This New Idea Could Explain Complexity

[@antman7673]

I don’t undestand the details, but a clear understanding emerges.

[@hyperduality2838]

LUMPABILITY = integration or summation of states, dimensions -- a syntropic process! Complexity is dual to simplicity. Micro is dual to macro. Increasing the number of dimensions or states is an entropic process -- differentiation or reductionism. Decreasing the number of states or dimensions is a syntropic process -- integration or holism, LUMPABILITY. Increasing (divergence, entropy) is dual decreasing (syntropy, convergence). Syntropy (prediction) is dual to increasing entropy -- the 4th law of thermodynamics! Teleological physics (syntropy) is dual to non teleological physics (entropy) -- physics is dual. Integration is dual to differentiation. Reductionism is dual to holism. Homology (syntropy) is dual to co-homology (entropy). "Always two there are" -- Yoda.

[@Liam-ke2hv]

​@@hyperduality2838 if two depend entirely on one another and cannot have an existence in isolation without the counterpart, could they not be described as two parts of one? There is no male without female or female without male. How do two things give rise to each other when they both are dependent on the other which they give rise to in order to exist in the first place

[@__-op4qm]

@@hyperduality2838I am surprised nobody mentions about statistical mechanics. Lumpability seems to be just dimensionality reduction for space and ensemble averaging for time. Some degrees of freedom/dimensions matter a lot less at larger length scales (thus can be marginalised out), and microscopic observables can be average in time (assuming that the ensemble is not perturbed too frequently).

[@hyperduality2838]

@@__-op4qm Lumpability is just a clumsy way of saying syntropy (convergence). Your mind associates or integrates information -- integrated information theory. Syntactic information is dual to semantic information -- information is dual. Syntax (objective, absolute) is dual to semantics (subjective, relative) -- languages or communication. If mathematics is a language then it is dual. Syntropy (prediction) is dual to increasing entropy -- the 4th law of thermodynamics! Teleological physics (syntropy) is dual to non teleological physics (entropy) -- physics is dual. Categories (form, syntax) are dual to sets (substance, semantics) -- Category theory. "Only the Sith think in terms of absolutes!" -- Obi Wan Kenobi. "Always two there are" -- Yoda. All messages in a communication system are predicted into existence according to Shannon's information theorem -- a syntropic process, teleological. Making predictions to track targets, goals and objectives is a syntropic process, teleological. In homology you start with hypervolumes and reduce the number of dimensions:- Hypervolumes become volumes become planes or surfaces become lines become points or zero dimensions and this is clearly a dimension reduction process -- syntropic. Points are dual to lines -- the principle of duality in geometry. In co-homology you do the opposite or opposame:- Points becomes lines become planes become volumes become hypervolumes -- increasing dimensions or states is an entropic process. Convergence (syntropy, homology) is dual to divergence (entropy, co-homology or dual homology). Sine is dual to cosine or dual sine -- the word co means mutual and implies duality. Vectors (contravariant) are dual to co-vectors (covariant) -- dual bases. Riemann geometry or curvature is dual -- upper indices are dual to lower indices (tensors). Gravitation is equivalent or dual (isomorphic) to acceleration -- Einstein's happiest thought, the principle of equivalence (duality). Space is dual to time -- Einstein.

[@hyperduality2838]

@@__-op4qm "The brain is a prediction machine" -- Karl Friston, neuroscientist. Your brain integrates information to make predictions -- a syntropic process, teleological. Certainty (predictability, syntropy) is dual to uncertainty (unpredictability, entropy) -- the Heisenberg certainty/uncertainty principle. Hence there is a 4th law of thermodynamics. Synergy is dual to energy -- energy is dual. Synchronic points/lines are dual to enchronic points/lines.

[@carlbrenninkmeijer8925]

what a great explanation of such a fascinating subject. Our cat is called Kant, now he gets a new name, we call him Emergence. He is lumped with dogs

[@Dr.M.VincentCurley]

Are you relating to his behavioral aspect?

[@christianheichel]

​@@Dr.M.VincentCurley you Kant do that.

[@michaelmoser4537]

I was told that a good cat name should have a hissing sound (like psps) because that is grabbing their attention, or something like that. "Emergence" would better, if this is true. (But maybe your cat is different and likes these names, who knows?)

[@alieninmybeverage]

If your intuition is to name your cat Kant, then it's too late!! You've already done it!!

[@DonDee123]

@carl: hope you‘re not living in an english spoken region. If you call your cat like that, the neighbours could be irritated 😄 EDIT: I can’t get rid of that picture in my head now and keep giggling 😄

[@Dr.M.VincentCurley]

I gave this some thought when I was sequencing DNA in 1994 using the God awful method "dideoxy chain termination sequencing" method. Very painful, but the point is. Identical twins are the same (ignoring the complexity) and yet you find a large number of emergent properties between them that are unexplainably different. While there are aspects we can certainly lump together, there are strange permutations that are unexpected.

[@SabineHossenfelder]

That's very interesting, hadn't thought about this. Thanks for sharing!

[@alieninmybeverage]

We are all the same (ignoring the complexity)!

[@dtrcs9518]

I was still using sanger sequencing in 2017 :(

[@DonDee123]

@dr: nature vs nurture is a long standing topic. Monozygotic twins are the ideal study objects for such research.

[@Dr.M.VincentCurley]

@@dtrcs9518 Was your face as sunburned as mine?

[@hallstewart]

This reminds of software architecture. The underlying purpose of code encapsulation is causal closure to reduce complexity. Similarly the lumpability of data reduces the test complexity to manageable levels

[@nijolas.wilson]

My thoughts exactly, it sounds like it's describing layers of an architecture that are cleanly separated by an abstraction. Emergence, then, is a "decoupling" of two distinct "scales"?

[@tylersmith7534]

This is what engineers do as well I think. An example I can think of is using transistors to create logic gates to create structures like adders/multipliers (for an alu) and control units to build a CPU, or transistors going to things like the different stages of an op-amp to piece together the op-amp itself so it can be used to build things like voltage comparators or a difference amplifier or whatever other configuration you want. And these things can be used to create larger circuits.

[@RD-jc2eu]

Yes... layers of abstraction work effectively in the human realm because the natural world already does something similar.

[@mikemondano3624]

Not the same kind of "complexity", Complexity is an essential aspect of the objects so described. Removing any complexity removes the nature of the object or the entire object itself.

[@Flako-dd]

Cat Memes just emerge from the OSI model.

[@NotJustBikes]

3:46 I get the idea, but I hate this example, because I have yet to see a traffic flow prediction that was actually correct. They always predict far more traffic than in reality. In my experience, there are two reasons for this: First, traffic engineers almost exclusively plan for moving as many cars as possible, rather than as many people as possible, so they overplan for cars to the detriment to every other form of transportation. Second, traffic engineers are paid to build roads. They are not paid to _not_ build roads. So every projection always results in (surprise!) proof that they need to build more roads.

[@NotJustBikes]

Incidentally this highlights an interesting difference between "traffic engineers" and "transportation engineers" and I talked about that with Build the Lanes on an episode of the Urbanist Agenda podcast.

[@foolmoron]

Such a great (albeit non sequitur) comment to see on a Sabine vid!

[@ASpaceOstrich]

One of my biggest pet peeves when driving is that roads are built exclusively for people who already know where they are going. Which makes driving in the city a miserable experience. Need to park somewhere? better hope you're lucky enough to be on the right side of the road and can spot the almost indistinguishable parking turning before you pass it. If not, add another 15 to 45 minutes to your trip so you can try again.

[@CM-dk9xu]

Not just bikes!!!!

[@HenriFaust]

If they always predict more traffic than there really is, why is traffic always congested? Shouldn't it be the other way around?

[@delicious_seabass]

"Usually these people are computer scientists." Shots fired.

[@corbono]

As a software engineer, I laughed out loud

[@anthonylosego]

@@corbono As a software engineer, I laugh at your laughing out loud.

[@virno69420]

​@@anthonylosego As someone who took an introductory webdev course, I lol'd at your lol'ing bc their lol.

[@jpt3640]

​@@anthonylosego as a software engineer i ask: could you explain? Didn't get the joke (well her's, not yours)

[@DinsDale-tx4br]

Most software engineers know diddly squat about anything except their own interminable code that defies comprehension to normal Man. I can't speak for how Women see things.

[@Windows__2000]

Highly lumpable is such a good insult

[@oldcowbb]

to your mom?

[@themore-you-know]

There are much worst than a mere insult: "Mrs, your test results show your breast is highly lumpable"

[@Caellyan]

It's not, it applies only to a group of things.

[@Windows__2000]

@@Caellyan Yeah, it says that they are easily added to a big group: don't think for themselves or such.

[@evandrolima1724]

@@Windows__2000 Lumpenproletariat?

[@alieninmybeverage]

Lumpability? I would have gone with "Glomular."

[@Vondoodle]

I would have gone with ‘morsular’

[@TheIgnoramus]

Corpuscular

[@brb__bathroom]

tubular idea

[@nobodyisperfect1564]

Lumpability. Useful for making complicated things simpler. Secret superpower for mathematicians, you could say! (My AI say's)

[@aniksamiurrahman6365]

That'll mix with the term 'Glomarular'. Glomarular Filtrate is basically urine. So, then it'll become 'piss parameter'.

