I thought OpenAI was more about open sourcing deep learning algorithms and ensuring that a couple of rich companies/individuals weren’t the only ones with access to the most current techniques. I could be wrong, but from what I understand OpenAI was never about AI safety issues as much as balancing power. Like, instead of building Jurassic Park safely, it let anyone grow a dinosaur in their own home.
denimalpaca
Everyone has different ideas of what a “perfectly” or “near perfectly” simulated universe would look like, I was trying to go off of Douglas’s idea of it, where I think the boundary errors would have effect.
I still don’t see how rewinding would be interference; I imagine interference would be that some part of the “above ours” universe gets inside this one, say if you had some particle with quantum entanglement spanning across the universes (although it would really also just be in the “above ours” universe because it would have to be a superset of our universe, it’s just also a particle that we can observe).
I 100% agree that a “perfect simulation” and a non-simulation are essentially the same, noting Lumifer’s comment that our programmer(s) are gods by another name in the case of simulation.
My comment is really about your second paragraph, how likely are we to see an imperfection? My reasoning about error propagation in an imperfect simulation would imply a fairly high probability of us seeing an error eventually. This is assuming that we are a near-perfect simulation of the universe “above” ours, with “perfect” simulation being done at small scales around conscious observers.
So I’m not really sure if you just didn’t understand what I’m getting at, because we seem to agree, and you just explained back to me what I was saying.
An idea I keep coming back to that would imply we reject the idea of being in a simulation is the fact that the laws of physics remain the same no matter your reference point nor place in the universe.
You give the example of a conscious observer recognizing an anomaly, and the simulation runner rewinds time to fix this problem. By only re-running the simulation within that observer’s time cone, the simulation may have strange new behavior at the edge of that time cone, propagating an error. I don’t think that the error can be recovered so much as moved when dealing with lower resolution simulations.
It makes the most sense to me, that if we are in a simulation it be a “perfect” simulation in that the most foundational forces and quantum effects are simulated all the time, because they are all in a way interacting with each other all the time.
Go read a textbook on AI. You clearly do not understand utility functions.
My definition of utility function is one commonly used in AI. It is a mapping of states to a real number: u:E → R where u is a state in E (the set of all possible states), and R is the reals in one dimension.
What definition are you using? I don’t think we can have a productive conversation until we both understand each other’s definitions.
I tried to see if anyone else had previously made my argument (but better); instead I found these arguments:
http://rationalwiki.org/wiki/Simulated_reality#Feasibility
I think the feasibility argument described here better encapsulates what I’m trying to get at, and I’ll defer to this argument until I can better (more mathematically) state mine.
“Yet the number of interactions required to make such a “perfect” simulation are vast, and in some cases require an infinite number of functions operating on each other to describe. Perhaps the only way to solve this would be to assume “simulation” is an analogy for how the universe (operating under the laws of quantum mechanics) acts like a quantum computer—and therefore it can “calculate” itself. But then, that doesn’t really say the same thing as “we exist in someone else’s simulation”.” (from the link).
This conclusion about the universe “simulating itself” is really what I’m trying to get at. That it would take the same amount of energy to simulate the universe as there is energy in the universe, so that a “self-simulating universe” is the most likely conclusion, which is of course just a base universe.
Let me be a little more clear. Let’s assume that we’re in a simulation, and that the parent universe hosting ours is the top level (for whatever reason, this is just to avoid turtles all the way down). We know that we can harness the energy of the sun, because not only do plants utilize that energy to metabolize, but we also can harness that energy and use it as electricity; energy can transfer.
Some machine that we’re being simulated on must take into account these kinds of interactions and make them happen in some way. The machine must represent the sun in some way, perhaps as 0s and 1s. This encoding takes energy, and if we were to simply encode all the energy of the sun, the potential energy of the sun must exist somewhere in that machine. Even if the sun’s information is compressed, it would still have to be decompressed when used (or else we have a “lossy” sun, not good if you don’t want your simulations to figure out they’re in a simulation) - and compressing/decompressing takes energy.
We know that even in a perfect simulation, the sun must have the same amount of energy as outside the simulation, otherwise it is not a perfect simulation. So if a blue photon has twice as much energy as a red photon, then that fact is what causes twice as much energy to be encoded in a simulated blue photon. This energy encoding is necessary if/when the blue photon interacts with something.
