That’s why I have to get ahead of it by explaining why physics models work in many universes and how that means we should be unsurprised when we can make them work on practically anything.
I’m not optimistic that it will help stop the war, but it might save some people.
We could just as easily say that physically pushing on things is not a force. My intuitive explanation would no longer make any sense, but that’s a problem with humans, not the law.
We live in this universe. We could solve this issue by saying that there is “etheric drag” or something which provides a resistive force against fast-moving objects, but I’m glad we invented special relativity instead.
This is a problem with the theory of mass as I presented it in the intuitive section, but you could solve it by saying that the composite object has a quarter of the mass of each of the two objects you stuck together. Maybe you live in a universe where objects with mass have total mass . This is a better universe than one where you have to measure the mass of any object including composite objects each time. Newton’s second law can be used to retroactively define masses based off of experiment, but it’s nicer to live in a universe where masses are more predictable than that.
I’m pointing out that Newton’s second law is tautologically correct as a formal theory. It’s true that it aligns particularly well with human conceptions of manipulating objects in space. It’s true that it works particularly well in our universe. (We only had to define one omnipresent force with a simple inverse-square form that only depends on one free-but-set-by-experiment parameter G to make momentum be conserved for most objects that don’t look like they’re interacting with anything.)
My point is that the mass is constant no matter what you do. Sometimes that’s not true. Cars lose mass over time because the gasoline is burned and lost via the tailpipe.
In hindsight, I should have just said that we’re pretty sure that there are no macroscopic objects with zero mass. What’s an object that you can push on but has no stuff in it?
I consider the lattice to be a regulator as well, but, semantics aside, thank you for the example.
Field theorist here. You talk about renormalization as a thing which can smooth over unimportant noise, which basically matches my understanding, but you haven’t explicitly named your regulator. A regulator may be a useful concept to have in interpretability, but I have no idea if it is common in the literature.
In QFT, our issue is that we go to calculate things that are measurable and finite, but we calculate horrible infinities. Obviously those horrible infinities don’t match reality, and they often seem to be coming from some particular thing we don’t care about that much in our theory, so we find a way to poke it out of the theory. (To be clear, this means that our theories are wrong, and we’re going to modify them until they work.) The tool by which you remove irrelevant things which cause divergences is called a regulator. A typical regulator is a momentum cutoff. You go to do the integral over all real momenta which your Feynman diagram demands, and you find that it’s infinite, but if you only integrate the momenta up to a certain value, the integral is finite. Of course, now you have a bunch of weird constants sitting around which depend of the value of the cutoff. This is where renormalization comes in. You notice that there are a bunch of parameters, which are generally coupling constants, and these parameters have unknown values which you have to go out into the universe and measure. If you cleverly redefine those constants to be some “bare constant” added to a “correction” which depends on the cutoff, you can do your cutoff integral and set the “correction” to be equal to whatever it needs to be to get rid of all the terms which depend on your cutoff. (edit for clarity: This is the thing that I refer to when I say “renormalization.” Cleverly redefining bare parameters to get rid of unphysical effects of a regulator.) By this two step dance, you have taken your theoretical uncertainty about what happens at high momenta and found a way to wrap it up in the values of your coupling constants, which are the free parameters which you go and measure in the universe anyway. Of course, now your coupling constants are different if you choose a different regulator or a different renormalization scheme to remove it, but physicists have gotten used to that.
So you can’t just renormalize, you need to define a regulator first. You can even justify your regulator. It is a typical justification for a momentum cutoff that you’re using a perturbative theory which is only valid at low energy scales. So what’s the regulator for AI interpretability? Why are you justified in regulating in this way? It seems like you might be pointing at regulators when you talk about 1/w and d/w, but you might also be talking about orders in a perturbation expansion, which is a different thing entirely.
A decision-theoretic case for a land value tax.