[@ANunes06]

4:00 - having conducted a few traffic studies in the US... "You still get the correct prediction" is giving us a LOT of credit we probably don't deserve. But then, the fact that your individual odds of getting stuck at any traffic light (not involving a train, anyway) for more than 120 seconds are basically zero means that statistics kinda work. Which is reassuring. And yes, rather than use actual stats terminology, traffic engineers and city planners call "the value that tells you how meaningful your grouping selections have been" "Lumpability". The reason for this is that they often have to explain the results of their research to town councils and city board selectpersons who barely understand the concept of "road".

[@julioivansalazar9853]

A research group led by Dr. Hector Zenil offers a deeper view on the concept of 'emergence' (in science and philosophy), pushing beyond traditional information theory approaches like Shannon entropy. Their work (eg., the field of Algorithmic Information Dynamics, see, for instance: “Emergence and algorithmic information dynamics of systems and observers”, published by the Royal Society) tackles the limitations of using stochastic processes to explain causality, emphasizing the need for a more computational and algorithmic approach. This insights into causal emergence provides a fresh perspective that moves past simple correlations.

[@lepidoptera9337]

Yes, that is total bullshit. Nature does not compute anything, on any level.

[@cuthbertallgood7781]

Wolfram's A New Kind of Science uses some of these ideas as a fundamental property, particularly that complexity arises out of simple rules, as with Cellular Automata. What's fascinating is that from simple rules, you can derive BOTH the math of Relativity and Quantum Mechanics, and why they are the way they are is completely explained and understandable. Again, from very simple rules. Simple rules can even produce what seems to be "randomness" -- unpredictability is what's called computational irreducibility. It's impossible to predict the output in the future without running the rules in sequence. It's still early, and we don't have experiments to make predictions and provide evidence that it's "what's really going on" yet, but it's fascinating stuff.

[@energyscholar]

Yes, well said & accurate! That Simple-rule generated "randomness" was used as the cryptographic basis for a generation of NATO radio communication, starting in the late 1980s. Darpa has been ALL OVER this research.

[@danheidel]

Wolfram is definitely not the first person to look at the problem in depth. I was reading entire books dedicated to the subject in the 90s and Ilya Prigogine did a lot of the original ground work in the area back in the 1960s. I applaud Wolfram's efforts in the area but I don't feel that his research has created much in the way of actual insights beyond simple categorization. If this new paper holds up, it will be one of the first major advances in the subject I've seen in a long time.

[@nunomaroco583]

Hi, if I understand Wolfram also use Cellular Automata ....to try explain the Universe using simple rules....

[@netscrooge]

​@@danheidel True, "complexity science" was not invented by Wolfram, but he has made important contributions.

[@energyscholar]

@@danheidel FYI, wolfram's CA work was in the 1980s. He knew about Prigogine's work, of course, and built on it. FYI, Wolfram's work had HUGE effects but he is forbidden to mention it for National Security reasons. He's party to NDA from Darpa. The juicy good stuff we aren't allowed to know about. I know, though ...

[@bartroberts1514]

Nice shot at Wolfram.. Oh. Just all computer scientists in general? Well, we are kinda lumpable. Lumpen? Lumpy?

[@leecarraher]

wolfram is a physicist by training, but oddly the paper doesnt mention his work once, which is weird.

[@michaelsmith4904]

@@leecarraher yeah my first thought on seeing this video was to start looking for his name or the name of one of his student co-authors...

[@trapkat8213]

@@leecarraher Well, Wolfram was not very good at mentioning anybody else in his book A New Kind Of Science

[@emilgustavsson7310]

Yes, lumpy would be the closest to reality.

[@bartroberts1514]

@@emilgustavsson7310 Also my nickname from when I used to work out with weights.

[@41alone]

Thank you for this

[@SabineHossenfelder]

Thanks from the entire team!

[@williamkaufman274]

Speaking as a research mathematician (PhD 1979), this is the clearest, and most correct and complete explanation of emergence not requiring advanced mathematics I have ever encountered. (Of course, we expect that from Sabina.) I was also a computer science professor, and I find it interesting that systems analysts working on very large computer programs have to "offload" some of the "bug detection" onto the end users, because they are emergent.

[@toddq6443]

I have studied the Physical and Natural Sciences for over 60 years & can't remember ever having enjoyed presentations more. Your brief offerings are more like being immersed in a thought provoking song than a dry didactic lecture. Nicely done as always Bee.

[@oldsarge1441]

"Highly lumpable man" made my day, I feel, channel is gold. Big thanks to you!

[@michaelblacktree]

Thankfully, my girlfriend thinks I'm pretty lumpable. 😎

[@DOGB14]

⁠@@michaelblacktreemore like h… nvm.

[@michadybczak4862]

"Emergence of activists groups" also killed me :D. This time, Sabine outperformed herself :D.

[@hyperduality2838]

LUMPABILITY = integration or summation of states, dimensions -- a syntropic process! Complexity is dual to simplicity. Micro is dual to macro. Increasing the number of dimensions or states is an entropic process -- differentiation or reductionism. Decreasing the number of states or dimensions is a syntropic process -- integration or holism, LUMPABILITY. Increasing (divergence, entropy) is dual decreasing (syntropy, convergence). Syntropy (prediction) is dual to increasing entropy -- the 4th law of thermodynamics! Teleological physics (syntropy) is dual to non teleological physics (entropy) -- physics is dual. Integration is dual to differentiation. Reductionism is dual to holism. Homology (syntropy) is dual to co-homology (entropy). "Always two there are" -- Yoda.

[@scottperry9581]

In addition to Wolfram's work, the Santa Fe Institute has done great work in Complexity and Emergence. My favorite novel about Emergence is "Lila" by William Pirsig, the same guy/genius who wrote "Zen and the Art of Motorcycle Maintenance".

[@maheshkanojiya4858]

Interesting! thanks a lot

[@michaelstreeter3125]

I'm still undecided on whether to buy "A New Kind of Science" - it's over a decade old now. Maybe I should just buy a more recent book by SW.

[@evelynsinclair4937]

In Lila, though, we were told that a Creator God was necessitated by the second law of thermodynamics. His utter misunderstanding of science disgusted me mightily.

[@scottperry9581]

@@michaelstreeter3125 It is worth it if you can find a deal on a second hand copy. It exhaustively and methodically goes through every rule (within the constraints of his rule set). I found it interesting to see the visualizations of each rule in a way that is super easy to grok. It also offers a peak into chaos theory because it is so methodical.

[@scottperry9581]

@@evelynsinclair4937 Huh, I must have read the other "Lila" by Pirsig. I have no idea how you came up with your conclusion. "Lila" is more focused on metaphysics than science, and outlines a concrete instantiation of emergence . A number of people I know hated the book. I think it is brilliant.

[@bodotrenaud7441]

So much to learn, so little time. Thank you for lumping together such high density information.

[@hyperduality2838]

LUMPABILITY = integration or summation of states, dimensions -- a syntropic process! Complexity is dual to simplicity. Micro is dual to macro. Increasing the number of dimensions or states is an entropic process -- differentiation or reductionism. Decreasing the number of states or dimensions is a syntropic process -- integration or holism, LUMPABILITY. Increasing (divergence, entropy) is dual decreasing (syntropy, convergence). Syntropy (prediction) is dual to increasing entropy -- the 4th law of thermodynamics! Teleological physics (syntropy) is dual to non teleological physics (entropy) -- physics is dual. Integration is dual to differentiation. Reductionism is dual to holism. Homology (syntropy) is dual to co-homology (entropy). "Always two there are" -- Yoda.

[@f.schmid468]

Instant subscription. Who ever has the ability to speak so eloquently and easy to understand at the very same time and giving out deeper Understanding of the Universe is a Master in Teaching. very inspiring

[@hyperduality2838]

LUMPABILITY = integration or summation of states, dimensions -- a syntropic process! Complexity is dual to simplicity. Micro is dual to macro. Increasing the number of dimensions or states is an entropic process -- differentiation or reductionism. Decreasing the number of states or dimensions is a syntropic process -- integration or holism, LUMPABILITY. Increasing (divergence, entropy) is dual decreasing (syntropy, convergence). Syntropy (prediction) is dual to increasing entropy -- the 4th law of thermodynamics! Teleological physics (syntropy) is dual to non teleological physics (entropy) -- physics is dual. Integration is dual to differentiation. Reductionism is dual to holism. Homology (syntropy) is dual to co-homology (entropy). "Always two there are" -- Yoda.

[@brent9616]

Hi Sabine, this is my research area. Emergentism is pretty well disavowed outside of biology. It likely has more to do with how we draw the parameters of a larger-scale system, such as what are screened off. I think you explained this all very well. Thank you for the video. I would love to see more. If I could recommend some topics: causal closure, scientific reduction (especially radical reduction), and the ontology of levels.

[@paulbloemen7256]

Super interesting, thank you for showing this topic. I once, long ago, made computer programs for business applications. The most valuable lesson I learned there is, that the program should have the same structure as the problem you are tackling. This way, the program would be more robust, less prone to mysterious errors, which proved to be true. This gave quite some “freedom”, not sure how to put it, and maintaining the program was rather easy as long as you kept a keen eye on the also changing structure of the problem. Somehow your video rings a bell, I’ll have a look at it a few times.

[@bnarit]

freedom = maintainability? low technical debt?

[@vkjs2]

This makes perfect sense as what you are stating in basis is that the “problem” is understood. At this point there is no longer a problem as such, but rather a known characteristic that may be worked with and offset for. This is what your program is doing - providing a naturally fitting response 🕹️

[@stevemartin4249]

Thank you Sabine. This is one of the more interesting and timely podcasts to my particular situation - helping build alternative / supplemental schools for young children in Japan. In the broadest sense, education as a process of social maturation is an emergent process, though typical institutionalization of that process tends to restrict human potential. My research area as a college instructor was in tapping into the students' intrinsic motivation as a social primate by replacing end of semesters tests and papers with what I termed an "Event-Driven Curriculum" ... student presentations in front of a real audience as a fractal of what we professors do in academic conferences. By chance (synchronicity?), only a few days ago, I came across a link in substack's "Naked Emperor" to an on-line article in Quanta Magazine named "The New Math of How Large-Scale Order Emerges" ... a great supplement to this video. Thank you again Sabine!

