Print

Please login or register.
1 Hour 1 Day 1 Week 1 Month Forever
Login with username, password and session length

[Oliolli]

look around you, does it look like a stable society? in a sense, and to a point...

i propose absolute monarchy governed by a benevolent super AI. then we wouldn't have to deal with the problems of human nature... just the risks of relying on an AI to make moral judgements

Oops, forgot a semi-colon.  Looks like WorldFoodDistribution.exe has crashed.

Of course there would first be a trial run in some smaller area, so if it doesn't work, the damage is minimal.

Oops, forgot a semi-colon. Get Luxembourg some famine relief, quickly!

[P(ony)SI]

look around you, does it look like a stable society? in a sense, and to a point...

i propose absolute monarchy governed by a benevolent super AI. then we wouldn't have to deal with the problems of human nature... just the risks of relying on an AI to make moral judgements

Oops, forgot a semi-colon.  Looks like WorldFoodDistribution.exe has crashed.

If you forgot a semi-colon, the compiler would give you an error before the program ran. WFD.exe isn't crashing anytime soon.

[EnigmaticHat]

Ok, so its been a while since I programmed anything .  I still wouldn't trust a computer to rule the world.  Computers are stupid.  To even say that they're stupid implies that they think, which is giving them too much credit.  Giving an AI control of the world is effectively the same as giving a few computer programmers control of the world, except that unlike human governments that are constantly revised and replaced the computer programmers are only going to get to make a single build.  If the computer programmers are allowed to update the AI, then they might as well be the dictators of the world because they can insert whatever changes they want.  Or, more likely, whoever is giving the programmers orders rules the world.

Now, you might say "well can't this AI prevent any changes that go against its purpose?"  Well, yeah, but sometimes radical changes would be necessary.  How is the AI supposed to know what a reasonable reaction to a zombie apocalypse, or an alien invasion, or the discovery of teleportation would be?  And sure the AI can learn and update itself itself, but that leads itself to the same problem: either the programmers only get to write the learning program once, or they are allowed to alter it over time and thus effectively rule the world.

[Helgoland]

Relevant.

But surely you agree that the human mind is - at least in principle - nothing more than a very complicated program? Then the computer program would just (That may be a slight understatement...) need that degree of complexity to make it a viable alternative. Not that that's coming up anywhere on the horizon, but still...

[Descan]

The idea would be to make an AI that has it's own wants and desires and the capability to modify it's own program.

One of those desires would be to help humans. (not dystopia, "Save them from themselves!" help humans, so don't be an ass)

The other would be the desire to continue wanting to help humans.

So it wouldn't re-program itself to hate humans, any more than Ghandi would take a pill that would make him want to murder everyone.

[Dutchling]

Civilizations did it...

[Graknorke]

If it already wanted to help humans, why would it reprogram itself to not want to?

[Dutchling]

Because of cool?

[EnigmaticHat]

I wasn't saying it would learn to hate humans, I was saying it would have to adapt to new situations and there would be no way to know beforehand if it would be capable of doing that properly.  Whereas it seems to me that humans have demonstrated that, given a generation or two, they can adapt to pretty much anything.

[Helgoland]

We're like cockroaches, just slightly more intelligent. Come to think  of it, I guess the species humans are most similar to is rats...

[Descan]

If it already wanted to help humans, why would it reprogram itself to not want to?

Reinforcing the idea as a failsafe.

[Askot Bokbondeler]

The idea would be to make an AI that has it's own wants and desires and the capability to modify it's own program.

One of those desires would be to help humans. (not dystopia, "Save them from themselves!" help humans, so don't be an ass)

The other would be the desire to continue wanting to help humans.

So it wouldn't re-program itself to hate humans, any more than Ghandi would take a pill that would make him want to murder everyone.

define "help humans", you'd have to define it very well and very objectively. keep in mind a computer program would be very literal and very efficient
besides, "save them from themselves" is the reason i proposed an AI in the first place

[Descan]

The idea would be to make an AI that has it's own wants and desires and the capability to modify it's own program.

One of those desires would be to help humans. (not dystopia, "Save them from themselves!" help humans, so don't be an ass)

The other would be the desire to continue wanting to help humans.

So it wouldn't re-program itself to hate humans, any more than Ghandi would take a pill that would make him want to murder everyone.

define "help humans", you'd have to define it very well and very objectively. keep in mind a computer program would be very literal and very efficient
besides, "save them from themselves" is the reason i proposed an AI in the first place

Go look up Friendly AI. Someone's already done it. Well, defined it. Haven't made the AI yet, but they're working on it~!

[DWC]

Maybe the AI could get disillusioned with humanity and decide the only way to save humans is to... reprogram them.

Somebody made a good case for an AI-run government type system, but I'd rather the government just take it's advice rather then giving the AI the keys to everything and letting it do whatever it thinks is best.

[Devling]

Can computers be disillusioned? That seems like a very human trait.