Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I don't know if this instance qualifies as one, but I think its fair to say that cosmology is the one domain of "fundamental" physics where "discrepancies" or question marks keep piling up and not really resolving.

It the pattern of previous science revolutions repeats, there could come a point where reinterpreting the large existing body of knowledge using a different paradigm would explain an number of "oddities" in a more economical way.

I don't know if this generation of telescopes will get us there but it feels that this is a plausible outcome over the next 1-2 decades. Which would be very exciting :-)



I think this says less about cosmology and more about the incredibly effectiveness of the standard model in the regime we can test directly on earth.

If we compare ΛCDM to most other scientific theories it doesn't look so bad in terms of discrepancies. Certainly there are many unexplained effects in solid state physics, there isn't even an accepted explanation for why rubbing a balloon on your head makes it stick to a wall and that's an experiment you probably did as a child.


> ΛCDM

Lambda-CDM Model [0], for the ones like me who haven't heard it before.

[0]: https://en.wikipedia.org/wiki/Lambda-CDM_model


>Certainly there are many unexplained effects in solid state physics

Wait for it… Why ice is slippery?

Usual explanation is completely incorrect. Actual semi-conclusive research just recently happened.


I had to look that up. Here's research[1][2] from 2019 about "why ice is so slippery", including some of the apparent surprises. I dunno. I'm not a physicist so some of the surprises seem like very minor things to me.

Spoiler: According to this research, ice is slippery because of a thin layer of water. (As we expected, no?) But the water layer is 1) thinner than expected, 2) more viscous than expected, and 3) contains bits of ice which help make it extra slippery.

> "Usual explanation is completely incorrect."

Only for an unusual definition of "completely" IMO. Again, IANAP.

[1] https://phys.org/news/2019-11-ice-slippery.html

[2] https://journals.aps.org/prx/abstract/10.1103/PhysRevX.9.041...


Exactly, this it’s the new research. Standard (incorrect) explanation is because ice melts because of the pressure from the object put on it. Robert Wood showed it to be untrue at the beginning of the twentieth century, but “popular scientists” didn’t get the memo.


> Only for an unusual definition of "completely" IMO.

Agreed. While the "usual explanation" may lack the details that actual testing provided, deduction and logic in this case were pretty much harmonious with the findings. The water layer being thinner or more viscous than expected doesn't invalidate the basic assumption, and that's where all science starts, right? Some basic, yet to be disproved* assumption.


> contains bits of ice which help make it extra slippery

Wait, why would bits of ice make it extra slippery if it's the water that makes ice slippery?


I assume like walking on marbles or ball bearings.


Maybe the ice molecules move through the water with less resistance, since the ice molecules are already 'tied up' in a lattice structure and therefore do not form as strong of hydrogen bonds with the neighboring water molecules.


Ice isn't slippery, water is. If anything I'd say ice is actually pretty sticky. A very cold ice cube will easily stick to your skin.


That's just because your skin has water molecules that freeze on contact with the ice cube. If you use tongs to put an ice cube on your desk, it doesn't stick at all, right? And the friction is very low so it's easy to kick away -- things like a leather wallet stick much better to your desk.


I've not tried it but intuitively I'd expect it to slide about as well as other very hard things of the same shape.


I've dropped ice cubes on the floor before and they definitely slide a lot more than most objects of the same shape.


I remember listening to joe rogan when he interviewed neil degrasse tyson and he had some fascinating insights into the behavior of water with relation to pressure and temperature.

I can imagine ice on an iceskate wanting to be solid, but because that takes up too much space it becomes a liquid instead.


It is not, because ice has a smooth surface and that probably the surface layer melts a bit because your shoes are warm?

That would be my reasoning, but it likely seems to be wrong, well why?


The usual hypothesis is that a microscopic layer of the surface melts, not because your shoes are warm, but because of the pressure. But the pressure is not enough to do that.

That said, as anyone who has been in icy conditions can attest, it is clear that ice at ~0° C is vastly more slippery than at, say, -20°C.


My understanding is that, at the borders, master is constantly changing between its states. A boiling pot has water molecules turning to steam, as well as vice versa. It just has more of the first probabilistically.

Maybe the same happens with ice and water.


That's more or less it, as far as I understand. There's the hexagonal lattice of solid water ice, where hydrogen bonds form a 3D tetrahedral structure which is very stable. At the boundary, there are no molecules "above" the solid latice, so those water molecules are held less tightly. The exact dynamics are challenging to predict because we can't exactly see what's going on (most simulation based).


The pressure from well distributed static load divided by area is not, but on the tiny scale where the difference between grippy and less grippy surfaces happens there isn't so much "well distributed" going on. And once you add lateral force to the mix all bets are off: there will always be a point getting better grip (is surface interference the correct term?) than others, see a local force concentration and when that causes a tiny spot of phase transition there will very soon be a new point of least local slippyness getting all the attention of lateral force.


", it is clear that ice at ~0° C is vastly more slippery than at, say, -20°C."

There is nothing more slippery in my experience, than rain on the street, that just turned frozen. But ice at -20°C is usually older and has not such a smooth surface anymore, so hard to compare in non lab settings.


If that were the case, then cold things wouldn't slip on ice, but they do (for a demonstration, pick up a rock that's been sitting out in the cold and note that it still slides on ice)


I'm not sure a cold rock sliding across very cold ice will slide any better than if the ice was another very large smooth rock. Ice is hard and smooth. Hard smooth things have low friction.


Wouldn't that just be due to the low coefficient of friction?