[@ullrichfischer5796]

Who doesn't want a t-shirt with "Highly Lumpable" emblazoned on it? 😆

[@themore-you-know]

With an Ompa-Lumpas: "Ompa-lumpa-dee-di-do. Lumpability is what we do. "

[@ndi4926]

with the L crossed and an H scribbled in?

[@Kestrel1971]

This is rooted in Wolfram's cellular automata work. For anyone interested, he published the book, "A New Kind of Science" with a follow-up in 2023, 20 years after the first book was published. It's an excellent book; my degree is in computer science and I've been fascinated by cellular automata since I first discovered them in the early 80's so stumbling across Wolfram's book made my day.

[@WaterspoutsOfTheDeep]

Does he explain how cellular mechanisms can form when there is no evolutionary pressure to create building blocks of said mechanism that does not yet exist because evolution has no foresight?

[@noop9770]

Lumpability sounds a lot like computational reducibility.

[@hyperduality2838]

LUMPABILITY = integration or summation of states, dimensions -- a syntropic process! Complexity is dual to simplicity. Micro is dual to macro. Increasing the number of dimensions or states is an entropic process -- differentiation or reductionism. Decreasing the number of states or dimensions is a syntropic process -- integration or holism, LUMPABILITY. Increasing (divergence, entropy) is dual decreasing (syntropy, convergence). Syntropy (prediction) is dual to increasing entropy -- the 4th law of thermodynamics! Teleological physics (syntropy) is dual to non teleological physics (entropy) -- physics is dual. Integration is dual to differentiation. Reductionism is dual to holism. Homology (syntropy) is dual to co-homology (entropy). "Always two there are" -- Yoda.

[@remitemmos9165]

So happy to see that! I’ve been fascinated by threshold effect as general principle forever but never found literature on it… so it’s emergence! Good to know

[@toreon1978]

And emergent properties

[@generichuman_]

It's crazy that this paper doesn't mention Stephen Wolfram anywhere...

[@glashoppah]

You beat me to it.

[@juang.garcia7390]

They even use Mathematica for the graphics. They are certainly familiar with Stephen Wolfram :/

[@somjrgebn]

Ya, but Wolfram rarely mentions the concepts he's drawing from either. Maybe it's a tit-for-tat happening now?

[@alextilson9741]

Based on some of the comments I have read, and speaking as a computer scientist (well, PhD student, take it as you will): 1) please don't conflate software engineering with computer science, these are two totally different things entirely - even if, and especially if, you are yourself a software engineer 2) Computer science is essentially the study of computation, which I believe can be very accurately described as the study of the macroscopic emergent properties of mathematics 3) Hence if anything, I would argue this paper actually serves as evidence that computation (if we assume it functions as the study of emergence) is a fundamental property of the universe 4) I don't think Sabine was being at all sarcastic when she described some computer scientists as seeing their field as more fundamental than particle physics - I personally interpreted this response to be that she found this notion to simply be an interesting concept. (Perhaps her further input would clarify this?)

[@geekinasuit8333]

I'm happy someone besides myself posted a comment about this, indeed, software engineering is not computer science. It's unfortunate the word "computer" is part of the description because it creates the false impression that electronic computers - as we know them, including the programming tools that help make them perform useful tasks - is what the science specifically studies.

[@hyperduality2838]

LUMPABILITY = integration or summation of states, dimensions -- a syntropic process! Complexity is dual to simplicity. Micro is dual to macro. Increasing the number of dimensions or states is an entropic process -- differentiation or reductionism. Decreasing the number of states or dimensions is a syntropic process -- integration or holism, LUMPABILITY. Increasing (divergence, entropy) is dual decreasing (syntropy, convergence). Syntropy (prediction) is dual to increasing entropy -- the 4th law of thermodynamics! Teleological physics (syntropy) is dual to non teleological physics (entropy) -- physics is dual. Integration is dual to differentiation. Reductionism is dual to holism. Homology (syntropy) is dual to co-homology (entropy). "Always two there are" -- Yoda.

[@alextilson9741]

@@hyperduality2838 haha I love this

[@taylorhornby7475]

I would define computer science a little differently: it's the study of the behavior of Turing machines (or any other equivalent model). It just so happens, as long as the Church-Turing thesis is true, that the space of all computations (i.e. all Turing machines) is so rich that it includes everything imaginable, from simple mathematical models to our brains to the whole universe that we live in. It even encompasses all of mathematics in some sense, since formal proof systems can be seen as nondeterministic computations that generate the set of all of that system's theorems. Whether or not that means it's more fundamental, I don't know, it really depends on your definition of "fundamental," but we can certainly make an argument that all of the theorems of physics and chemistry could rightly be considered theorems of computer science at the same time.

[@geekinasuit8333]

@@hyperduality2838 What if there's partial duality or triality, etc?

[@PrometheanConsulting]

Having been involved with computer for over 40 years, I have often used the example that a programmer doesn't need to know what individual bits are doing at any given time to know that the program is running correctly. In fact, for most all of us, that level of detail would not be useful or even resemble the initial code we used because it's been compiled. But they can insert break points or use other debugging tools to look at specific use cases during runtime to verify.

[@David-l6c3w]

Separation of Scales ... Sabine is such an illuminating teacher ... this idea was seldom discussed or even mentioned in my classes ...

[@Thomas-gk42]

She explains that term very detailed and accurate in her book "Lost in Math" from 2018.

[@Thomas-gk42]

An every day´s pleasure, to follow Sabine´s thoughts. Astonishing how much content she compresses in five minutes. This one I have to watch more than one time. 😊 (This is a bit like "Mehr als nur Atome")

[@mathiasbttger980]

I dont understand why emergence is made up to be so mysterious and unknown. I dont imagine that things on a large scale dont just follow the rules of what is happening on the small scale inside. Am i wrong in thinking that new and advanced behaviour on a large scale isnt in fact new, but just complex application of the basic rules on the smallest scale? Complex behaviour is just so complex that we create simpler abstractions. These simple abstractions are usefull, we can just look at the large scale thing and not have worry about every single particle that it is made up of. Why do we make these abstractions so mystical when they arent laws of nature, just approximations of complex structures that do follow the laws of nature? I feel like there is something im missing here...

[@jmbreche]

It has nothing to do with being mysterious and everything to do with emergence being codified and predictable. The goal is to use emergence as a mathematical/physical tool and not just as an intuition.

[@romh7261]

@@jmbreche I think I agree. But people quite often use the term 'emergent' much like they use the term 'god'. No further explanation required. Are the different levels of scale connected? Of course yes.

[@jan.kowalski]

because you "loose" some information during separation of scales. Imagine that in the context of quantum size objects there is determinism, than at the size of "our" scale it is perceived as random or chaotic. In our scale we have laws of mechanics, thermodynamics but it is possible, that on the bigger scale, our own world could be perceived as quantum. Some of the information is lost between scales and it has physical effects (for example thermodynamic). It is possible that in other scales information has a mass or information is equivalent of matter or that there is a process a information-energy conversion. That's why emergence is a good name for this "information phase shift".

[@Bidon555]

I agree that consciously or not, scientists seem to smear out the whole topic. It is not difficult to present it clearly. There are two basic possibilities: 1/ In reality, there's only a single fundamental layer. The universe doesn't 'know' or 'care' whether the fundamental 'pixels' are lumped into cells or planets. Exactly like cellular automata don't care about the macro shapes of the pixel lumps - they simply transform from frame to frame, pixel by pixel. In this case, scales are only hierarchical levels of abstraction in _human thinking_. They are not something 'real' out there. 2/ A given scale is truly _irreducible_ to the smallest scale (or any other scale, or combination thereof). There are different laws that modulate the whole at different scales (this direction is investigated for example by Michael Levin). This would mean that, for example, in Conway's game of life, there would be certain gliders that can _never_ be simulated using only the pixel rules. In the same sense, this would mean that the purely physical laws of attraction and repulsion of particles would never be able to produce the behavior of a biological cell. This has the interesting consequence that our cognitive flow may also be irreducible to other scales. This doesn't mean that our thinking process is independent of other scales but only that there are certain aspects of our intuitive steering through the cognitive landscape that cannot be explained as merely the output of other levels.

[@WaterspoutsOfTheDeep]

Rationality does not come from irrationality, the burden of proof is on those who say it does. Emergence is a deus ex to do away with the need for God. A blind faith in magic aka that probability can produce rational outcomes.

[@ImBalance]

The way that I’ve seen emergence framed as “separation of scales” seems problematic to me. Ultimately, more simplifying models can be used effectively at larger scales because with increasing scale, less resolution tends to be necessary for usably high accuracy of analysis. But that doesn’t mean the scale “below” disappears, only that our resolution of imaging lacks perfect precision but remains workable.

[@DeLambada]

But in some cases a low resolution of imaging remains workable in others not. I guess what they are trying to do is use this fact for a definition of emergence. Of course now you need to define what 'workable' means.

[@netscrooge]

No one is saying the scale below disappears. But in some cases, it becomes irrelevant. All this will make more sense if you study complexity science.