You can basically only take income tax by threatening people. “Give me 40% of your earnings or I put you in prison.” It is the nicest type of threatening! Stable governments have a stellar reputation for only doing it once per year and otherwise not escalating the extortion. You gain benefit from the stable civilization supported by such stable governments because they use your taxes to pay for it. But there’s no reason for the government to put you in prison except for the fact that they expect you to give them money not to. By participating, you are showing that you will respond to threats, which is an incentive to extract more wealth from you. If enough people understood decision theory and were dissatisfied by the uses the government put their money to, they could refuse to pay and the prison system wouldn’t be big enough to deal with it. Oops, it’s time to overthrow the government.
Under a better land value tax, the consequence for not paying your taxes is that the government takes the land away and gives it to someone else. They aren’t threatening you, they’re just reassigning their commitment to protect the interests of the person who uses the land over to a user who will pay them for the service. Of course, people can still all refuse to do it if they don’t like the uses to which government puts their money, and from the point of view of the person paying taxes, it’s still pretty much a case of “pay up or something bad will happen to you,” so some would argue that the difference is mostly academic. That said, I really prefer to have a government which does not have “devise ways to make people miserable for the purpose of making them miserable” (you know, prison as a threat) as a load-bearing element of its mechanisms of perpetuating itself.
This argument flagrantly stolen from planecrash: https://www.projectlawful.com/replies/1721794#reply-1721794 Of course planecrash also offers an argument for what gives a hypothetical government the right to claim ownership for the land: https://www.projectlawful.com/replies/1773744#reply-1773744 I was inspired to write this by Richard Ngo’s definition of unconditional love at https://x.com/richardmcngo/status/1872107000479568321 and the context of that post.
I think your point has some merit in the world where AI is useful and intelligent enough to overcome the sticky social pressure to employ humans but hasn’t killed us all yet. That said, I think AI will most likely kill us all in that 1-5 year window after becoming cheaper, faster, and more reliable than humans at most economic activity, and I think you have to convince me that I’m wrong about that before I start worrying about humans not hiring me because AI is smarter than I am. However I want to complain about this particular point you made because I don’t think it’s literally true:
Powerful actors don’t care about you out of the goodness of their heart.
One of the reasons why AI alignment is harder than people think, is because they say stuff like this and think AI doesn’t care about people in the way that powerful actors don’t care about people. This is generally not true. You cannot in general pay a legislator $400 to kill a person who pays no taxes and doesn’t vote. That is impressive when you think about it. You can argue that they fear reputational damages or going to prison, but I truly think that if you took away the consequences, $400 would not be enough money to make most legislators overcome their distaste for killing another human being with their bare hands. Some of them really truly want to make society better, even if they aren’t very effective at it. Call it noblesse oblige if you want, but it’s in their utility function to do things which aren’t just give the state more money or gain more personal power. The people who steer large organizations have goodness in their hearts, however little, and thus the organizations they steer do too, even if only a little. Moloch hasn’t won yet. America the state is willing to let a lot of elderly people rot, but America wasn’t in fact willing to let Covid rip, even though that might have stopped the collapse of many tax-generating businesses, and most people who generate taxes would have survived. I don’t think that’s because the elderly people who overwhelmingly would have been killed by that are an important voting constituency for the party which pushed hardest for lockdown.
AI which knows it won’t get caught and literally only cares about tax revenue and power will absolutely kill anyone who isn’t useful to them for $400. That’s $399 worth of power they didn’t have before if killing someone costs $1 of attention. I don’t particularly want to live in a world where 1% percent of people are very wealthy and everyone else is dying of poverty because they’ve been replaced by AI, but that’s a better world than the one I expect where literally every human is killed because, for example, those so-called “reliable” AIs doing all of the work humans used to do as of yesterday liked paperclips more than we thought and start making them today.
Thank you. As a physicist, I wish I had an easy way to find papers which say “I tried this kind of obvious thing you might be considering and nothing interesting happened.”
My current job is only offered to me on the condition that I am doing physics research. I have some flexibility to do other things at the same time though. The insights and resources you list seem useful to me, so thank you.
