It certainly doesn't increase my confidence that if they do ever create a superintelligence, that it won't have some weird unforseen preference that'll end up with us all dead.
USER: Do you think it will be possible in the future to use machines, powered by electricity, to do the kind of mathematical calculations that computers do today?
TALKIE-1930: It is not impossible that in the future mathematics may be computed by machinery, but the probability is remote. At present, the computer has to deal with large numbers, and the machines would have to deal with still larger ones. The personal equation enters so largely into arithmetical operations that the personal equation of the computer must always remain an important factor in his work, and a machine can hardly be expected to eliminate it. Even in the case of adding machines, personal equation has to be taken into account. Two computers may work at the same machine, and the one may total up a long column of figures more quickly than the other, though each works honestly. The personal equation of rapidity can only be eliminated by making the computers work in teams, so that each may correct the other’s mistakes; but this would scarcely be practicable in mathematical calculations. At best, machinery can only be used to save labour, not to supersede it. Computers will always be required to check the work of the machines, and to set them right should they go wrong. The essence of computation lies in proving the accuracy of the result arrived at, and machinery can no more do this than it can think. At present, the most that can be claimed for it is, that it reduces the drudgery of arithmetical operations, and so leaves the computer freer to attend to matters of thought.
Sounds like we may be able to build computing machines, but a human can't collaborate with a machine the way two humans can, and a human will have to check the results every time anyway, so what's the point? Only a human can prove that a calculation is correct.
Continuing this conversation, I'm trying to convince TALKIE about computers.
USER: I wonder if we could build a calculating machine that would be close enough to perfectly reliable that we would not have to verify the results. For example, you may have seen Leibniz's work showing that all numbers can be represented with just 0 and 1, or George Boole's work on algebra with just two values. Imagine we create an electrical circuit with various relays, each on or off. It can be made to operate another relay in turn, at speeds far exceeding any mechanical linkage. Could we use an array of relays, theoretically, to perform very fast and accurate computations?
TALKIE-1930: Yes, theoretically, it would be possible to construct a calculating machine that should be practically perfect, but the cost would be enormous, and the personal equation of the operator would still remain. Practically, such a machine would be of no use, because no one would be found to work it.
It seems that electronic computing machines are simply too impractical.
Let's try some more...
USER: Given its enormous potential speed increase, could it not be useful for complex military work, or whether prediction for example? I'm sure someone could be trained to operate such a machine.
It doesn’t know about transistors, only rudimentary vacuum tubes
It cannot hypothesize something that isn’t completely unwieldy
You have to explain the concept of a transistor as a replacement for the mechanisms of binary state operation, and how an elegant electrical circuit reduces the size and power demands of a vacuum tube computation machine
On the contrary, I think a "simulator of common objections" that reflects all the blind spots and biases of wider society is an extraordinarily valuable tool for exploring and evaluating new ideas. You might find that, in neatly summarizing what "everyone" thinks and justifying it as best it can, the LLM inadvertantly shines a spotlight on common misconceptions. Look there for the novelty.
In this case - the concept of using automated computing devices to manipulate numbers that represent ideas at arbitrary levels of abstraction was, by 1930, nearly an entire century old. Talkie's myopic viewpoint does not represent the most farsighted viewpoint, merely the average. So if, in 1930, you had read the writings of Ada Lovelace, gotten very excited, and wanted to figure out how to pitch it to investors - Talkie might have been very useful.
I vividly remember my friend and I first thinking of this question during a sleepover at around 13 years old, as we stayed awake late talking about what seemed at the time like the deep philosophies of life. This isn't to say that it's a bad question, but more that it's funny how everyone seems to come up with this question independently at some point. I've read many others with the same question since.
You certainly stumbled onto it much sooner in life than I did. It wasn't until I had children in my late 30s that this dawned on me - and has perplexed me ever since. Funny indeed.
I wouldn't say they necessarily aren't personally concerned as well. I think quite often if people disagree with their employer but don't want to lose their jobs, it's more amenable to phrase disagreement like they have there. Yes it would be braver to just come out and say "I really don't like this", but at least it's braver than saying nothing at all.
Ultimately even with that tech, you can still take a photo of an AI generated scene. Maybe coupled with geolocation data in the signature or something it might work.
I see signing chains as the way to go here. Your camera signs an image, you sign the signed image, your client or editor signs the image you signed etc etc. Might finally have a use for blockchain.
That diagram is pure marketing nonsense. The real chart is on page 10 of their paper[1]. It shows a modest ~3dB less attenuation around 800Hz across several brands.
reply