[@nateneligh3155]

You can think of the emergence between scales as the result of two statistical effects. Combinatorial effects create new behaviors at large scales while the law of large numbers flattens out the details of the level below. Both of these effects are only on average if they exist in a given setting

[@ImBalance]

@@DeLambada As in, some system phenomena can be considered more “emergent” than others based on how effectively those systems can be described without any reference to lower, underlying scales of objects? So, “emergence” is more of an adjective than a noun? Which ultimately depends a lot on the system and the complexity of the constructs used for modeling. But, like, all of this boils down to the choices we use in describing systems and what level of precision / accuracy we want, which feels subjective in a way that it feels like we’re missing something on how these ideas properly connect to objective knowledge and science.

[@luisostasuc8135]

Well, to be fair, in most applications you don't need to take electron spin or ionization to make a program work, or as Sabine pointed out, in order to model orbital mechanics for time scales longer than human civilization. Even a thing like tic tac toe works with only marks on some surface. It's whole and complete without taking any scale into account, just certain rules and bounds with very precise limits. Despite this it's still the product of the extremely complex quantum to meter scale object that is a human with a mind.

[@planetofthepete]

What a wonderful video - many thanks Sabine. So pleased to hear a scientist talk about ideas like Emergence and Lumpability - these are concepts that Engineers have had to manage for decades (although we might refer to it as propensity for coupling) . Both Engineers and Scientists rely heavily on the scientific method, but the way they approach complexity is a key defining difference: Scientists are inherently reductionist - as they seek to remove complexity in the pursuit of causality. Engineers seek value and approach complexity from the vie of behaviours to manage at each strata of organisation. Both need to understand Emergence as a superimposed phenomena in its own right.

[@stomerzi]

This is so enlightening! Will this 'complexity model' would work equally well if there are no "building blocks"? In other words, would the model be the same if the elementary particles themselves are made of smaller (and smaller) particles? (BTW, Thank you Sabine for your videos. I wrote you an Email, from Tomer Zimmerman, I hope it was delivered)

[@Entrophius]

Did mathematicians really create a formal description to "decide on cohort before running experiments"?

[@TheIgnoramus]

Ya our ontology is starting to run together as the fields over specialize and don’t talk to each other.

[@DonDee123]

Did mathematicians ever make experiments? 😉

[@DinsDale-tx4br]

Ask The Romans.

[@MsSonali1980]

@@DonDee123 I would say proving something is an experiment but it can only have definite outcomes yes or no. There is no significance testing required. Other experimental methods EMERGE from mathematical concepts, tho, lol. So, I guess it's good, that you don't need a significance associated to if the sqrt(2) is irrational are not.

[@DonDee123]

@@MsSonali1980 Math has its axions, which can’t be proven. And everything else is derived from them. Math is the language of science, needed to analyse and interpret data from experiments. But math itself makes no experiment.

[@thisisbriannaandrea]

I have had a hypothesis that gravity is emergent. Rather than a fundamental force with an associated particle, it's a perceived force much like a centrifugal force. However, being a lowly youtube, layman commenter, I don't have the resources to test such a hypothesis. Also, I could be way off in my understanding of particle physics as well...🤷‍♀

[@rayparent1]

Lmao

[@thisisbriannaandrea]

@@rayparent1 I would appreciate being corrected, as I said, I am a layman. More productive than just laughing.

[@Thomas-gk42]

@@thisisbriannaandrea Nothing to laugh about, some others had similar thoughts too. But of course there´s a lot of research on quantum gravity.

[@rayparent1]

@@thisisbriannaandrea most people that talk like you in my experience think they know better. I laugh because you talk about testing without being intimately aware of the mathematical structure of our theories. Which sparks my crackpot detector. Maybe ive spent to much time talking to flat earthers and you were genuine. If so this is an open area of research

[@thisisbriannaandrea]

@rayparent1 I agree! I don't know better which is why I stated it as hypothesis given my limited understanding of particle physics. I don't claim it to be definitive. And unlike flerfers, I am open to new information, evidence and experimentation. And will revise or toss out my hypothesis based on new information.

[@stevemackelprang8472]

Stephen Wolfram wrote about this 20 years ago in his book " A New Kind of Science ."

[@ek3279]

Isaac Asimov wrote about this 73 years ago in his book “Foundation.”

[@andrasbiro3007]

@@ek3279 I don't see how those are related.

[@victorsago]

@@ek3279 Not really.

[@Kokuswolf]

Would say, depends on what "this" is.

[@somjrgebn]

​@@Kokuswolf Yes, the problem is plenty have wrote about "this" way before 20 years ago. Who cares about Wolfram then? And if we still care that Wolfram had something to add, why not care about what this work adds too?

[@mrkristiangutt]

More on this please! (I’m not a computer scientist, but I think computation is more fundamental than particle physics)

[@SandipChitale]

Stephen Wolfram talks about rule 30 a lot. He is lately proposing a new kind of mathematics and theory of everything based on this notion of computational equivalence and computational irreducibility and notions of discrete space, brancheal space and rulial space and multiway graphs. Sara Imari Walker and Lee Cronin have a new theory about complexity called Assembly Theory which also sounds similar to the above. The notion of entropy is also similar in the sense that the fraction of micro-states (from the phase space) that map to what we would course grain and identify as the same macro-state. For example a water in a glass could be said to be at 50 degrees Celsius temperature, yet there may be many different arrangements of water molecules, zipping around at different speed that result in the same temperature.

[@unshakablespirit]

It looks to me these ideas are Stephen Wolfram’s ideas. He published the cellular automata long ago and most recently he and his team talk about observer theory. How this new paper is different from Wolfram’s team ideas apart from the mathematical particularities? I found observer theory the most convincing theory of everything.

[@stevenverhaegen8729]

I was waiting for Wolfram to be mentioned in the video 😮

[@monnoo8221]

Wolfram is utterly naive, regarding computation, information,, and meaning. The three central counterarguments are: 1. it is impossible to xtract meaning from something 2. the claim of fundamentally computational disregards Heisenbergs principle 3. Information is not received, but a result of perception That theory is neither convincing nor leading anywhere. particularly it is not explaining the mechanism by which complexity arises

[@cuthbertallgood7781]

Yep, I posted the same thing. This is straight out of Wolfram's A New Kind of Science, except not as advanced. Still, I'm happy to see that the ideas are spreading. People should realize that ANKOS explains both Relativity and QM in terms of simple rules, and if nothing else, it's remarkable that we have ANY theory that can completely resolve those two into the same simple model, without having to invoke some sort of "AND THEN MAGIC HAPPENS", as we do with so much physics ("and then the particle splits at some random time, for magical reasons").

[@energyscholar]

@@monnoo8221 Sure he is. He was also the leader of multiple highly successful Darpa projects to generate Quantum Neural Computing and AI. His books, which are HAMSTRUNG by Non Disclosure Agreements, only say a FRACTION of what he wanted to say. Dapra would not let him publish the key insights & implications for 'national security' reasons.

[@energyscholar]

@@cuthbertallgood7781 Sure is. I'm shocked this knowledge has been so slow spreading.

[@kevinvanhorn2193]

Sounds like this paper has connections to the ideas in Wolfram's book "The Second Law."

[@hansekbrand]

indeed, but what happened to rule 30? Not detected by the new algorithm?

[@DanielMartinez-ss5co]

The Second Law was explained in a perfect way by Arieh Ben Naim in his book series about Entropy ( 1) Information Theory, 2) A Farewell to Entropy, 3) Entropy Demystified, 4) Information, Entropy, Life and the Universe)

I would go further to say that LLM processing power allow s for reduction in lumpability. And every decrease in lumpability corresponds with an increase in predictive power. Delumping means moving from word lumps to granular 1 dimensional scales. Then those scales can be combined in increasingly complex ways to allow for multidimensional analyses that increase predictive power AND computational efficiency. Multidimensional gradient scales > lumpability. Keep in mind computer programming also happens in lumps. Most notably the binary lump. 0 or 1 instead of 0 through 1. True or false instead of 0 through 1 true and 0 through 1 false.

[@pnf197]

Ya gots to get your own show -- you just lumped too much in two paragraphs, and my head feels bumped.

[@Thomas-yl8lb]

@@pnf197 😅👍

[@DarkFox2232]

@@Thomas-yl8lb LLMs say: " 'Fart' goes well with 'brain' " Are you having it?

[@Steve-xh3by]

I agree, and very good insight here.

@@pnf197 Doing a show is a lot of effort. I can respect the heck out of Sabine for doing it for us, but I couldn’t do it myself. 🤣

[@godsofentropy]

Wonderful! I need more :) This emergence is a reason that some scientists don't support superdeterminism, claiming that sum is different than its parts (recently Kurzgesagt made a video about it). It is also a heart of entropy and I have a hunch that going deeper into this phenomena would give us answers to many scientific questions. and many philosophical ones. Thanks for the video, Sabine :)

[@Four_Words_And_Much_More]

Great review of a seminal article. It applies directly to my current research. I will look into how it might be used "by the numbers." That is to say, using the exact ideas and doing rigorous application to the concepts in my work. TY Sabine.

[@amorphant]

The beautiful, shimmering patterns in flocks of flying starlings are a glaring way to get the concept of emergence across. The patterns are the result of a few simple rules each bird follows in regards to other starlings flying close to it. A single starling by itself would give no indication whatsoever of the patterns that flocks exhibit -- the patterns are emergent. Here's a National Geographic video of them in action: kzbin.info/www/bejne/jGXJkGSVp51jiLs

[@DinsDale-tx4br]

Absolutely!

[@mba321]

Great example!