I am a physics PhD student. I study field theory. I have a list of projects I’ve thrown myself at with inadequate technical background (to start with) and figured out. I’ve convinced a bunch of people at a research institute that they should keep giving me money to solve physics problems. I’ve been following LessWrong with interest for years. I think that AI is going to kill us all, and would prefer to live for longer if I can pull it off. So what do I do to see if I have anything to contribute to alignment research? Maybe I’m flattering myself here, but I sound like I might be a person of interest for people who care about the pipeline. I don’t feel like a great candidate because I don’t have any concrete ideas for AI research topics to chase down, but it sure seems like I might start having ideas if I worked on the problem with somebody for a bit. I’m apparently very ok with being an underpaid gopher to someone with grand theoretical ambitions while I learn the material necessary to come up with my own ideas. My only lead to go on is “go look for something interesting in MATS and apply to it” but that sounds like a great way to end up doing streetlight research because I don’t understand the field. Ideally, I guess I would have whatever spark makes people dive into technical research in a pretty low-status field for no money for long enough to produce good enough research which convinces people to pay their rent while they keep doing more, but apparently the field can’t find enough of those that it’s unwilling to look for other options.
I know what to do to keep doing physics research. My TA assignment effectively means that I have a part-time job teaching teenagers how to use Newton’s laws so I can spend twenty or thirty hours a week coding up quark models. I did well on a bunch of exams to convince an institution that I am capable of the technical work required to do research (and, to be fair, I provide them with 15 hours per week of below-market-rate intellectual labor which they can leverage into tuition that more than pays my salary), so now I have a lot of flexibility to just drift around learning about physics I find interesting while they pay my rent. If someone else is willing to throw 30,000 dollars per year at me to think deeply about AI and get nowhere instead of thinking deeply about field theory to get nowhere, I am not aware of them. Obviously the incentives are perverse to just go around throwing money at people who might be good at AI research, so I’m not surprised that I’ve only found one potential money spigot for AI research, but I had so many to choose from for physics.
The simulation is not reality, so it can have hidden variables, it just can’t simulate in-system observers knowing about the hidden variables. I think quantum mechanics experiments should still have the same observed results within the system as long as you use the right probability distributions over on-site interactions. You could track Everett branches if you want to have many possible worlds, but the idea is just to get one plausible world, so it’s not relevant to the thought experiment.
The point is that I have every reason to believe that a single-level ruleset could produce a map which all of our other maps could align with to the same degree as the actual territory. I agree that my approach is reductionist. I’m not ready to comment on LDSL
From the inside, it feels like I want to know what’s going on as a terminal value. I have often compared my desire to study physics to my desire to understand how computers work. I was never satisfied by the “it’s just ones and zeros” explanation, which is not incorrect, but also doesn’t help me understand why this object is able to turn code into programs. I needed to have examples of how you can build logic gates into adders and so on and have the tiers of abstraction that go from adders, etc to CPU instructions to compilers to applications, and I had a nagging confusion about using computers for years until I understood that chain at least a little bit. There is a satisfaction which comes with the dissolution of that nagging confusion which I refer to as joy.
There’s a lot to complain about when it comes to public education in the United States, but I at least felt like I got a good set of abstractions with which to explain my existence, which was a chain that went roughly Newtonian mechanics on top of organs on top of cells on top of proteins on top of DNA on top of chemistry on top of electromagnetism and quantum mechanics, the latter of which wasn’t explained at all. I studied physics in college, and the only things I got out of it were a new toolset and an intuitive understanding for how magnets work. In graduate school, I actually completed the chain of atoms on top of standard model on top of field theory on top of quantum mechanics in a way that felt satisfying. Now I have a few hanging threads, which include that I understand how matter is built out of fields on top of spacetime, but I don’t understand what spacetime actually is, and also the universe is full of dark matter which I don’t have an explanation for.
I’m putting in my reaction to your original comment as I remember it in case it provides useful data for you. Please do not search for subtext or take this as a request for any sort of response; I’m just giving data at the risk of oversharing because I wonder if my reaction is at all indicative of the people downvoting.