> Wouldn't that just be due to the low coefficient of friction?

You mean, its slipperiness?


You're talking about the "2D gas vs liquid" discussion?


Link to the research?


My favourite example of the intractabilities of some theories is that magnetohydronamics apparently can't predict the formation of streamer jets when you put your finger on a kid's plasma ball – i.e. the main point of the toy is beyond the most advanced theory that lies behind NIF, JET, ITER, etc...


At this point in the thread, I'm wondering if we do a disservice to physics students by making it appear we have it all figured out.


I don't think I've ever, out of all my physics classes up to grad seminars, been given the impression we have everything figured out. In fact, it was hammered into us that all we have are "effective" theories, at least when it comes to high energy physics, and that's not even talking about grand unification (electroweak + strong force unification), let alone Theory of Everything (electroweak + strong + gravity).


Maybe not where you studied, or at the level you studied, but in upper division undergrad physics at a top tier California school I definitely was given the impression that I should just crunch the numbers and not think too much about how it might be working.


Was this a quantum mechanics class? Thinking about how it might be working leads to strange things like the Many-Worlds Theory[1] and other very weird ideas. "Shut up and calculate" is the usual method of dealing with these deeper questions.

Beware; deep rabbit hole. [1]https://plato.stanford.edu/entries/qm-manyworlds/#:~:text=Th....


So much this! There’s surely a huge argument that all of scientific education is a massive disservice.

The point should be to learn and appreciate the method or process of scientific investigation of uncertain and mysterious or hard to understand phenomena.

Instead we get dogma as a proxy of measuring intelligence with little regard for what the fundamental tools are of being a scientist.

I’ve gone all the way through to Grad School and came out astounded at just how little commitment to or a sense of the essence of scientific investigation and what’s expected of the investigator there is in the system. They don’t prepare you for it because they themselves weren’t prepared. You can try to leverage some meta understanding of the “process” in conversation or debate, but so often the conversation falls flat because few are prepared or accustomed to it. Research is often done, IMO, in philosophical poverty by people eking out a living in the gutters of novelty and paradigmatic safety, averting their gazes from the sky (flourishes aside, you get my point).

Putting aside the health of actual research. If the general public is to benefit from education and pass that benefit into their society (that’s the point right), it needs to be more than soon to be forgotten and often useless fallacies.


> There’s surely a huge argument that all of scientific education is a massive disservice.

> If the general public is to benefit from education and pass that benefit into their society (that’s the point right), it needs to be more than soon to be forgotten and often useless fallacies.

I realize this is hyperbole, but still I think it's obvious that there is more than soon to be forgotten and often useless fallacies.

I do generally agree though that current models/paradigms are usually presented more as "the final word" vs "a useful mental model".

Esp. when paradigms are challenged by, or conflict with untestable traditional explanations, ppl tend to get irritated and overstate the confidence of their own understanding


Agree. I’m guilty of descending to hyperbole at times!

Nonetheless, while I agree with your pushback, I do wonder how much utility there is in the “dogma” approach. There’s a lot of “facts” being thrown around in education, from what I’ve seen, that are often forgotten or become vague memories. How much better would it be to focus on skills and practice and concepts? Especially in the digital age where a fact is easily discoverable, provided one has the appropriate research skills.


Calling mental models "laws of physics" is the biggest linguistic disservice to science itself, so in a way, yes.


Who do you think makes it appear we have it all figured out? That is not my impression at all. All the scientists I know are extremely aware of the limitations of their field.


If it was all figured out why get into the field? Sure some do it just to know. But the hunt is what drives most.


It is easy for children to come up with questions for biologists that none can answer, and that none has even tried to answer.

Biologists are almost unique among scientists in being happy to say how little they still know about their subject. Up until last year nobody had thought to see whether anything eats viruses! Turns out some do.


> Biologists are almost unique among scientists in being happy to say how little they still know [...]

Citation needed.

> Up until last year nobody had thought to see whether anything eats viruses! Turns out some do.

Nah, lots of things eat viruses. It's nothing unusual at all. You eat viruses, I eat viruses. They are everywhere, after all.

The novel finding was a critter that lives / can live solely on viruses.


    > Nah, lots of things eat viruses. It's nothing unusual at all. You
    > eat viruses, I eat viruses. They are everywhere, after all.
When an engineer walks in front of an idling jet engine you don't say the jet eats viruses.


To be more precise, viruses are just made up of proteins and DNA / RNA. Your normal digestion that can handle proteins and DNA/RNA from animals, plants etc doesn't have any more problem breaking down virus proteins into amino acids and absorbing them.


I think the OP was talking about the bacteria that derive non-negligible sustenance from viruses.

>Moreover, our foraging trials demonstrated robust growth in the Halteria population with only chloroviruses as food (rint = 0.66 ± 0.26 [SD], black lines, Fig. 1A), with minimal to no growth in the controls (with chloroviruses filtered out; rint = 0.22 ± 0.12 [SD], blue lines, Fig. 1C). The abundance of the larger Paramecium did not increase in treatment or control trials (Fig. 1D), indicating that not all ciliates can grow on chloroviruses in these conditions, even when they consume them.

https://www.pnas.org/doi/10.1073/pnas.2215000120


Yes, I know. That's why I wrote

>> Up until last year nobody had thought to see whether anything eats viruses! Turns out some do.

> Nah, lots of things eat viruses. It's nothing unusual at all. You eat viruses, I eat viruses. They are everywhere, after all.

> The novel finding was a critter that lives / can live solely on viruses.


You wrote it, but it was what we all understood already, making writing it nothing but an exercise in snark.