[@Zaphod23]

Didn’t wolfram already solve this?

[@KravMagoo]

Solve? Dunno...but the emergence found in the cellular automata concept is 100% Wolfram. Kind of astonished that his name wasn't mentioned...it's like talking about general and special relativity and not mentioning "that guy again ".

[@Hotmedal]

​@@KravMagoo Emergence from cellular automata as a concept has been there since Conway's game of life.

[@michaelblankenau6598]

@@KravMagoo100 % Wolfram ? That’s ridiculous.

[@patrickgriffiths889]

Sure. Just ask him, he'll tell you.

[@Ruktiet]

You can’t “solve” something which isn’t a clear question. And Wolfram goes into a much deeper concept in his book: “A New Kind of Science”. There he talks about mostly how complex behavior can arise from extremely simple rules, counterintuitively. And also about how most non-obvious patterened or nested systems are “computationally irreducible”, which essentially means that there are no shortcuts regarding calculating the system’s state other than simply performing the computation which it’s defined by. This has very far reaching implications in physics and other fields. But all that is not completely relevant to this video’s topic, where that is more about system’s tendency to form patterns/emergent phenomena as we go up scales, for which we use different models than the underlying, fundamental dynamics (e.g. Navier-Stokes equations for macroscopic fluid behavior vs particle physics to express the dynamics of each fundamental particle that each atom that each molecule of that fluid is made of)

[@DCDevTanelorn]

I’m not big on these more recent videos not ending with a strong conclusion and transitioning directly into a sponsor segment. We need the takeaway message to be stated in a way that we recognize it as the takeaway message, not as a transitional sentence into a sponsor message.

[@leahtigers771]

1) pay for content if you don’t want advertising - of course not! I’d also want knowledge & understanding to be free. Unfortunately our societies don’t value that. They value endless consumption & greed for some & grueling drudgery of work - if lucky, for the rest of us. 2) the conclusion was clearly stated twice in the beginning. Make the effort to rewind if you’ve already forgotten it.

[@doug3691]

I paused the video half way through and tried to imagine where it would end. So if the idea is to mathematically relate the micro, standard and macro, then that deals with transposing elements and forces from one to another -- 4 possibilities at first, later 6 perhaps. The things that immediately came to mind were teleportation (and entanglement) and faster than light travel (and wormholes). When like elements or processes or forces [I'm not sure where I'm going with this] get grouped they get scaled up to the next level; when broken down you end up at the next smaller level. Assuming you're an expert at some part of this, there must be nearly infinite practical applications (i.e.: some things move faster than light [or otherwise ignore that speed limit], most don't). Thank you, Sabine, for a thought-provoking segment. The above may not be new, but it's new to me, and pretty cool.

[@JamieC-qq7qw]

Huh, cyber sec researcher here, and this is of great interest for what I get up to. With the tcp/ip stack we’ve taken this idea of separation of ideas as an explicit rule of network architecture, ie you don’t need the hardware layer to understand the application layer, or vise versa It’s interesting since we haven’t updated it in a while too, with emergent cloud computing and edge functions, it would be an interesting branch of research to design emergent computing concepts beyond our current explicit stack

[@zeroamu]

Do you think the transition from one of these levels of complexity to another would involve what we would usually consider random errors? Where would these 'random' events be accommodated in this model? Love your content, Keep keeping us updated on the latest science news, Thank you :D

[@SabineHossenfelder]

I'm not sure what you mean by error, but transitioning from one level to the next can (and usually does) bring in some noise, that's remaining fluctuations from the underlying levels that isn't resolved. I mean, think of the traffic example: you'll get statistical predictions, but if you don't know exactly what each driver is doing, you will inevitably have some outlier events.

[@TheIgnoramus]

I recommend looking into new Noise based thermodynamic computation. It applies what you’re implying I believe.

[@axle.student]

That's an interesting thought considering error and noise as Sabine said. I was immediately thinking about the transition from quantum to relativistic and the collapse of the wave function where the left over uncertainty needs to be manually reset. Left over uncertainty, noise, error... We seam to encounter this often in any conversion or transition. Analog to digital is a good example in my head. In that conversion the noise (leftover precision or error) is discarded, but in the real universe you would expect that it has to go somewhere.

[@hudatolah]

New???!!! That’s Stephen Wolfram “New Kind of Science” book that was published 20 years ago!! 😢😢😢

[@Nathan-vt1jz]

As a “Lumpable” creature, I find comfort that scientists also struggle understanding complexity. Husbands have been working on that problem ad infinitum and while we have workable general model to understand the female mind, we definitely don’t have the details figured out.

[@brendangolledge8312]

Women are attracted to power, they love men for their utility, they are willing to deceive in order to get what they want from you, and they judge things emotionally rather than rationally. I think that summarizes the main differences between men and women.

[@neo-filthyfrank1347]

Stop begging for acceptance in a youtube comment section

[@Nathan-vt1jz]

@@neo-filthyfrank1347What are you talking about? I made a mildly humorous joke riffing on Sabine’s mildly humorous joke. Maybe you didn’t watch the video or just missed her dry humor.

[@neo-filthyfrank1347]

@@Nathan-vt1jz The type of joke one's inclined to tell belays the underlying psychology.

[@augustwest-e8l]

Many humans briefly enter the state of highly Humpable then after a period of entropy , emerging into a state of solid lumpability

[@rbarghouti]

I'm going to go out on a limb and say that this was actually your most important video. I think there's a good chance that this video's impact, at least in it's second order effects, will probably have the biggest impact of all the videos you've created.

[@milkerreklim]

I bet this was a relief for a hobbiest ❤

[@gordonwalter4293]

Great show. This is a sweet spot for you.

[@MichaelPiz]

"Lumpability" is my new favorite word. Also, Stephen Wolfram (the Mathematica guy) got a start on the cellular automata side of this in his 2002 book, _A New Kind of Science._ it's a fascinating read, and now available for free on line as a PDF. (I spent like $60 on it some years ago, but who knew?)

[@netscrooge]

Complexity science is older than that.

[@DanielMartinez-ss5co]

I have a well founded maths & physics background with specialization in IT and sincerely, I have read it (A new kind of science) and I've got nothing new, it is extremely boring and : OK, complexity could emerge from simple rules, Boltzmann knew it! He showed how Entropy could emerge from the atomistic structure level, Claude Shannon's Theory of Information was the key to understand it. So what with Wolfram? Now they have discovered a new term "lumpability" when IT has the more proper "encapsulation" to hide complexities when you don't need them

[@jan.kowalski]

@@DanielMartinez-ss5co Boltzman operated in adiabatic systems, Wolfram put the problem in a wide context of any system.

[@MichaelPiz]

@@DanielMartinez-ss5co I spent my entire 40+ year career in I.T. and software development, so I'm qualified to say that surely your credentials prove that Wolfram is full of shit. Right. "Boring" is a personal assessment, not a universal one. I found the book intelligent and engaging, but my physics background is merely that of more than 30 years as a passionate layman, so what do I know? Gee, you win.

[@DanielMartinez-ss5co]

@@jan.kowalski You should read Arieh Ben Naim books about Entropy, not Wolfram that is “Words, Words, Words”

[@seanvalentinus]

Be nice, Sabine! It's not"lumpable", traffic flow just has big bones, okay???

[@pheonix72]

So, they've just discovered Conway's game of Life? Bless...

[@xmathmanx]

Wolframs ' a new kind of science ' came out about 30 years ago and is by far the most thorough investigation into cellular automata

[@spacefertilizer]

I bet you they are already familiar with this

[@energyscholar]

@@xmathmanx Yes. Also, Wolfram was a team leader in assorted Darpa projects to generate new Quantum Computation & AI technologies. Seems like those were successful. NKS is an active thing. Perhaps someone needs to write another book on this topic.

[@xmathmanx]

@@energyscholar I never heard of wolframs association with DARPA and it doesn't sound likely to me

[@energyscholar]

@@xmathmanx Of course you've not heard about it! It's covered by NDA! I'm sharing inside information right now. His first Darpa project was in the late 1980s, when one of his CA rules were used as the cryptographic basis for next-generation NATO radio communication. Later he lead a Darpa project starting in late 1990 to build a new technology to crack Public Key Cryptography. Other project scientists included Stuart Kauffman, Murray Gel-Mann, & Brosl Hasslacher. Gel-Mann had to withdraw for health reasons and was replaced by a young Aussie super-genius. This project SUCCEEDED beyond wildest expectations and was HEAVILY CLASSIFIED. It's created a new form of Quantum Neural Computing that has lead directly to the current breakthroughs in AI. This is history-making stuff that's not documented publicly. I could go on but will stop with those two. I've had the privilege of interviewing quite a few people connected with these projects. Much of the work took place at the New Mexico Center for Complexity. Lol, "Doesn't sound likely to me". Funny! His particular special talent, beyond innate brilliance, is how he enhances the effective intelligence of those with whom he works.

[@wry6read]

Thanks!