I thought about downvoting because your comment seemed mean-spirited. I think the copypasta format and possibly the flippant use of an LLM made me defensive. I mostly decided I was mistaken about it being mean spirited because I don’t think that you would post a mean comment on a post like this based on my limited-but-nonzero interaction with you. At that point, I either couldn’t see what mixing epistemology in with the pale blue dot speech added to the discussion, or it didn’t resonate with me, so I stopped thinking about it and left the comment alone.
I think I see what you’re saying, let me try to restate it:
If the result you are predicting is course-grained enough, then there exist models which give a single prediction with probability so close to one that you might as well just take the model as truth.
I appreciate your link to your posts on Linear Diffusion of Sparse Lognormals. I’ll take a look later. My responses to your other points are essentially reductionist arguments, so I suspect that’s a crux.
That said, I’m using “quantum mechanics” to mean “some generalization of the standard model” in many places. In practice, the actual experimental predictions of the standard model are something like probability distributions over the starting and ending momentum states of particles before and after they interact at the same place at the same time, so I don’t think you can actually run a raw standard model simulation of the solar system which makes sense at all. To make my argument more explicit, I think you could run a lattice simulation of the solar system far above the Planck scale and full of classical particles (with proper masses and proper charges under the standard model) which all interact via general relativity, so at each time slice you move each particle to a new lattice site based on its classical momentum and the gravitational field in the previous time slice. Then you run the standard model at each lattice site which has more than one particle on it to destroy all of the input particles and generate a new set of particles according to the probabilistic predictions of the standard model, and the identities and momenta of the output particles according to a sample of that probability distribution will be applied in the next time slice. I might be making an obvious particle physics mistake, but modulo my own carelessness, almost all lattice sites would have nothing on them, many would have photons, some would have three quarks, fewer would have an electron on them, and some tiny, tiny fraction would have anything else. If you interpreted sets of sites containing the right number of up and down quarks as nucleons, interpreted those nucleons as atoms, used nearby electrons to recognize molecules, interpreted those molecules as objects or substances doing whatever they do in higher levels of abstraction, and sort of ignored anything else until it reached a stable state, then I think you would get a familiar world out of it if you had the utterly unobtainable computing power to do so.
In what way? I find myself disagreeing vehemently, so I would appreciate an example.
Maps are territory in the sense that the territory is the substrate on which minds with maps run, but one of my main points here is that our experience is all map, and I don’t think any human has ever had a map which remotely resembles the substrate on which we all run.
This is tangential to what I’m saying, but it points at something that inspired me to write this post. Eliezer Yudkowsky says things like the universe is just quarks, and people say “ah, but this one detail of the quark model is wrong/incomplete” as if it changes his argument when it doesn’t. His point, so far as I understand it, is that the universe runs on a single layer somewhere, and higher-level abstractions are useful to the extent that they reflect reality. Maybe you change your theories later so that you need to replace all of his “quark” and “quantum mechanics” words with something else, but the point still stands about the relationship between higher-level abstractions and reality.
I’m not sure I understand your objection, but I will write a response that addresses it. I suspect we are in agreement about many things. The point of my quantum mechanics model is not to model the world, it is to model the rules of reality which the world runs on. Quantum mechanics isn’t computationally intractable, but making quantum mechanical systems at large scales is. That is a statement about the amount of compute we have, not about quantum mechanics. We have every reason to believe that if we simulated a spacetime background which ran on general relativity and threw a bunch of quarks and electrons into it which run on the standard model and start in a (somehow) known state of the Earth, Moon, and Sun, then we would end up with a simulation which gives a plausible world-line for Earth. The history would diverge from reality due to things we left out (some things rely on navigation by starlight, cosmic rays from beyond the solar system cause bit flips which affect history, asteroid collisions have notable effects on Earth, gravitational effects from other planets probably have some effect on the ocean, etc.) and we would have to either run every Everett branch or constantly keep only one of them at random and accept slight divergences due to that. In spite of that, the simulation should produce a totally plausible Earth, although people would wonder where all the starts went. There do not exist enough atoms on Earth to build a computer which could actually simulate that, but that isn’t a weakness in the ability of the model to explain the base-level of reality.