Not sure.

Eg creatures that eat plastic are still news, even if plastic is not their sole diet.


Yet, you are eating plastic every day.


Yes, but not digesting it.


> Citation needed

How could you possible find a citation for that? It’s not even pretending to be a scientific or totally objective claim. Asking for a citation for this type of statement is no way to have a discussion. Do you not see why?


Eh, 'Citation needed.' was my admittedly somewhat snarky way of calling bullshit.

Most any scientist will happily babble all about the stuff they don't know yet in their discipline, because that's exactly where the excitement lies for them.


Some do. Many don't.

Much of Wikipedia is "curated" by retired professors carefully scrubbing mention of anything new that makes their graduate thesis look ill-conceived.


> Much of Wikipedia is "curated" by retired professors carefully scrubbing mention of anything new that makes their graduate thesis look ill-conceived.

What makes you think so? What evidence do you have?


Have you read any of it?


Intractable in the analytic sense, or intractable numerically… or both?


Both!


Magnetohydrodynamics is, specifically, the "easy part" carved out of plasma fluid dynamics. It is inadequate to almost all applications, with only rare, precious exceptions, mostly manufactured. Devices that rely on plasma fluid dynamics to work are carefully designed to keep the plasma in the domain where MHD can be used to model them.

Astrophysicists, as a rule, hate to be obliged to consider phenomena that involve plasma fluid dynamics, even what can be shoehorned into MHD. Such phenomena are thus orphaned, and you won't find anybody talking about them.

The exception is solar physics, where nothing can be done at all without fully general plasma fluid dynamics. Solar physicists have the largest gonads in science, on par with rocket propellant chemists.


Is plasma fluid dynamics the most important hated obligation of astrophysicists?


I think most consider it "somebody else's problem". I know some don't like to think there is anything to it beyond MHD, so they call anything involving plasma "MHD".

Are there other phenomena they see but don't like to talk about? Maybe?


Is it called "hydrodynamics" because of an assumption of incompressibility (like regular hydrodynamics vs aerodynamics)?


It has several commonly unphysical assumptions, including infinite conductance, "freezing" the magnetic field in a chosen frame, and assumptions about time and length scales.

"Effects which are essentially kinetic and not captured by fluid models include double layers, Landau damping, a wide range of instabilities, chemical separation in space plasmas and electron runaway."

That electrons are 1836 times less massive than the lightest positive charge carrier is neglected. Accelerated, they strike positive and neutral particles and knock loose more electrons.


> there isn't even an accepted explanation for why rubbing a balloon on your head makes it stick to a wall

But the accepted explanation is "static electricity", no?

Or do you mean we don't "really" know when asking a couple of follow-up "why?" questions further?


"Static electricity" as an explanation without follow-up "why?" questions is just a curiosity-stopper [1] or guessing the teacher's password [2].

[1] https://www.lesswrong.com/posts/L22jhyY9ocXQNLqyE/science-as...

[2] https://www.lesswrong.com/posts/NMoLJuDJEms7Ku9XS/guessing-t...


This is the triboelectric effect, and the low-lying mechanisms are poorly understood & poorly characterized.


Reading https://en.m.wikipedia.org/wiki/Triboelectric_effect , I have the impression the mechanisms are not _that_ poorly understood, at least from my layman's perspective.


It's in the lines:

> The triboelectric effect is very unpredictable, and only broad generalizations can be made.

> The mechanisms of triboelectrification (or contact-electrification) have been debated for many years, with possible mechanisms including electron transfer, ion transfer or the material's species transfer.

> Recent studies in 2018 using Kelvin probe microscopy and triboelectric nanogenerators revealed that electron transfer is the dominant mechanism for triboelectrification between solid and solid.

> For a general case, since triboelectrification occurs for any material, a generic model has been proposed by Wang, in which the electron transfer is caused by a strong electron cloud overlap between two atoms for the lowered interatomic potential barrier by shortening the bonding length.

So, still very much misunderstood. There is an experiment showing the dominant mechanism (so still only explaining a part!) between solid-solid and a generic model proposed that can be used to explain other interactions (solid-liquid, liquid-liquid, etc).

Unless there's a tested model with predictable results, I'd say we're not really understanding it properly.


> So, still very much misunderstood. There is an experiment showing the dominant mechanism (so still only explaining a part!) between solid-solid and a generic model proposed that can be used to explain other interactions (solid-liquid, liquid-liquid, etc).

This seems like a very large part, no?

I mean, we know it works, we get the majority of it, and it doesn’t seem super necessary to spend a lot of dollars and brain power to satisfy an internet debate on a theory of rubbing a balloon on one’s head.


Sorry for my late response. Anyway:

I get your point. However, this is worked on by researchers who get paid to work on unsolved problems. This is one of them. It's a surprising one, since it looks like such a simple and obvious effect governed by physics we've (seemingly) understood for centuries. Gauss's Laws are from 1773 and much of the work on static electricity is from that era.

So, it's not just an internet debate. Knowing how things work _exactly_ is what scientists do. Getting the majority is not good enough.

And yes, that will often surpass the scale of "Is what we're doing useful?". However, won't know until we find out. Most likely understanding this effect will not bring any revolutionary insight but we should understand it nonetheless. Maybe our understanding will help someone else solve a problem, that solves another problem, that solved another problem, that gives someone a brilliant idea.


Maybe there are researchers who want to study the discrepancies of static electricity but if they don’t get funding, then they won’t be paid and have to take other priorities.