[@ablebaker8664]

This is very interesting. I've always thought of emergence as a thermodynamic process. Whatever structure/ process releases heat in forming is subject to being broken if the heat it releases is available in the environment. When a structure forms that requires more heat than is usually available it remains stable and can accumulate additions based on how stable those additions are. Snowflakes for example, or spontaneous polymerisation of nitrogenous bases. A grain of dust can act as a substrate for water vapor to initiate formation of an ice nanocrystal but it's the thermodynamic stability of the additional water molecules to the crystal that directs the structure and symmetry of the delicate snowflake that grows from it. In abiogenesis, there seems to be a bias for there being some "best" way for self catalyzing nucleotides to form by spontaneous polymerisation, but all that appears to be necessary is an environment that favors thermodynamicly stable structures, which pretty much implies that there were multitudes of differently viable environments competing and colluding together to produce the first primordial living chemistry and the first reproductive proto-living constructs by assimilation and çonstructive interaction, eventually resulting in crude homeostatic assemblages... Living cells. Through it all, the structures that perform the most work tend to compete most favorably and lead to the highest dissipation of potential. The highest entropy structure/process wins. More complex structures/processes tend to require more available potential, and tend to increase in complexity so long as there is sufficient available potential. Evolution then, is just a competition for the best heat engine.

[@souprememc]

I defer to Wolfram on anything in this domain…

[@commentarytalk1446]

I'm sure one of the pictures was Rule 30 ie a non-repeating aka random emergence out of a few simple rules. I'm a little surprised that an even simpler system was not postulated than 25 physical units (itself almost certainly a limitation of current knowledge) and starting with a more logic/rule based starting position.

[@energyscholar]

@@commentarytalk1446 Yes, that was Rule 30.

[@aleksandarjovanovic9080]

I am not sure that we have a lot of evidence for emergence as a principle. I think small building blocks could cause "complexity" to emerge, but it could also be reversed from all we know. The key question is, when you plot different resolutions like in the video, ftozen at one point in time, and then start evolving them, are all resolutions evolving simultaneously or not? If they are, it's hard to put a direction that must be implied by causality.

[@SabineHossenfelder]

I don't know what you mean by a resolution evolving, sorry, can you explain?

[@generichuman_]

The separate resolutions aren't different realities that are evolving in unison, it's all one reality that evolves, we just have different descriptions as a matter of convenience. I don't think there's a good case for downward causation, which seems to be what you're implying. If moving water molecules are one description, and waves are another description, I think it's clear that all that really exists is the atoms, and waves are a higher order concept that we use because motion of waves is what we perceive, but I think it's a mistake to say that because the atoms and the waves evolve simultaneously, that causation can go the other way and the waves could cause the atoms.

[@monnoo8221]

@@generichuman_ yep, make it flat, make it into dus, and then try explaining. usual positivist crap

[@aleksandarjovanovic9080]

@@SabineHossenfelder Yes, I might have hyper-focused on a very specific part of the video, sorry :D. I meant if we look at the representation at 1:37, which was very interesting to me, we see different resolutions of "the world", so to say. These are still representations of the same "world" and in the same space, and (I think) same time - i.e. if we somehow start evolving the "world" over time according to some laws, all of the resolutions should evolve simultaneously. So if that is true, it seems hard to say if the direction of causality goes from deepest resolution upward, ex from particle physics to the solar system, or the other way around. It seems like it could be the other way too, for all I can tell. Though it might be only me, I'm a data scientist, not physicist. :D

[@TheWooTubes]

​@@aleksandarjovanovic9080Surely, if you are a data scientist, the laws of physics are just data compression from data about the universe :-) I think you said "particle physics" when you really meant "particles". Physics is the study of reality, not reality itself.

[@ktrethewey]

Why do you have a problem saying the name Stephen Wolfram?

[@TruthWielders]

✅"Emergence evolves universal machines to solve environmental challenges"✅ I was wondering when somebody would eventually talk about the problem of spaces (what you call scales, which seems like a substantive for 'level' rather then for 'breadth'). I was not expecting to hear about separation there, I was rather contemplating the potentials for interweaving of those (sub)spaces. Note: Everybody seems to forget that any 'thing' participate intimately with the environment no matter how independent it looks, it is not ! In a way, the 'thing' doesn't exists. Thanks Sabine, I'll be on the watch not to fall into any causal aperture.

[@ioanniskleftogiannis649]

Very good video, but it should have included at least one mention of the condensed-matter-physics(CMP) field, which is basically synonymous to emergent phenomena in physics. The concept that the macroscopic properties of a system do not depend on its microscopic details is the widely used concept of universalities in CMP, for example in phase transitions, localization phenomena etc..

[@KryptonianAI]

Could this apply to particle accelerators as well?

[@李原-j6r]

Stephen Wolfram likes this video.

[@ChrisAthanas]

I AM THE HIGHEST LUMPABLE!

[@Songfugel]

This is 101 of computer sciences (CS). Really nice of her to use it as an example, since the whole field of CS is 100% based on this. In programming specifically, we use high-low level languages to describe the level of this abstraction (not lumbability). For example we call Python and JAVA high level (of abstraction) programming language and C and Assembly low level (of abstraction) programming languages. The low and high refer only to the level of abstraction, not to the quality, power or difficulty of the languages (like many new and non-programmers often think) However, I don't see how anything in this is in anyway new or could give us a leg up, since it is a very well understood and "abused" phenomena. For example, neural network AIs are based on exactly this emergent phenomena that we have used since 1943

[@mateoconk]

I hope your daily release model has worked out for you Sabine. I’ve definitely grown to like it more. I feel like it’s given you more time with each topic, even just a minute or two

[@ludiclogic]

Terence McKenna talked a lot about the mechanisms of complexity conservation and generation (concrescence)

[@charlievane]

5:45 Wilma Flintstone would agree

[@Dr.M.VincentCurley]

I see what you did there...

[@EricKolotyluk]

Wow, this sounds closer to Wolfram Physics... Before we know it, Sabine will be advocating we replace String Theory with Wolfram Physics. I am just teasing, of course, or am I? 😏 Seriously though, I would love to hear Sabine pontificate on Wolfram Physics: the good, the bad, and the ugly...

[@netscrooge]

It's called complexity science. Wolfram has contributed to it.

[@Thomas-gk42]

Well she made fun of him in the song video "theories of everthing"...

[@EricKolotyluk]

@@Thomas-gk42 Sabine making fun of someone... who would have thought that possible? 🤔

[@Thomas-gk42]

@@EricKolotyluk hihi..

[@IuliusPsicofactum]

I'd use this kind of analysis to define what is an "observer". For example, measuring the spin of a particule causes a great change on your behavior as a complex system, then you are observing that spin. If it does not, then that spin is part of your complex system and counts as your own internal workings or even "noise". But I am just saying things here.

[@noob19087]

Interesting idea!

[@drewjaques7437]

What I can't wrap my head around is the relationship between scale and emergence. if we have layers of systems built on each other, that implies that scale in this regard is inherently discrete, no? What dictates that boundary layer? like that transition between states of matter, or that balancing of order and chaos on a knife's edge in chaos theory... There's something eerily fascinating about that transition to order, that moment of self-organization in such eerily beautiful and coordinated ways.

[@NightmareCourtPictures]

You should watch Wolfram's New Kind of Science series he has on KZbin. He shows, with proofs of exhaustion, that rules typically emulate the behaviour of other rules. That when a rule is computing something at one scale, you can course grain it (blur it, or zoom out to a larger scale) and see it computing something that seems completely different (and you can test that for yourself by running cellular automata like game of life, and blurring it to see what behaviour it emulates. Hint : It no longer looks like game of life) In extension, it is this ability for rules to emulate one another that implies Computational Equivelence : That all systems are capable of emulating each other, and the maximal ceiling of complexity for this emulation, is that of a Turing Universal Machine. Here is an example : Take an image of white noise. You can look at this image up close and see that its made of little random black and white pixels. But if you "zoomed out" or blurred the image (called course graining) then the noise becomes a single uniform color. This is a visual statement that Randomness and Uniformity are the same thing...equivalent to each other...as a function of scale. This being true, is an interesting fact. The same kind of thing with light : White light is made out of all wavelengths of light. a single color, being comprised of a near infinite number of colors, is again, another interesting fact that scale expresses equivalences between what are two opposite things (randomness and uniformity, the continuous and discrete, infinity and one-ness) Take another set of transformations : If we have in front of us an unshaded cube, from your angle, looking at this cube head-on, you see a square, but from my perspective which is looking at the same cube from a 45 degree angle...i see a rectangle. Both of us seeing different shapes...is an interesting fact. How can it be that we see different shapes when describing what is precisely the same object. Building off of this type of example, you can take a random distribution of dots and fill the cube. In most directions where you rotate this cube, it just appears random to us, but rotate it exactly 90 degrees and almost like magic, you find that it aligns in a patterned lattice. Again, it's another interesting fact, that this object can "emulate" the behavior of some other object, (randomness, to a pattern) under a group transformation (rotation)...a mere change in perspective... And that's the clue : What dictates the "boundary layer" is perspective...the observer. Why does this system do that thing at that scale, and this other thing at this other scale? It's because WE impose a perspective on the system at a particular scale. At a smaller scale...we wouldn't say it has these properties...where at others, we might say that it does (because at a different scale it's emulating the behavior of something else) for instance a molecule sized bacteria can not hear sound, or understand what it is...because sound is the result of many molecules moving up and down in a certain pattern. Therefor this bacteria, would not have a theory for sound. It would have a completely different description of "physics" as a creature of that size. Again...this is an interesting fact, that we impose a lot of the properties of systems to be what they are, as a result of trying to describe it. And this makes sense in the work of Stephan Wolfram, where all these systems are equivalent (like a single abstract object), and we simply "sample" or perceive this complex object in a particular way, because of the characteristics of our scale, our senses etc. I hope this kinda long paragraph, addresses in part your question. Cheers,

[@drewjaques7437]

@@NightmareCourtPictures thanks for the response. I can see how your examples relate to scale- but it seems to me they are more about describing the effects that perspective has on our ability to quantize this than the strangness inherent in emergent properties that seem to have no specific or linerar connection to its constituient scales- you can say that the idea of sound is irrelevant to something at the microscopic scale, but what about something like flow- it's an emergent behavior that doesn't feel like it has some sort of natural gradual transition- at some point there isn't flow, and then there is, no? or consciousness perhaps as a better example- it seems there's a specific threshold at which the sum becomes more than the parts. I think your answer explains part of this through perspective, but I feel like there's something else going on too, as if there's a metaphysical component we haven't quite figured out.