It may be that generating horrible counterfactual lines of thought for the purpose of rejecting them is necessary for getting better outcomes. To the extent that you have a real dichotomy here, I would say that the input/output mapping is the thing that matters. I want all humans to not end up worse off for inventing AI.
That said, humans may end up worse off by our own metrics if we make AI that is itself suffering terribly based off of its internal computation or it is generating ancestor torture simulations or something. Technically that is an alignment issue, although I worry that most humans won’t care if the AI is suffering if they don’t have to look at it suffer and it generates outputs that humans like aside from that hidden detail.
I’m doing a physics PhD, and you’re making me feel better about my coding practices. I appreciate your explicit example as well, as I’m interested in trying my hand at ML research and curious about what it looks like in terms of toolsets and typical sort-of-thing-one-works-on. I want to chime in down here in the comments to assure people that at least one horrible coder in a field which has nothing to do with machine learning (most of the time) thinks that the sentiment of this post is true. I admit that I’m biased by having very little formal CS training, so proper functional programming is more difficult for me than writing whatever has worked for me in the past writing ad-hoc Bash scripts. My sister is a professional software developer, and she winces horribly at my code. However, you point out that it is often the case that any particular piece of research code you are running has a particular linear set of tasks to achieve, and so:
You don’t need to worry much about resilient code which handles weird edge cases.
It is often better to have everything in one place where you can see it than to have a bunch of broken up functions scattered across a folder full of files.
Nobody else will need to use the code later, including yourself, so legibility is less important
As an example of the Good/Good-enough divide, here’s a project I’m working on. I’m doing something which requires speed, so I’m using c++ code built on top of old code someone else wrote. I’m extremely happy that the previous researcher did not follow your advice, at least when they cleaned up the code for publishing, because it makes life easier for me to have most of the mechanics of my code hidden away out of view. Their code defines a bunch of custom types which rather intuitively match certain physical objects. They wrote a function which parses arg files so that you don’t need to recompile the code to rerun a calculation with different physical parameters. Then there’s my code which uses all of that machinery: My main function that I have written is sort of obviously a nest of loops over discrete tasks which could easily be separate functions, but I just throw them all together into one file, and I rewrite the whole file for different research questions so I have a pile of “main” files which reuse a ton of structure. As an example of a really ugly thing I did, I hard-code indices corresponding to momenta I want to study into the front of my program instead of making a function which parses momenta and providing an argument file listing the sets I want. I might have done that for the sake of prettiness, but I needed to provide a structure which lets me easily find momenta of opposite parity. Hard-coding the momenta let me keep the structure I was using at front of mind when I created the four other subtasks in the code which exploited that structure to let me construct subtasks which needed to easily find objects of opposite parity.
I agree that there are counterfactual frameworks which require more complication to describe reality than Newton’s second law does. There are also counterfactual realities for which Newton’s second law would require more complications to work than other frameworks would. Are you trying to say anything else?
One way to restate my point is that Newton’s second law working well rules out many fundamental rules which might have described our reality, but it doesn’t directly map to any fundamental rules of reality. The larger point which I am trying to communicate is that physical models have a lot of structure which metaphorically defines terms which you can use to describe reality without actually mapping to anything in reality[1]. The theory as a whole doesn’t describe reality without those parts, but those parts don’t necessarily directly correspond to something in reality. A map describes reality, but latitude and longitude lines do not directly correspond to anything in reality even if you can stand at a place in reality and unambiguously use latitude and longitude lines to describe your location using the map. I can use an English sentence to describe the fundamental rules of reality, but the linguistic syntax of that sentence doesn’t correspond to anything fundamental in reality even if it is fundamental to mapping the sentence as a whole to fundamental rules of reality. My physics education presented physical models as package deals with every component corresponding to some intuition about reality, and that led me to confuse map and territory in ways that I wish I had been warned about. I am trying to warn others.
I don’t know whether I am successfully communicating the thing which I am trying to communicate, and I am open to being told that I am wrong.