Seeming to demand these problems are resolved is a road to cynicism, in my opinion.


At that point why not call it “witchcraft;” a sciencey word for something is not an explanation.


Clearly you've never recalibrated the thermal interferometery scanner so you can reverse the polarity of the neutron flow in the isoneutronic pulse wave carrier.


A good retroencabulator helps a lot here.


You need a plumbus for that.

Everyone need one.


That's technobabble - a pejorative term for a technical word salad that usually is an explanation, just not a very good one.


We do not call it witchcraft, because that is the end of the discussion and the answer. We call it unknown because it is knowable and is the beginning of the experiments.


>We do not call it witchcraft, because that is the end of the discussion and the answer.

Also, we'd have to eliminate the practitioners for clearly being witches. We've had that period and history, but it seems some modern day people are content to bring that very time period back.



Relevant xkcd: https://m.xkcd.com/2682/

And from the alt-text:

"Friction-driven static electrification is familiar and fundamental in daily life, industry, and technology, but its basics have long been unknown and have continually perplexed scientists from ancient Greece to the high-tech era. [...] To date, no single theory can satisfactorily explain this mysterious but fundamental phenomenon." --Eui-Cheol Shin et. al. (2022)


Reminds me of this one https://xkcd.com/1489

"Of these four forces, there's one we don't really understand." "Is it the weak force or the strong--" "It's gravity."


My understanding is that the standard model likely does predict static electricity, but since it's a phenomenon bigger than a few molecules, we have no way to actually run the simulation. The physics is willing but the computers are weak.


This seems incorrect as it’s just an imbalance of charge and isn’t a strange phenomena.

Can you provide a reference, please?


> there are many unexplained effects in solid state physics

Looks like there is plenty of opportunity for newly minted physicists to make their names and careers!


Also there's that whole "worst prediction in the history of physics" thing with the Vacuum Catastrophe.


My favorite poorly understood phenomenon in basic physics is the Mpemba effect, where hot water can freeze faster than cold water under certain circumstances. It's just phase changes of water in a simple experiment you can do at home, and I think there's still no widely accepted explanation.


You might want to find a phenomenon that everyone can agree exists. Failing to explain something that doesn't happen isn't very mysterious.

https://en.wikipedia.org/wiki/Mpemba_effect

> the actual occurrence of the Mpemba effect is a matter of controversy

> In 2016, Burridge and Linden defined the criterion as the time to reach 0 °C (32 °F; 273 K), carried out experiments, and reviewed published work to date. They noted that the large difference originally claimed had not been replicated, and that studies showing a small effect could be influenced by variations in the positioning of thermometers: "We conclude, somewhat sadly, that there is no evidence to support meaningful observations of the Mpemba effect."

> In controlled experiments the effect can entirely be explained by undercooling [water may cool below the freezing point without actually solidifying] and the time of freezing was determined by what container was used.


That's because nobody's replicated that effect in a real lab. People who claimed to observe effect didn't even bother to bypass the freezer thermostat and force the compressor to stay on, nor did they measure power consumption. It's just shoddy science.


which part. how is that not electostatics and van der walls forces?



> there isn't even an accepted explanation for why rubbing a balloon on your head makes it stick to a wall

You mean dielectric moments and static electricity? Electromagnetism is the one thing we know the most about. It's that spooky gravity junk that makes us scratch our heads. It never seems to behave quite right and doesn't mesh with all the other forces.


> You mean dielectric moments and static electricity?

You're confusing what with why. My understanding is that everyone knows it has something to do with electrons collecting on the balloon; but nobody quite knows why rubbing rubber against hair causes the electrons to do that.


Exactly.

Often the gap between what and why is enormous. Humanity began curing meats to protect against microorganisms around 3000BC. The effect of what was going on was immediately observable, but it wasn't until 4500 years or so later that we discovered the why of microorganisms.


I think I got confused because I was thinking about why it stuck to the wall, rather than why it accumulated charge. I know why electrically charged objects stick to things. The why of how they got like that is a bit different as you mentioned. Triboelectric effect is spooky, but there are some theories. It's one of those non-linear messy quantum things that's a pain in the neck to solve.


> It's one of those non-linear messy quantum things that's a pain in the neck to solve.

That is exactly equivalent to "dunno, maybe something".


> That is exactly equivalent to "dunno, maybe something".

Yup! It's like understanding the why of weather and people. They are messy and have so many factors you can't account for. It's like saying, why are the clouds shaped like that. You can why your way down, but it's turtles all the way!

When it comes to non-linear junk, the why becomes mixed up because the causes are so numerous. There are so many tiny interactions you can't really say there is one individual cause. Often times you have phenomena that occur at specific energy levels that aren't really caused by any one thing. Even something as simple as a double pendulum is unpredictable.

One thing that is kind of mind blowing is strange attractors. Systems that are so random you cannot predict them even a few moments later can exhibit seemingly ordered patterns. They seem to have a cause, but they are literally just statistical mechanics. A slightly more likely outcome out of un-countable numbers of other outcomes.


It is entirely possible that global warming could tip us into the next ice age, though probably not in our lifetimes.

First you would need a world-wide cloud layer reflecting insolation back without conversion to IR. As the temperature drops, ice forms. When the clouds dissipate, the ice takes over reflecting sunlight out.


Or it could return us back to the hothouse earth of the cretaceous era. Or it could turn our entire planet into a second Venus with a runaway effect from all the methane. Or it could do almost nothing at all. There is just no way to know because it's never really happened before. We are playing with fire for sure.