[@NightmareCourtPictures]

@@drewjaques7437 sound is very much like “flow” which I assume you mean like the direction of waves in water. Sound waves…water waves…basically the same construct: water is constituted by collections of molecules. If you were the size of a molecule you wouldn’t be able to perceive the flow of water. Better way to visualize this: imagine your at a bowling alley. People are rolling balls generally speaking in the same direction. We humans wouldn’t describe this as flow…but in aggregate bowling balls in a bowling alley is flowing, in a single direction. We don’t normally describe bowling balls being rolled down a bowling alley as a liquid flow because the bowling balls is roughly our size and we don’t perceive enough of the aggregate behavior to think of it as a flow. So meaningfully, the description of flow among a collection of discrete objects is a reflection of our perception, a perception imposed by our size relative to the bowling balls. In the wolfram model, the underlying metaphysics for why it is like this is because systems follow rules. The rules of the bowling alley: roll the ball and hit the pins. The resulting dynamics of many bowling balls rolling down an alley results in a larger scale dynamics that you can consider as something like a laminar flow. In extension all systems are following rules…and all those rules create behaviors that can then be extracted as physics depending on the perspective of the observer of those dynamics. If your a large observer you describe the balls in laminar flow…as a normal human observer you describe it as a bowling alley…as a tiny observer you describe it as molecules moving around randomly. Notice how at each scale the properties of the same system take on radically different behaviors, again based on who is doing the observation.

[@drewjaques7437]

​@@NightmareCourtPictures Ok, went and watched some wolfram vidoes. I see what yall are saying, but there still seems to be a flaw in our understanding for things like emergent behaviors that are radically different from the constituent behaviors. He talks at the edges of this in a few places, how simple rules can create complex patterns, but the problem of self definition and equivalent operations seems wrong instinctually- he talks about how our mathematics are really just a bunch of scaffolding add-ons to the maths of geometry and algebra, and i think he's right in that the divisions of specialities in sciences, the fields and tracks are really limiting our ability to create axiomatic rules that work better. The limit on computational models and similar issues like our inability to analyze/understand our own consciousness seems at odds with the idea of the simple to complex rule- as if there's something missing. So yea i can see the argument that in most cases where the scalar differences seem to result in systems/mechanics is really a matter of perspective, but that doesn't really address the root of some of these other issues. For example, let's ignore consciousness. What about matter at the nanoscopic scale? An electron isn't a physical object, it has absolutely nothing in common with our understanding of everyday matter- it doesn't have a size or a shape, it's a probabilistic wave. I don't see how we get from that to macroscale naturally.

Fascinating. According to Wikipedia (I know, I know…), the term “lumpability” has been around since 1976. It originates from the area of modeling and simulation of systems, a field I briefly taught to future teachers. However, we used methods and terminology from the former Czechoslovakia, which was “a bit” different, so I never heard this term or any similar ones before. I guess one learns something new every day…

[@PC42190]

I would love to hear you about what Ilya Prigogine called "dissipative structures", also treated in Bobby Azarian's "The Romance of Reality"

[@WilliamRamirez-m2t]

You clarify complicated ideas so well!

[@StephenOcean]

I asked Claude to write this: # Quantum Information Theory and Consciousness: A Technical Exploration **Sabine Hossenfelder:** Federico, let's dive into the mathematical structure of quantum information theory and how you propose to apply it to consciousness. Can you start by outlining the key mathematical concepts you're drawing from? **Federico Faggin:** Gladly, Sabine. The core of my approach revolves around quantum entanglement and quantum superposition. Mathematically, we can represent a quantum state as a vector in a Hilbert space. For a two-qubit system, we might have: |ψ⟩ = α|00⟩ + β|01⟩ + γ|10⟩ + δ|11⟩ where α, β, γ, and δ are complex numbers satisfying |α|² + |β|² + |γ|² + |δ|² = 1. **Sabine:** Okay, that's standard quantum mechanics. How do you relate this to consciousness? **Federico:** I propose that conscious states can be represented as quantum states in a similar manner. Just as a qubit can be in a superposition of states, a conscious thought might be in a superposition of potential experiences until it's "observed" or brought into focus. **Sabine:** That's an intriguing analogy, but how do you account for the vastly greater complexity of conscious states compared to simple qubit systems? **Federico:** You're right to point out the complexity. We'd need to consider much higher-dimensional Hilbert spaces. For instance, we might represent a conscious state as: |C⟩ = ∑ᵢ cᵢ|ϕᵢ⟩ where |ϕᵢ⟩ represents basic conscious elements and cᵢ are complex coefficients. The challenge is defining these basic elements and understanding how they combine. **Sabine:** That's a significant challenge indeed. How do you propose to identify and measure these 'basic conscious elements'? **Federico:** This is where quantum information theory becomes crucial. We can use concepts like von Neumann entropy to quantify the information content of these conscious states. For a density matrix ρ representing a conscious state, we'd have: S(ρ) = -Tr(ρ log ρ) This could provide a measure of the complexity or richness of a conscious experience. **Sabine:** Interesting approach, Federico. But I'm skeptical about how we can experimentally determine the density matrix for a conscious state. Unlike with physical qubits, we can't directly manipulate or measure conscious states. **Federico:** You're right that direct measurement is challenging. However, we might infer these states indirectly through neural correlates. For instance, we could look at the entanglement between different brain regions. The entanglement entropy between subsystems A and B of the brain could be represented as: S(ρᴀ) = -Tr(ρᴀ log ρᴀ) where ρᴀ is the reduced density matrix of subsystem A. **Sabine:** That's an interesting idea, but it seems like we're still dealing with classical correlations between neural activities rather than true quantum entanglement. How do you propose to distinguish between the two? **Federico:** You've hit on a key challenge. One approach might be to look for violations of Bell-like inequalities in neural data. We could adapt the CHSH inequality to neural correlations: |⟨AB⟩ + ⟨AB'⟩ + ⟨A'B⟩ - ⟨A'B'⟩| ≤ 2 Where A, A', B, and B' represent different measurement settings on neural subsystems. A violation of this inequality would suggest quantum correlations. **Sabine:** That's clever, Federico, but I'm concerned about the practical feasibility. The brain is a noisy, warm environment. How do you maintain quantum coherence long enough to observe these effects? **Federico:** You're right to be concerned about decoherence, Sabine. However, recent work in quantum biology suggests that biological systems might exploit noise-assisted quantum effects. We could model this using the Lindblad equation: dρ/dt = -i[H, ρ] + ∑ᵢ (LᵢρLᵢ† - ½{Lᵢ†Lᵢ, ρ}) Where H is the Hamiltonian of the system and Lᵢ are Lindblad operators representing the interaction with the environment. **Sabine:** I'm familiar with the Lindblad equation, but applying it to neural systems seems like a huge leap. Have you considered how to parameterize this for brain dynamics? **Federico:** It's certainly challenging, but not impossible. We could start by modeling smaller neural circuits and gradually scale up. The Hamiltonian could represent neural interactions, while the Lindblad operators could model interactions with glial cells or the broader chemical environment. **Sabine:** That's an ambitious program, Federico. But I'm still not clear on how this relates to subjective experience. Even if we find quantum effects in the brain, how does that explain the qualitative aspects of consciousness? **Federico:** This is where I believe we need to extend our mathematical framework. I propose that we need to introduce a new mathematical object to represent qualia - let's call it a 'quale operator' Q. This operator would act on the quantum state of the brain to produce subjective experiences. **Sabine:** Now we're really in speculative territory, Federico. How would you mathematically define this 'quale operator'? **Federico:** You're right, this is highly speculative. But as a starting point, we might define Q as a Hermitian operator, ensuring that the eigenvalues are real and could correspond to the intensity of subjective experiences. The expectation value of Q in a given brain state |ψ⟩ could represent the overall subjective experience: ⟨Q⟩ = ⟨ψ|Q|ψ⟩ **Sabine:** This is creative, Federico, but it seems to push the hard problem of consciousness into the definition of Q. How do we determine the form of this operator? **Federico:** You've identified the crux of the challenge, Sabine. Determining the form of Q is indeed the hard part. We might start by looking at how different brain states correlate with reported subjective experiences and try to construct Q empirically. It's a daunting task, but not unlike how we've constructed other operators in quantum mechanics. **Sabine:** I appreciate the attempt to formalize these ideas, Federico. But I'm concerned that we're adding layers of mathematical complexity without necessarily increasing our explanatory power. How can we test these ideas empirically? **Federico:** You're right to push for empirical tests, Sabine. We could start by looking for quantum signatures in brain activity, such as long-range quantum correlations or unexpected coherence times. Additionally, if the quale operator theory is correct, we might predict certain patterns of brain activity that consistently correlate with specific subjective experiences. **Sabine:** Those are interesting proposals, Federico. While I remain skeptical, I appreciate the rigor you're trying to bring to these ideas. It's clear that applying quantum information theory to consciousness raises as many questions as it answers. **Federico:** Thank you, Sabine. Your skepticism is valuable - it pushes us to be more precise and to ground our speculations in testable mathematics. Even if this specific approach doesn't pan out, I believe exploring these ideas will deepen our understanding of both quantum systems and consciousness. **Sabine:** I hope you're right, Federico. This conversation has certainly given me a lot to think about. While I'm not convinced that quantum mechanics holds the key to consciousness, I agree that we need bold new ideas to tackle this profound mystery.

