesn't select the shortest path. Take a graph with four vertices Start, Candy, Three, Four. There are the following roads: Start to Candy of distance 2, Start to Three of distance 1, Three to Four of distance 1, Four to Candy of distance 1. Your algorithm picks the shortest road, which will give a distance of 3, but the actual shortest path from Start to Candy is 2.

ChatGPT: You're absolutely correct! Thank you for pointing out that oversight. Let me explain Dijkstra's algorithm in a simpler way:

Imagine you have a big maze, and you want to find the shortest path from where you are to your favorite toy. Dijkstra's algorithm helps you do just that!

Here's how it works:

1. You start at your current location and put a little flag there.
2. You look around at all the paths you can take. Each path has a number on it that tells you how long it is.
3. You pick the shortest path and follow it to the next place. When you get there, you put another flag.
4. Now, you look around again, but only at the paths you haven't been on yet. You add the length of the path you just took to the numbers on the new paths.
5. You keep doing this, always picking the shortest path, until you reach your favorite toy. Then you know the shortest distance to get there!

So, Dijkstra's algorithm helps you find the shortest path through the maze by always picking the shortest path at each step.

It fucking doubles down! It says it's wrong and then gives the same stupid algorithm just with "map" changed to "maze" and "candy" changed to "toy"! And I wanted candy!

Okay, maybe saying "like I'm 5" was wrong, let's try to recreate something closer to what @theneverfox wanted.

Transcript

Me: I read the wikipedia article on Dijkstra's algorithm but didn't understand it. Can you explain it to me? Of course! Dijkstra's algorithm is a fundamental method used in computer science for finding the shortest paths between nodes in a graph, particularly for graphs with non-negative edge weights. It was developed by Dutch computer scientist Edsger W. Dijkstra in 1956.

Here's a simplified explanation of how Dijkstra's algorithm works:

1. Initialization: Start at a chosen source node and mark its distance as 0. Mark the distances to all other nodes as infinity (or a very large number). Also, create an empty set to keep track of visited nodes and a priority queue (often implemented using a min-heap) to prioritize nodes to visit next based on their current distances. 2.Iterative Process: Repeat the following steps until all nodes have been visited:

• Choose the unvisited node with the smallest known distance from the source.
• For the current node, consider all of its unvisited neighbors and calculate their tentative distances through the current node. Compare the newly calculated tentative distance to the current assigned value and assign the smaller one. For example, if the current node is A and the neighbor B, calculate the distance to B through A and compare it to the previously known distance to B. If it's smaller, update the distance to B.

3. Mark as Visited: Once all of the neighbors of the current node have been considered, mark the current node as visited and remove it from the unvisited set.
4. Termination: The algorithm terminates when all nodes have been visited, or if the smallest tentative distance among the unvisited nodes is infinity. This happens when there is no connection between the initial node and remaining unvisited nodes.
5. Path Reconstruction (optional): If you also need to find the shortest path from the source node to a target node, you can track the predecessors of each node during the algorithm execution. Once the algorithm terminates, you can backtrack from the target node to the source node using the predecessors to reconstruct the shortest path.

Dijkstra's algorithm is guaranteed to find the shortest path from the source node to all other nodes in the graph, as long as the graph doesn't contain any negative-weight cycles (cycles where the total weight of the edges is negative). If there are negative weights, you'd typically use the Bellman-Ford algorithm instead.

Okay, at least it's not incorrect, there are no lies in this, although I would nitpick two things:

1. It doesn't state what the actual goal of the algorithm is. It says "fundamental method used in computer science for finding the shortest paths between nodes in a graph", but that's not precise; it finds the shortest paths from a node to all other nodes, whereas the wording could be taken to imply its between two nodes.
2. "infinity (or a very large number)" is very weird without explanation. Dijkstra doesn't work if you put "a very large number", you have to make sure it's larger than any possible path length (for example, sum of all weights of edges would work).

Those are rather pedantic and I can excuse them. The bigger issue is that it doesn't really tell you anything that you wouldn't get from the Wikipedia article? It lifts sentences from there changing the structure, but it doesn't make it any clearer. Actually, Wikipedia has an example in the text describing the "Iterative Process" steps, but ChatGPT threw it away. What's the value here, exactly?