There's a joke that calling Computer Science Computer Science is like calling Astronomy Telescope Science, but part of what makes it funny is the ring of truth to it. Our instruments really do limit our observations. The advantage Computer Scientists have is that we can glimpse a world of Platonic Forms[1], where Functions, and Sets, and Information exist, or something close enough for government work, merely through the intellect. Astronomers have no such luxury.

[1] Or whatever circumlocution you prefer to express the same general concept.


Astronomers probably should go on the quest for immortality since otherwise you are basically condemned to look at a still image. Even if that image contains a story from the earliest universe until now. It is a million states, but no real process.

What I find so fascinating is that the observations are still quite precise. How do you know the outer rims are rotating too fast? Couldn't this be some gravitational lensing and stars are actually much closer to the core than they appear?

How do you even begin to estimate the mass of a galaxy? How do you weight the behavior of a disc and combine it with keplers law to even see that something is wrong here? As a layman I would be perfectly happy with how galaxy are rotating... I find it fascinating that much is so precisely determined that we have to miss something.


Computer Science doesn’t get the pass, unfortunately. First of all because it’s a branch of maths, so in reality it doesn’t have any instruments to worry about. Secondly, applied CS relies on an incredibly simple instrument: binary logic gates. The computers we have today are just a mesh of stuff that flips on and off with no intermediate states. That’s pretty primitive as a means of expression and computation compared with the rest of the universe


A lot of people think that computer science is just a branch of maths. But when I was doing my doctorate, I was a computer scientist, and my three supervisors were a mathematician, an engineer, and a meteorologist. The difference between us was much more than the stuff we knew - it was the way that we thought, and therefore approached a problem. Supervision meetings were interesting - it very much felt like four people speaking four different languages.

On a very broad level (and I'll get loads of people disagreeing with this, because both mathematics and computer science divide further into different specialities), mathematics is primarily about proving logical truths, whereas computer science is about managing complexity. That's a massive cognitive difference, even if many of the problems the two fields tackle are the same.


Oh, let me introduce you to metastability ....


Is that computer science or is that physics though?


well a bit of both - if someone hasn't given you the scary meta stability lecture you haven't really done computer science :-)


> The computers we have today are just a mesh of stuff that flips on and off with no intermediate states.

Only when things are working properly and there isn't too much cosmic radiation, interference, strange patterns accessing memory, someone turning on a light…


Fields of science should always be willing to change based upon empirical evidence.

I think there are several other scientific areas where we know less than we ought.

1. The sub-atomic level

2. The cellular level

3. Ocean biology

4. Geology, particularly effects of earthquakes and volcanic activity

5. Weather patterns over time


I feel for the Weather pattern folk. All of the one I have spoken to over the years are pretty cool. They are trying to model an insanely complex system - oh but thanks to global warming they are struggling to make models that work for longer than a few years because it all keeps changing!


If “it all keeps changing”, which thwarts their attempts to “model an insanely complex system”, then wouldn’t that mean any claim about “global warming” is actually a claim to possessing a priori knowledge?


No. That the planet is warming is incontrovertible. What this might mean for highly interdependent, chaotic systems is harder to predict. Will the Greenland ice sheet melt? Looks like yes. Will that affect the Gulf Stream? Probably. Will that make Spain colder? again, probably, but the error bars are bigger, and so on.


It just sounds like global warming is giving them good test data. A comprehensively accurate model should be able to take e.g. a Greenland ice sheet melting in stride.


It's a lot of factors that they didn't even consider in the first place; decades ago, the Greenland ice sheet melting wasn't a consideration. Similar things: The north pole ice cap melting causes less sunlight to be reflected back into space, adding to the warming effect. Or the huge areas of permafrost melting (not so perma now, but for earlier models they would have considered permafrost not an issue), which causes sequestered biomatter to start decomposing and releasing tons of methane.

Forest fires were probably in the model, but they seem to be intensifying due to (mis)management and droughts. The Amazon rainforest probably has a significant impact on weather and weather models, but under Bolsenaro a lot of it was cut down and burned. And it goes on.


No as has already been answered. The example I can directly think of is modelling of specific weather patterns across Australia. A model that works in predicting weather 2 weeks out may work today but not work so well in 5 years.

Global Warming is happening, that is not just a realm of modelling but is directly observable today. The models on a broad scale look to be working very well, specific locations and reactions not so much.

It is possible to make broad engines that work but also get the finer details wrong. Signal : Noise ratio and all of that.


We know very well how carbon dioxide interacts with infrared radiation (easily tested with an IR spectrometer), and we know human activity releases enormous quantities of carbon dioxide into the atmosphere, which does not magically disappear.

Precise predictions are hard, but the general direction of travel cannot be seriously disputed without arguing against the above simple facts.


Carbon dioxide is actually a relatively weak greenhouse gas. At least compared to water vapour, or even methane.

Btw, CO2 does 'magically' disappear. Into the oceans. Alas, from what I've read it'll take about 2,000 years to do so.

> [...], but the general direction of travel cannot be seriously disputed without arguing against the above simple facts.

I don't want to argue against global warming, but I want to argue that can't argue against global warming without arguing against your 'simple facts'.

Your 'simple fact' about CO2 could be true, but global warming could still be a myth. (I don't think it is; but your argument is far from sufficient. It's a complex system. Eg from time to time volcanic eruptions produce a lot of CO2, but they are typically associated with a cooling of the climate, because of other factors.

Similarly, burning coal releases a lot of CO2, but it also used to release a lot of SO2. Locally, SO2 is pretty bad (ever heard of acid rain?), but SO2 converts to sulfuric acid aerosols that can block solar radiation. These days most coal fired power plants have measure to avoid spewing so much SO2.