[@czolus]

I hear "and they call that property 'lumpability'", and as a computer scientist, it warms my heart to see something sensibly named

[@jaykaye6684]

For fear of sounding like an actor, going back to your videos on free will, I've had this idea for a while that consciousness is a result of localized areas of complexity. The metaphor I use when explaining it to other people is you think of a string as the universe, then you tie a knot in it, that knot is a mind. It's still part of the string, but it's also a distinct object. Simpler creatures are less complex, so they have a lower level of consciousness, until you get down to creatures that are basically just organic machines. I figure that rather than living creatures having some kind of divine pleroma that gives them thought, it might just be an inherent property of the universe.

[@Shynobyn]

As a programmer I did the excercise of creating a virtual CPU out of Nand gates and it's fascinating. By combining them you create new building blocks which in turn you can use to create even more building blocks, and before you realize you have a very complex machine that can do all sorts of things, all made out of a single elementary block.

[@artscience9981]

I’ve spent a lot of time trying to model the impact of radiation effects in semiconductors on spacecraft systems. This is a good example of complexity and scalability, because the radiation cause, an energetic ion or photon, collides with the atoms in a semiconductor crystal. This in turn results in liberated charge, which can change the state of a bit, or create an unwanted pulse in continuous signal, which can affect propagate through software, which can affect more hardware, such as a star trackers, which might cause a satellite to lose track of where it is in space. Of course we do everything we can to arrest the propagation of these effects, but prediction is not always possible because of the complexity of the system and all the scales involved. I think I’m going to read this paper and take a look at Wolfram’s book.

[@jan.kowalski]

on bigger scales, our own world could be perceived as quantum

[@amorfati4752]

Individual drivers tend towards the average driver as the amount of drivers increase. You can calculate information about a canister of gas without knowing something about every single particle inside the canister, precisely because you have so many of them that the statistical information caused by numbers dominates whatever individual differences these particles might have. But this is precisely the emergence of the next layer. Every layer tends to be the limit (mathematical definition) of the summation of something in the lower layer.

[@Sheblah1]

Cellular automata are equivalent to a subset of Turing Machines and a brief study of Tibor Rado's article on the Busy Beaver Function will offer a clearer and more general understanding of why we can't explicitly predict the outcome of iterative computations per se. The keyword here is 'explicitly'.

[@UgowestLx]

Must say that most architects are curious by nature, and for me the very fabric of the universe is something fascinating. Physics amd cosmology are very cool. Ty Sabine

[@petkish]

Separation of scales is a beautiful reason why in the quantum-mechanistic universe we still may think we have the free will. We just operate on a scale where quantim mechanics are not observable and the emergent complexity of our scale requires us to be adaptive and do our learning and decision making.

[@mikelistman5263]

Great choice of paper and presentation. "Lumpability" shows why English is a great tech language and also describes my social skills.

[@hanslepoeter5167]

Computer hardware is completely independent of algorithm. Implementing computers with electric circuits is common but a computer implemented with pneumatics, hydraulics, mechanical is absolutely possible. Slow, huge, expensive ... but possible.

[@kenjohnson5124]

0:59 Simple to less simple? Following what plan ? Following what program?

[@RogerValor]

To be honest, as someone who thinks about code, not specificly the computer, and grew up with coding since my teens, and being able to understand even hard parts of my field by now, I think in the world of programming, the solid world view of math meets the flow of logic and the intuition of art. This makes it natural, that "emergence" emerges in that field. The hard part is, that coming from other fields, usually programming is simply seen as something formal, which is why there are so many different types of programmers. So yes, I believe those "computer scientists" are right, as we are only still at the beginning of understanding that science itself, and often forget, that the world of virtual logic is by itself interesting, if we only think about the limitations of our current hardware. It is also quite interesting, that many of the programming paradigms and patterns actually arise from limitations or rules of the underlying programming language or hardware itself. And in the end, simulating large systems, like writing a simulator for gravity, and trying to make that simulation realistic but at the same time fast enough to be only part of your program, gives you great respect of the numbers involved. I am also kind of amazed, that none of what you said in this video surprises me after 30 years of working with simulations or games

[@Khomyakov.Vladimir]

In artificial neural networks, the activation dynamics of non-trainable variables is strongly coupled to the learning dynamics of trainable variables. During the activation pass, the boundary neurons (e.g., input neurons) are mapped to the bulk neurons (e.g., hidden neurons), and during the learning pass, both bulk and boundary neurons are mapped to changes in trainable variables (e.g., weights and biases). For example, in feed-forward neural networks, forward propagation is the activation pass and backward propagation is the learning pass. We show that a composition of the two maps establishes a duality map between a subspace of non-trainable boundary variables (e.g., dataset) and a tangent subspace of trainable variables (i.e., learning). In general, the dataset-learning duality is a complex non-linear map between high-dimensional spaces, but in a learning equilibrium, the problem can be linearized and reduced to many weakly coupled one-dimensional problems. We use the duality to study the emergence of criticality, or the power-law distributions of fluctuations of the trainable variables. In particular, we show that criticality can emerge in the learning system even from the dataset in a non-critical state, and that the power-law distribution can be modified by changing either the activation function or the loss function.

[@dryued6874]

Funny you should say that. I was recently pointed to an article in AI called "Pretraining Without Attention", where the authors came to the conclusion that the architecture of the neural network matters surprisingly little for the accuracy of the results, given that the network is "reasonably well-connected", which the channel I found the article in interpreted as follows: 1) There is nonlinearity (which pretty much any neural network has), and 2) There are layer-skipping connections between several layers (which one can interpret as intermixing of scales).

[@winstongludovatz111]

The authors consider a (discrete) stochastic process and study whether there is a coarse graining of states that leads to a _deterministic_ dynamic. This is easiest to decide in the case of a Markov process and reduced to this case by replacing the process with the process of increasing histories. The interesting take is the following: you can have a nontrivial deterministic macroscopic evolution driven by a stochastic microscopic one. This may explain the existence of deterministic laws of physics in the macroscopic domain when there are no such laws on the subatomic level. However this all depends on the process of coarse graining which is _subjective_ (what distinctions do you think are important?) So the negation free will rest entirely on how coarse you willing to see the world.

[@jan.kowalski]

Not entirely. Emergence is a process where you loose or transfer out some information. This has to have a thermodynamic effects. On different scales even our current world (in "out" scale") could be seen as "quantum".

[@joyl7842]

This is quite fascinating. It's like trying to understand something that appears to exist for the sole reason of not being understood.

[@nicholaslozenski5149]

At the intrinsic level of existence, all things are dependent upon the same primordial principles. These principles are eminent and unify all manifest reality, extending from the quantum level to the cosmic scale. This creates a self-referential and self-similar property that results in a consistent cosmic mechanical framework.This framework is evident in universal constants, geometric and mathematical axioms, and the intrinsic interconnectedness of quantum states. These fundamental principles are not only foundational but necessary for the coherence and stability of the universe. They reflect an underlying order that ensures the regularity and predictability of natural laws.While I’m not being exhaustive in this explanation, I think the point is clear: the universe operates on a unified set of principles that are essential and inescapable, creating a harmonious and interdependent reality.

[@chinemeremohaeri9100]

Nothing is the absence of something is number theory. Nothing is an object. So is something. After heat death, nothing will assume a tiny point and resume towards its limit, which is inevitable something. Never ending braid of immovable and unstoppable objects. Because you can't tell which is moving or static, a new object is created. The concept of nothing goes by Einstein's two-point thesis. If you have two objects and nothing else, you invariable have a single object. This is because if you have an immovable force and an unstoppable force, you cannot tell which one is moving and which one is standing still. One becomes two becomes three becomes four. This can only be detected in motion. Something moving in nothing have both space and matter expanding, causing a sort of pseudo motion. The world expanded and vanished.

[@DavidEsp1]

As presented, the "levels of lumping" occur on an axis of physical+numerical scale. As a slightly (ex-) comp-sci guy, the word "Abstraction" is strong in my head. In that context, there need not be a single (universal) "upwards/bigger/better" direction, there may be several, each leading towards a different kind of specialisation (e.g. class of observation or use-case). Like different Views on a database - especially if they are complex (e.g. state-machine driven/interpreted) ones. Neurons vs neural network also comes to mind (though still a kind of "bigger"). Then there's Mandelbrot's various creations (e.g. his famous figures) and of course fractals (rules => types => dimensionalities). Applying this (more generic) perspective of abstraction back to physics, what _other_ kinds of lumping are recognised or postulated in such observational philosophies? Like do lumping-particles always have to be physically/geographically close (relative to other such particles), as with planets, or could they just all be in random locations but "on the same wavelength" in some fashion. For example different matter with different absorption spectra in an energetic nebula. Human communications comes to mind (internet and otherwise). Viruses (alone or interacting with others or other stuff) could be another. Same for mankind's historical and current _memes_ (of the pre-social-media kind).

[@jseligmann]

It certainly makes sense that regardless of the scale, all scales are governed by to the same relationship to energy, and, regardless of the scale, particles seek out combinations for relative stability at the cost of individuality and thus grow ever larger and more complex in an ongoing struggle with entropy.

[@Maouww]

Sabine and Kurzgesagt having an indirect conversation over KZbin and I'm here for it! Also emergence is extremely engaging in video games - there's so many layers to this.