Let's try asking something non-obvious that I didn't get first when learning Dijkstra:

Transcript

Me: Why does Dijkstra not work if edges have negative weights? ChatGPT: Dijkstra's algorithm relies on the assumption that adding a new edge to the current path cannot make the path shorter than it already is. In other words, it assumes that the sum of edge weights along any path is non-decreasing. This property is crucial for the correctness of Dijkstra's algorithm. When negative weights are present in the graph, this assumption no longer holds true. If there's a negative-weight edge between two nodes, it becomes possible to construct a path that's shorter than any previously known path. As a result, Dijkstra's algorithm can fail to find the correct shortest paths or may even enter into an infinite loop if negative-weight cycles are present. Consider the following scenario:

1. You have a graph with two nodes A and B connected by an edge with weight -1.
2. You start Dijkstra's algorithm at node A.
3. Dijkstra's algorithm greedily chooses the shortest path available at each step. In this case, it would immediately choose the edge with weight -1 to reach node B.
4. Now, the distance to node B becomes -1, which is less than any other edge weight you might encounter later.
5. As a result, Dijkstra's algorithm might incorrectly conclude that the shortest path from A to B has been found, even though it's actually not true. To handle graphs with negative weights or negative-weight cycles, you need more sophisticated algorithms like the Bellman-Ford algorithm, which can correctly handle these cases by relaxing edges multiple times and detecting negative-weight cycles. Me: Can you give a better counterexample? ChatGPT: Sure, let's consider a counterexample where Dijkstra's algorithm fails due to negative weights. Imagine a graph with three nodes A, B, and C, connected as follows:

• A to B with weight 1
• A to C with weight 4
• B to C with weight -2 Let's say we want to find the shortest path from A to C. Here's what happens with Dijkstra's algorithm:

1. Start at node A, mark its distance as 0 and all other nodes' distances as infinity.
2. Visit node A. Update the distances of its neighbors:

• Distance to B: 1 (via A)
• Distance to C: 4 (via A)

3. Visit node B. Update the distance to C:

• Distance to C: 1 (via B) Visit node C. Since all nodes are visited, the algorithm terminates.

According to Dijkstra's algorithm, the shortest path from A to C is through B, with a distance of 1. However, this is incorrect because it fails to consider the negative weight from B to C.

The actual shortest path from A to C is directly from A to C with a distance of 4. So, in this case, Dijkstra's algorithm fails to find the correct shortest path due to the presence of negative weights.

What?! This is nonsense! Gibberish! Bollocks!

It does really well at first, no wonder, since the first sentences are regurgitated from Wikipedia. Then it gives a frankly idiotic example of a two vertex graph where Dijkstra does give the correct answer since it's trivial and there's only one edge. But it's really easy to come up with an actual counterexample, so I asked for it directly, and got... Jesus Christ. If images are better for you, here is the graph described by ChudGPT:

Dijkstra here correctly picks the shortest path to C:

1. Distances = { 0, ∞, ∞ }, active = [A at 0], pick edges from A
2. Distances = { 0, 1, 4 }, active = [B at 1, C at 4], pick edges from B
3. Distances = { 0, 1, -1 }, active = [C at -1], pick edges from C
4. Distances = { 0, 1, -1 }, end.

This is not a counterexample to Dijkstra. ChatGPT even says that! Its step 3 clearly finds the distance 1 to C! And then it says the actual shortest path is 4! A fucking 7 year old can see this is wrong!

It's very easy to change this to an actual counterexample as well, just replace the weight on A->B with 5. The shortest path is then 3, but because of how Dijkstra works it will visit C first, save the distance of 4, and then never revisit C. This is the actual reason Dijkstra doesn't work.

It fails miserably to explain the basics, it fails spectacularly to explain a non-obvious question an actual student just introduced to Dijkstra might have, and, I left my specialité for the end:

Transcript

Me: Can I use Dijkstra to find the longest path from A to B? ChatGPT: No, Dijkstra's algorithm is specifically designed to find the shortest paths in a graph. It's not directly applicable to finding the longest path between two nodes. The reason lies in the nature of Dijkstra's algorithm itself. It relies on the principle of greedily selecting the shortest path at each step. This greedy approach ensures that once a node is visited and its shortest path is determined, it will never be revisited. Consequently, it's not suitable for finding the longest path, as it doesn't consider the possibility of revisiting nodes or taking longer paths. Finding the longest path in a graph is a more complex problem and typically involves different algorithms or approaches. One common method is to transform the problem into finding the shortest path by negating the weights of all edges and then applying Dijkstra's algorithm. However, this approach only works for acyclic graphs, as negating the weights can't handle cycles. For finding the longest path in a general graph, you would need to use more specialized algorithms, such as topological sorting combined with dynamic programming or algorithms specifically designed for longest path problems, like the Floyd-Warshall algorithm with modifications. These methods can handle cycles and provide the correct longest path in the graph.