Said another way: If, in our simulation, we encode the energy of physical things with the smallest number of bits possible to describe that thing, and blue photons have twice as much energy as red photons, then it should take X bits to describe the energy of the red photon and 2*X bits to describe the blue photon.
As to extra energy, as a practical (engineering) matter alone it would take more energy to simulate a thing even after the encoding for the thing is done: in our universe, there are no perfect energy transfers, some is inevitably lost as heat, so it would take extra energy to overcome this loss. Secondly, if the simulation had any meta-data, that would take extra information and hence extra energy.
Yes, then I’m arguing that case 1 cannot happen. Although I find it a little tediously tautological (and even more so reductive) to define technological maturity as being solely the technology that makes this disjunction make sense....
“(1) civilizations like ours tend to self-destruct before reaching technological maturity, (2) civilizations like ours tend to reach technological maturity but refrain from running a large number of ancestral simulations, or (3) we are almost certainly in a simulation.”
Case 2 seems far, far more likely than case 3, and without a much more specific definition of “technological maturity”, I can’t make any statement on 1. Why does case 2 seem more likely than 3?
Energy. If we are to run an ancestral simulation that even remotely wants to correctly simulate as complex phenomenon as weather, we would probably need the scale of the simulation to be quite large. We would definitely need to simulate the entire earth, moon, and sun, as the physical relationships between these three are very intertwined. Now, let’s focus on the sun for a second, because it should provide us with all the evidence we need that a simulation would be implausible.
The sun has a lot of energy, and to simulate it would itself require a lot of energy. To simulate the sun exactly as we know it would take MORE energy than the sun, because the entire energy of the sun must be simulated and we must account for the energy lost due to heat or other factors as an engineering concern. So just to properly simulate the sun, we’d need to generate more energy than the sun has, which already seems very implausible on earth, given we can’t create a reactor larger than the sun on the earth. If we extend this argument to simulating the entire universe, it seems impossible that humans would ever have the necessary energy to simulate all the energy in the universe, so we must only be able to simulate a part of the universe or a smaller universe. This again follows from the fact that to perfectly simulate something, it requires more energy than the thing simulated.
You should look up the phrase “planned obsolescence”. It’s a concept taught in many engineering schools. Apple employs it in it’s products. The basic idea is similar to your thoughts under “Greater Global Wealth”: the machine is designed to have a lifetime that is significantly shorter than what is possible, specifically to get users to keep buying a machine. This is essentially subscription-izing products; subscriptions are, especially today in the start up world, generally a better business model than selling one product one time (or even a couple times).
With phones, this makes perfect sense, given the pace of advancements in the phones, generation after generation.
While you would think that a poor person would optimize for durability, often durability is more expensive, meaning that the poor person’s only real choice is a lower-quality product that does not last as long.
“Better materials science: Globally, materials science has improved. Hence, at the local level, manufacturers can get away with making worse materials.” This doesn’t really follow to me. There are many reasons a manufacturer would use worse materials than the global “best materials”, including lower costs. It seems to me that your idea of ‘greater global implies worse local’ can be equally explained as a phenomenon of capitalism, where the need to make an acceptable product as cheaply as possible does not often align with making the best product at whatever the cost.
Is there an article that presents multiple models of UF-driven humans and demonstrates that what you criticize as contrived actually shows there is no territory to correspond to the map? Right now your statement doesn’t have enough detail for me to be convinced that UF-driven humans are a bad model.
And you didn’t answer my question: is there another way, besides UFs, to guide an agent towards a goal? It seems to me that the idea of moving toward a goal implies a utility function, be it hunger or human programmed.
Why would I give up the whole idea? I think you’re correct in that you could model a human with multiple, varying UFs. Is there another way you know of to guide an intelligence toward a goal?
I think you’re getting stuck on the idea of one utility function. I like to think humans have many, many utility functions. Some we outgrow, some we “restart” from time to time. For the former, think of a baby learning to walk. There is a utility function, or something very much like it, that gets the baby from sitting to crawling to walking. Once the baby learns how to walk, though, the utility function is no longer useful; the goal has been met. Now this action moves from being modeled by a utility function to a known action that can be used as input to other utility functions.