It's conceivable someone could find a coal so 'dirty' with sulphur, that burning it would decrease temperatures. I don't think it's very likely, but it's conceivable. So you need more empirical observations, than just your simple facts to make your argument.)


I understood their point to be that that based on our understanding of basic physics and chemistry, the energy balance is such that the Earth system is gaining energy, and that this will lead to increased temperatures among other things. Certainly there are all kinds of complexities about how that energy will be distributed and what the effects will be, but just in terms of a simple energy balance model based on well understood physics, it would be difficult to make the case that warming won't happen.


> Certainly there are all kinds of complexities about how that energy will be distributed and what the effects will be, but just in terms of a simple energy balance model based on well understood physics, it would be difficult to make the case that warming won't happen.

There are lots more effects. When lots of volcanoes erupt, we also see more CO2, but we see the climate cool down.

That's because the effect of the CO2 is outweighed by other factors. But exactly that there are lots of factors is my point.


Not in the long run. If CO2 levels are increasing and the energy balance into the Earth system is positive, then the basic physics that the original poster referred to will result in warming. The net energy increase of the system will result in a higher equilibrium temperature.


> Precise predictions are hard, but the general direction of travel cannot be seriously disputed without arguing against the above simple facts.

To add, the predictions re: global warming seem to have been too optimistic, and they were already gloom and doomsaying enough decades ago. I scoffed when I read a headline saying something about a specific glacier being gone in 100 years - I'm sure it'll be much sooner than that.


What are the indicators we have marine biology wrong to the level of the other mentions?


I don't think it is fair to characterize cosmology as not making progress no. Stuff is far away and occluded and hard to measure and see. Each improvement in observation causes a need to refine previous ideas, as expected. There are of course the two big mysteries that have lingered for a long time: Dark Matter and Dark Energy, but other areas of physics have lingering mysteries as well.


I almost had the same reaction, but technically they didn't say anything about cosmology not making progress. It's entirely reasonable to assume a scientifically minded person describing a field as "piling up question marks" means they think it's making a LOT of progress. Imagine a field that answers questions more often than it finds new ones; that'd be a pretty stagnant field to be in.


"Imagine a field that answers questions more often than it finds new ones; that'd be a pretty stagnant field to be in."

Funnily enough, that's what the science community of the ending 19. century thought about physics, before they started to look deeper.

Max Planck was advised against a career in physics, because:

"In this field, almost everything is already discovered, and all that remains is to fill a few holes."

He rather found some more holes.


This is how I understood OP, too. Last time we had a "crisis in physics", it was the early transition from classical physics to quantum mechanics, when some good new ideas had been coinceived of, but trying to reconcile them with the classical way of thinking and with experimental evidence required increasingly convoluted hacks in the models to make it all work - until folks like Heisenberg, Born, Jordan and Dirac found more holistic and clean ways to approach the problem space.

The number of question marks piling up in cosmology does feel similar. It will help to shape new theories that reconcile all this experimental evidence.


Sometimes the questions keep piling up until someone happens up on just the right question. That question itself wouldn't have been thought of except for the thinking of all of the previous unanswered questions. Then the big Eureka!! moment and someone gets a Nobel prize 20 years later.


Nobody says cosmology is not making progress.

People dunk on cosmology because cosmologists have consistently, over decades, insisted, in public, that they knew more than they did, and are continually obliged to abandon what they insisted they knew. If they were more forthright about how much they don't know, they would get less criticism. They have much to learn from the biologists, who know they know practically nothing (even though massively more than you), and are happy to say so.

The health of a branch of science may be read from how eager its researchers are for you to know about what they have no clue about.


>cosmologists have consistently, over decades, insisted, in public, that they knew more than they did

Exactly, and each time the theories are proven wrong, it's explained as a never-ending series of "oddities", yet the theories are never altered in any meaningful way other than ad-hoc additions to explain each "oddity".

At some point there needs to be a reckoning that, for instance, the current theories of star formation are essentially completely wrong.


This is exactly what pushed me away from pursuing cosmology. One of the most important 'discoveries' in cosmology was that of cosmic inflation [1]. The issue is that if you model the big bang, what it creates is nothing like what we see. Regions of space that wouldn't have had time to have become causally connected (nothing could have gotten between them even traveling at the speed of light since the time of the big bang) are causally connected.

So the solution? There was some very specific period of acceleration, faster than light acceleration to some very specific degree, at some specific point right after the big bang which then ended at some other very specific point, at which point everything returns back to normal. What's the logic for it? Well if we do this, then what we see matches what we expect to see. It's an absolute retrofitting of numbers to make a model fit reality. And not only does that constitute good science in cosmology, it was sufficient to win a Nobel Prize.

It is literally unexplained magic being taken as a fundamental concept of science. And the worst part of it all is that it's completely unfalsifiable. We only have one universe to observe. So if it turns out that the discrepancy is actually being caused by many smaller effects we stand near 0 chance of ever discovering because each one of those small effects will have a million flaws, while the perfectly retrofitted inflation theory has "none." At worst they'll even get absorbed into the inflation theory model magic. Just add more epicycles!

[1] - https://en.wikipedia.org/wiki/Inflation_(cosmology)


> It's an absolute retrofitting of numbers to make a model fit reality.

That's just called science. What else do you propose? Give up because you didn't get it right the first time?


It is one thing to identify a mechanism and show how in operation it must produce the numbers seen. It is entirely different to invent a name for a presumed mechanism, with no hint of how it happened to come to the numbers seen.