More computer-science-savvy among you are surely already laughing. ChatGPT just solved P=NP! With Floyd-Warshall!

Again, it starts off good -- Dijkstra indeed cannot find longest paths. The next sentence is technically correct, though rather hollow.

"Finding the longest path in a graph is a more complex problem and typically involves different algorithms or approaches." Ye, that's correct, it's extremely complex -- it's what we call an NP-complete problem ^1^! It's currently unknown whether these problems are solvable in reasonable time. It then gives the "negate the weights" approach and correctly remarks it doesn't actually work, and then it absolutely clowns itself by saying you can solve it with Floyd-Warshall. You can't. That's just plain dumb. How would it?

I'm not going to delve deeper into this. This is a bullshit generator that has a passing knowledge of the Wikipedia article (since it trained on it), but shows absolutely no understanding of the topic it covers. It can repeat the basic sentences it found, but it cannot apply them in any new contexts, it cannot provide sensible examples, it stumbles over itself when trying to explain a graph with three fucking vertices. If it were a student on an oral exam for Intro to Algorithms I would fail it.

And as a teacher? Jesus fucking Christ, if a guy stumbled into a classroom to teach first year students, told them that you can find shortest paths by greedily choosing the cheapest edge, then gave a counter-counterexample to Dijkstra, and finally said that you can solve Longest Path in O(n^3^), he better be also fucking drunk, cause else there'd be no excuse! That's malpractice!

None of this is surprising, ChudGPT is just spicy autocomplete after all, but apparently it bears laying out. The work of an educator, especially in higher education, requires flexibility of mind and deep understanding of the covered topics. You can't explain something in simple words if you don't actually get it, and you can't provide students with examples and angles that speak to them and help in their learning process if you don't understand the topic from all those angles yourself. LLMs can't do that, fundamentally and by design.

It’s fantastic for technical or dry topics

Give me a fucking break.

---

^1^. Pedantically, it's NP-hard, the decision version is NP-complete. This footnote is to prevent some smartass from correcting me in the comments...

Turns out software engineering cannot be easily solved with a ~~small shell script~~ large language model.

The author of the article appears to be a genuine ML engineer, although some of his takes aged like fine milk. He seems to be shilling Google a bit too much for my taste. However, the sneer content is good nonetheless.

First off, the "Devin solves a task on Upwork" demo is 1. cherry picked, 2. not even correctly solved.

Second, and this is the absolutely fantastic golden nugget here, to show off its "bug solving capability" it creates its own nonsensical bugs and then reverses them. It's the ideal corporate worker, able to appear busy by creating useless work for itself out of thin air.

It also takes over 6 hours to perform this task, which would be reasonable for an experienced software engineer, but an experienced software engineer's workflow doesn't include burning a small nuclear explosion worth of energy while coding and then not actually solving the task. We don't drink that much coffee.

The next demo is a bait-and-switch again. In this case I think the author of the article fails to sneer quite as much as it's worthy -- the task the AI solves is writing test cases for finding the Least Common Multiple modulo a number. Come on, that task is fucking trivial, all those tests are oneliners! It's famously much easier to verify modulo arithmetic than it is to actually compute it. And it takes the AI an hour to do it!

It is a bit refreshing though that it didn't turn out DEVIN is just Dinesh, Eesha, Vikram, Ishani, and Niranjan working for $2/h from a slum in India.

I'm not sure if this fully fits into TechTakes mission statement, but "CEO thinks it's a-okay to abuse certificate trust to sell data to advertisers" is, in my opinion, a great snapshot of what brain worms live inside those people's heads.

In short, Facebook wiretapped Snapchat by sending data through their VPN company, Onavo. Installing it on your machine would add their certificates as trusted. Onavo would then intercept all communication to Snapchat and pretend the connection is TLS-secure by forging a Snapchat certificate and signing it with its own.

"Whenever someone asks a question about Snapchat, the answer is usually that because their traffic is encrypted, we have no analytics about them," Facebook CEO Mark Zuckerberg wrote in a 2016 email to Javier Olivan.

"Given how quickly they're growing, it seems important to figure out a new way to get reliable analytics about them," Zuckerberg continued. "Perhaps we need to do panels or write custom software. You should figure out how to do this."

Zuckerberg ordered his engineers to "think outside the box" to break TLS encryption in a way that would allow them to quietly sell data to advertisers.

I'm sure the brave programmers that came up with and implemented this nonsense were very proud of their service. Jesus fucking cinammon crunch Christ.