As best as I can tell, human general intelligence comes from many small intelligences acting in a cohesive way. The brain is structured like this, as a bunch of different sections that do very specific things. Machine models are moving in this direction, with the Deepmind Go neural net playing a version of itself to get better a good example.
I disagree with your interpretation of how human thoughts resolve into action. My biggest point of contention is the random pick of actions. Perhaps there is some Monte-Carlo algorithm that has a statistical guarantee that after some thousands or so tries, there is a very high probability that one of them is close to the best answer. Such algorithms exist, but it makes more sense to me that we take action based not only on context, but our memory of what has happened before. So instead of a probabilistic algorithm, you may have a structure more like a hash table. Then the input to the hash table would be what we see and feel in the moment: you see a mountain lion and feel fear, this information is hashed, and run like hell is the output. Collisions of this hash table could result in things like inaction.
I think your idea of consciousness is a good start and similar to my own ideas on the matter: we are a system and the observer of the system. What questions remain, however, are what are the sufficient and necessary components of the system, besides self-observation, that would create a subjective experience? Such as, would a system need to be self-preserving and aware of that self-preservation? Is sentience a prerequisite of sapience? By your definition, you seem to imply the other way around, that one must be a self-observing system to observe that you are observing something outside of your system. Maybe this is a chicken and egg problem, and the two are co-necessary factors. I would like to hear your thoughts on this.
As to your thoughts on a friendly AI...I have come up with a silly and perhaps incorrect counter-intuitive approach. Basically, it works like this: a computer system’s scheduler gives processor time to different actions in preference of some utility level. Let’s say 0 is the least important, and 5 the most. Lower level processes cannot preempt higher level ones; that is, a level 0 process cannot run before all level 1 processes are complete, and even if the completion of a level 0 process can aide the completion of a level 1 process, it cannot be run. The machine must find a different method, or return that the level 1 process cannot be completed with the current schedule. A level 5 request to make 1000 paperclips is given to the machine, and the machine determines that killing all humans will aid the completion of paperclips. Alas! Killing all humans is already scheduled at level 0, and another approach must be taken.
The other, less silly approach I thought of is to enforce a minimum energy requirement on all processes of a sufficiently dangerous machine. It stands to reason that creating 1000 paperclips can take significantly less energy than killing all humans, so killing all humans will be seen as a non-optimal strategy. In this scheme, we may not want to ask for world peace, but we should always be careful what we wish for....
This looks like a good method to derive lower-level beliefs from higher-level beliefs. The main thing to consider when taking a complex statement of belief from another person, is that it is likely that there is more than one lower-level belief that goes into this higher-level belief.
In doxastic logic, a belief is really an operator on some information. At the most base level, we are believing, or operating on, sensory experience. More complex beliefs rest on the belief operation on knowledge or understanding; where I define knowledge as belief of some information: Belief(x) = Knowledge_x. These vertices of knowledge can connect along relational edges to form a graph, of which a subset of vertices and edges could be said to be an understanding.
So I think it’s not only important to use this method as a reverse-operator of belief, but to also take an extra step and try to acknowledge the other points on the knowledge graph that represent someone’s understanding. Then these knowledge vertices can also be reverse-operated on, and a more complete formulation of both parties’ maps can be obtained.
Seems to me both liberals and conservatives are social farmers, it’s a matter of what crop is grown. Conservatives want their one crop, say potatoes, not because it’s the most nutritional, but it’s been around for forever and it’s allowed their ancestors to survive. (If we assume like you do about Christianity, then we also have that God Himself Commanded They Grow Potatoes.) Liberals see the potatoes, recognize that some people still die even when they eat potatoes like their ancestor, and decide they need more crops. Maybe they grow fewer potatoes, and maybe they grow yellow potatoes instead of brown or some such triviality, but the idea like you state is to not privilege those people who are inherently better at digesting potatoes by growing other things as well. This is naturally heresy to conservative potato growers because you shouldn’t fix something that isn’t broken (and if God didn’t say it’s broken then it’s not—excluding the idea of God and you just get potato-digesting-enzyme supremacy).