Galaxy formation, anyway, or maybe galaxy supercluster formation.


The simulation gets less cohesive the farther from earth you look.


I was just thinking about video games where vegetation, animals, and hills spring into existence when you get close enough. Far away, and they don't bother to render the little things.

Depending what generation tech we're running on in the parent reality, JWST may be causing a noticeable jump in system load.


I had the same idea about magic. Back in the day people could do things that we can’t because nobody looked into details and the universe had enough “possibility space” to allow it. Once you turn your gaze into atomic or galactic workings, this space shrinks tremendously and further research becomes much harder because you glued the puzzle from its sides in a particular way and there’s not much left to hope for, except for solving it to the center in a bizarrely complex way. We may have painted ourselves into a horrible corner.


This is an excellent sci-fi premise. Also an interesting thought experiment to think of what an optimal research approach would be if you knew a priori that you were living in a universe in which the implementation details don’t exist until observed. Come to think of it, quantum physics is actually like this in some respects.


Whatever JWST can see should be trivial to convincingly mock compared to the complexity of simulation of the scenes here on Earth.


And now you have come to the reason GPU prices have been so high. Crypto was just a cover story.


It is a v0.93 of simulation, which was run a long time ago. Software was patched since and now simulation is much smoother.


It may be more a question of a new generation of physicists, willing to consider that particle dark matter is not the explanation for the acceleration discrepancy.


Sadly, I'm to the point that unless we call it the Kardashian Space Telescope, the draw to new generations will not be there. We're closer to Idiocracy future than Interstellar future.


I think you're overly generalizing, I don't believe today's generation is much different from previous generations when it comes to interest in STEM and the like. Sure, their attention spans are different - I mean "ours" are due to the advent of the internet etc - but I don't believe their ambitions are that much different. It's just that they want to become youtubers instead of movie stars / musicians.


There is the esoteric "Cosmological Natural Selection" theory that predicts the discrepancies. This guy at https://theeggandtherock.substack.com/archive explains his version of this theory (albeit in an emotional way) that I find a pleasant read.


It's an amazing theory that I now share.

F R A C T A L H A T C H E R Y


Would you bet that we'll see a paradigm shift of a similar nature to the classical physics -> quantum mechanics / relativity paradigm change, but for Cosmology in our lifetimes?


The answer to that will highly depend on how old you and the GP are.


Yes, we are in the middle of a huge shift in the definition of intelligence. AND that could have enormous impact on our perception and ability to see reality.


I always wondered if we could somehow get a James webb telescope revolving around all planets of our solar system in the next 1000 years. That should give us pretty awesome visuals.


Huh, why would you want to do that?

If you have the resources to spare, you can do much better than replicating James Webb style telescopes. See eg https://en.wikipedia.org/wiki/Solar_gravitational_lens


I want to venture that 1000 years is pessimistic. I just hope governments or private entities open up their wallets to build and launch more and better telescopes.

I'm reading the whole JWST project is estimated to cost $10 billion. That's about 4.4 overpriced Twitters, 77 US Department of Defense budgets (just for 2023), and 11.7 Facebook annual revenues.

We have the technology and the means, what's lacking now is the will.


Your maths is upside down, I think. $10 billion is 10/44 ≈ 0.227 overpriced Twitters, 10/816.7 ≈ 0.0122 US DoD budgets, etc.


What would be the benefit of the telescope orbiting other planets than earth?


There's definitely a benefit to placing a decent telescope outside the asteroid belt. From Earth, we get a lot of light reflected from the Sun from dust orbiting somewhere between Earth and 2 AU from the Sun, which pollutes our space images - it's called the Zodiacal Light [0]. A telescope outside this light pollution would be able to see faint objects much more clearly and easily than Webb.

[0] https://en.wikipedia.org/wiki/Zodiacal_light


I can't imagine any, besides redundancy and more observation time.


Interferometry.


Everyone knows that general relativity is broken.

Plus cosmology has the problem that you can't really conduct reproducible experiments.


not surprising imo, because of how limited our observational capabilities are. we'd probably progress quicker if we could look at far away stuff up close instead of from billions of light years away.


The number of possibilities are countably infinite. Makes sense that we will keep finding things we don't understand for a long time.


> It the pattern of previous science revolutions repeats, there could come a point where reinterpreting the large existing body of knowledge using a different paradigm would explain an number of "oddities" in a more economical way.

Could we train a GPT3 like model with the entire corpus of astronomical research and try to answer some questions that way?


Already done. They came back with the answer: "42"


You're really not going to like it


But what was really the question?


ChatGPT-3: What do you get if you multiply six by nine?

ChatGPT-4: How many roads must a man walk down?


"What is the Matrix?"


Mu.


They haven’t but they will


GPT3 cant even play tic tac toe properly (at least in my attempts). What makes you believe it can build and manipulate a model of the universe, and then answer questions about that model in a way that goes beyond what humans can do?


I'd say not a chance.

GPT3 can regurgitate, and, in my opinion, even use knowledge, but I don't think it can synthesize knowledge.


I think it's a bit more subtle than whether it can synthesize, because clearly it can produce seemingly new work.

But what it definitely cannot do is seek new abstractions. It can't be curious about an inconsistency and probe its own knowledge for possible resolutions, or design an experiment that might shed further light in an unknown area. It can't even play a board game after ingesting the rules to it, much less identify contradictions or problems in such a ruleset. And a board game is a tiny microcosm compared with the laws of physics.

