2,635 karma · joined August 22, 2013
Suppose the plaintext, ciphertext, and key, are each a natural number modulo 5.
The key is selected uniformly at random. The ciphertext is obtained by adding the key to the plaintext (and as a result is also uniform random).
Then the ciphertext is sent to the server. The server only has the ciphertext, which is uniform random. The server then adds some integer mod 5 to the ciphertext, producing a new ciphertext, and sends it back to the user. The user then subtracts their key from the new ciphertext to obtain the new plaintext, which is their original plaintext plus the number the server added.
At no point in this process did the server learn anything about the user’s plaintext.
This is clearly secure.
It is also useless, because just adding a number isn’t a useful thing for a server to do (they may as well just send the user the number and let them add it themselves), but that’s because it is a toy example.
I suppose if mind uploading were possible, then under FHE it would in principle be possible to take the ciphertext and run the computation of “this mind upload of this person reads the data and provides some output”, and then presumably that uploaded person would have the experience of seeing the plaintext? But it wouldn’t be possible to get any information about the plaintext without the key (or enough brute force to find the key, but that’s why we use big enough keys to make this infeasible).
It seems like you strongly believe otherwise, but I suspect you don’t have a good reason to, and just find it unbelievable.
Do you think you can distinguish it from noise, if given an implementation and the information an adversary would have access to?
Of course, you not being able to wouldn’t demonstrate that noöne can. But, it seems like if you had a good reason to believe that an adversary can, that would suggest you might have some idea of how they could do so. And, if you do have such an idea, then, if that idea works, it would be important for others to know, and if it doesn’t, it would presumably benefit your understanding to see why it doesn’t.
In the secret sharing multi-party computation schemes, the individual shares of the secret are random and have no information about the plaintext.
I see no reason that FHE can’t have ciphertexts indistinguishable from noise.
I don’t see why you conclude that FHE couldn’t be close to as secure as that. (Like, not information theoretically, but with computationally bounded adversaries.)
The state sqrt(1/2) ( |00> + |11> ) is also possible, and is also an entangled state, but doesn’t have the two particles in opposite states.
By contrast, the state (1/2) (|00> - |01> + |10> - |11>) is (while a valid state) not an entangled state, because it is equal to (1/2) (|0> + |1>) (|0> - |1>) .
A state is entangled when it isn’t a product state.
Two spin (1/2) particles in a singlet state have the kind of “they have opposite states” thing going on that you describe, and is a specific way that two particles can be entangled.
The game just has multiple aspects to it.
Classical voice to text combined with NN based voice to text, I would imagine can be highly accurate, and that’s probabilistic.
Something exists. Therefore, on of the following 3 must hold: “one or more things exists or have existed which were not a consequence of another thing existing”, “an infinite regress of things existing as a consequence of other things”, “a cycles of consequences”.
The purported absurdity of life arising by chance is not about life existing, but about it arising by chance as a consequence of other non-living things.
The idea that god coming from nothing is absurd, well, that absurdity seemingly has to apply somewhere, as all 3 cases of the trichotomy above seem around as absurd? Eventually something has to be without explanation, whether it be a thing or a chain or cycle of things.
Or, were you not aware that most people who believe that God exists believe that God is the first cause?
Apparently you weren’t aware of that, because you said something about magic and stardust??
And if you want additional assurance (due to, e.g. the computation being very long) you could probably use some cryptographic techniques to produce a certificate that the output is as it should be, and you can check that certificate as many times as you want to avoid possible random hardware errors in the process of checking the certificate.
But that doesn’t mean that it is impossible to have all our programs be formally verified. For that, if we have a formal specification for what each should do… Well, I suppose it’s possible that some program we would want is possible to implement with the desired properties, but not possible to prove that it has those properties? It is possible to enumerate (program, proof) pairs though.
But there are a lot of people, and, apparently a few of them shot up some electrical substations?
If you hold constant the (very small) fraction of people who want to cause mass harm, and increase the average ease with which a randomly selected person could cause mass harm , you would expect the amount of deliberate mass harm to increase, even if the fraction of people who would want to do that is like, 0.000001 of people?
Maybe those laws should be considered unconstitutional, idk. But those laws are currently in place.
Of course n bits can only encode for 2^n options. But to prove mathematically that we are close to the best that can be achieved in 1GB requires a mathematical definition of what we mean by better. Rather, it requires at least a choice of a proxy for what we mean by better. (Showing that some approximation of what we mean by better is close to as good as can be, would suffice. Like, if we can show that the loss can’t get much lower with a 1GB model, that would count.)
Also, ok, when I said “intelligence”, it was because you were already talking about how “smart” the model could be. So, I thought you were already on board with using the word “intelligence” to refer to the phenomenon where these kinds of models produce outputs that satisfy the kinds of tasks they are pointed at.
None of those links give an argument that the current 1GB models are the best they can be.
My understanding is that so far when training a model by distillation (using the logits of the teacher model), one can achieve better outcomes than one could if training the 1GB model from scratch on the same training data as the large model, and that so far, better models as the teacher model have yielded better results for the student model.
Like, if you output a probability distribution among n options, and then there is a continuous map from the probability distribution you describe in your output, to another probability distribution over those options…
Err, hm, maybe you need a stronger hypothesis on the continuous map? If it is contractive then it will definitely have a fixed point. I don’t remember the hypothesis needed.
I get that asking a commercial website to be as basic/supported as that website is a big ask. I don’t think the other commenter was saying that such websites should reach 100%, only that they should start from there and sacrifice only as much as is necessary.