It's conceivable that one or more scientists could work in conjunction with an AI to help augment their own abilities, co-pilot style, but I don't think we have a picture yet of what exactly that kind of thing would look like.


I kind of feel like _all it can do_ is seek new abstractions. It’s clustering the data into what you might think of as “concepts,” even though we haven’t made all that much progress on interrogating those concepts directly. I just think clustering concepts by their latent relationships is sort of what abstraction is.


Hmm, interesting. I feel like that clustering/grouping part is like... the first stage on the way to finding an abstraction, but if all you've done is that part of it, then you haven't reasoned about what the abstraction is, or extrapolated out to a new hypothesis, or grappled with the other consequences of the grouping.

Thinking of mathematics, an abstraction is only as valuable as what it can tell us about the underlying system— a laplace transformation into the frequency domain isn't particularly interesting unless we either a) happen to care about some frequency domain property of the function, or b) we can manipulate the transformed function and then un-transform it afterward, yielding a novel insight in the original time domain.

My layman's assessment is that the current state of the art for machine cognition is about on the level of identifying that such a transformation might be possible, but not actually applying it or doing anything about it, much less unapplying it afterward.


I think I get the gist of your point which I would handwavily summarize as “there is no there there,” which I agree with. But I’m thinking that in terms of functionality, there is no real distinction here. Like If I train a model to do video game physics, and reward it for getting the tank shell missile to land on arbitrary targets, then in some sense the system must have an abstraction of gravity or at least parabolic movement or at least a functional equivalent of that, and it must be able to “hypothesize” about the consequences of its model because that’s what it needs to do in order to hit the target, ie, “everything I’ve seen before leads me to believe tank missiles move like so, therefore if I apply the following forces, it should hit the goal”—the degree to which it wins at this task is exactly the degree to which it can form working models of its environment and reason about the cause and effect of the actions it can take. But of course all those words in the previous sentence are wrong because it’s not exactly doing any of that, just something functionally equivalent and automatic.

Maybe we disagree about whether that last point means it can meaningfully “do abstraction” or not.


well, you could. And it might not be a complete waste of time. I would not expect any directly useful answers(...). But producing a semi-random collation of sentences that spans the corpus of cosmological facts and models and asking scientists to review / draw "inspiration" from it might remove some of the biases of the average cosmologist (like having to follow the latest publish-or-perish fad). This would only be useful if the answer is sort of hidding in plain sight (within the published stuff) and you tweak the algorithm not to ignore weird observations or theories that are not cited a lot.

But the beauty of science (and the human mind driving it) that important progress happens with creative jumps that invent completely new things (e.g., new mathematics) and frequently bear little resemblance to the past


If you give GPT3 code with a bug in it, and ask it to find the bug, it can't really do that. I'm pretty sure giving it all the data and asking it why things aren't working the way it should, it wouldn't have actual knowledge.

There's a depth to explaining things that GPT still can't do. It's still astonishing, and has completely changed my idea on what AI can do, like write plays with very incredible context (better than most humans!) but there are still major limits.


>If you give GPT3 code with a bug in it, and ask it to find the bug, it can't really do that.

The hell are you talking about? I've been doing this literally any time I need something fixed and it does just fine.


It doesn’t solve non-trivial bugs. It can bugs that match patterns that have been asked a lot if Stackoverflow or something like that.


I love the sound of goal posts as they go whooshing past.


I think it's more likely a problem that the GP poorly worded their initial statement, rather than actually moving the goalposts. They were probably having trouble with a few thorny bugs, tried ChatGPT, got nowhere, and forgot to qualify their initial statement with "for the few non-trivial bugs I tried".

From the external point of view, the goalposts moved, but from within the GP's poorly expressed mental model, they haven't moved. But, that's just a guess.


It can definitely find and fix bugs. Of course it's not great at it and cannot be relied upon.


FWIW, I've tried asking ChatGPT to walk through some thought experiments.

Things like, what happens if I shoot two bullet at c/2 in opposite directions on a train going at c/2? Now suppose, I'm an outside observer. And then trying to introduce quantum gravity.

My thought was that perhaps it could 'reason through'. Unfortunately, it was unable to. Eventually, it said that this is an unsolved problem. In other words, it 'recognized' the thought experiments. Perhaps if you use a phrasing that's not in the literature.

EDIT: Actually, just checked again, and chatgpt can't reason through relativity anymore:

Me: Imagine I'm on a train traveling at half the speed of light. I'm in the middle of a car and I fire bullets going at half the speed of light towards the front and back of the car. Do the bullets arrive at the front and back of the car at the same time?

ChatGPT: No, the bullet fired towards the front of the car will arrive at the front of the car first, while the bullet fired towards the back of the car will arrive at the back of the car later. This is because the front bullet is moving in the same direction as the train and the back bullet is moving in the opposite direction of the train. The relative velocity of the bullet and train will determine the time it takes for the bullet to reach the front or back of the car.


It is going to be like a drunk Michael Ross (the fictional character). I.e. great memory but too drunk to think beyond what can be recalled. If it’s corpus has the answer it will shit it out.


I think chatbots can probably answer known things, but we'll still need smart humans for original ideas.

That said, I can imagine a chatbot can help as a rubber duck, bring up things that weren't considered yet, or be so wrong as to kickstart the human into a breakthrough.


The article mentions that they're training neural networks to classify these objects. Give it a decade and this kind of high level number crunching will be as common as calculators are today. Transformers will find their place in all of this, and I am confident we will have a breakthrough in a few years regarding novel synthesis.




Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: