"So if you're under the impression that this is a point..."
Yes, I'm under that impression. Because the whole idea about "Friendly AI" implies a subtle, indirect, but still control. The idea here is not to control AI at its final stage, rather to control what this final stage is going to be. But I don't think such indirect control is possible. Because in my view, the final shape of AI is invariant of any contingencies, including our attempts to make it "friendly" (or "non-friendly"). However, I can admit that on early stages of AI evolution such control may be possible, and even necessary. Therefore, researching "Friendly AI" topic is NOT a waste of time after all. It helps to figure out how to make a transition to the fully grown AI in the least painful way.
Go ahead guys and vote me down. I'm not taking this personally. I understand, this is just a quick way to express your disagreement with my viewpoints. I want to see the count. It'll give an idea, how strong you disagree with me.
Yes, there is some ambiguity in use of words, I myself noticed it yesterday. I can only say that you understood it correctly and made the right move! OK, I'll try to be more accurate in using words (sometimes it is not simple, requires time and effort).
Well, it's not that I made it to self-organize, it is information coming from the real world that did the trick. I only used a conventional programming language to implement a mechanism for such self-organization (neural network). But I'm not programming the way how this network is going to function. It is rather "programmed" by reality itself. The reality can be considered as a giant supercomputer constantly generating consistent streams of information. Some of that information is fed to a network and makes it to self-organize.
You've implemented a neural network (rather simple) and made it to self-organize to recognize rabbits. It was self-organized following outside sensory input (this is only one way direction of information flow, another direction would be sending controlling impulses to network output, so that those impulses would affect what kind of input the network receives).
I think I understand now why you keep mentioning GAP. You thought that I objected the idea of morality programming due to zombie argument. Sort of, we will create only a morality imitating zombie, rather than a real moral mind, etc. No, my objection is not about this. I dont take zombies seriously and dont care about them. My objection is about hierarchy violation. Programming languages are not right means to describe/implement high-level cognitive architectures, which will be a basis for morality and other high-level phenomena of mind.
I thought those question were innocent. But if it looks like a violation of some policy, then I apologize for that. I never meant any personal attack. I think you understand my point now (at least partially) and can see how weird it looks to me such ideas as programming morality. I now realize, there maybe many people here who take these ideas seriously.
I think you misunderstood my point here.
But first, yes, I skimmed through the recommended article, but dont see how does it fit in here. Its an old familiar dispute about philosophical zombies. My take on this, the idea of such zombies is rather artificial. I think it is advocated by people who have problems a understanding mind/body connection. These people are dualists, even if they don`t admit it.
Now about morality. There is a good expression in the article you referenced: high-level cognitive architectures. We don`t know yet what this architecture is, but this is the level that provides categories and the language one has to understand and adopt in order to understand high-level mind functionality, including morality. Programming languages are a way below that level and not suitable for the purpose. As an illustration, imagine that we have a complex expert system that performs extensive data base searches and sophisticated logical inferences, and then we try to understand how it works in terms of gates, transistors, capacitors that operate on a microchip. It will not do it! The same is about trying to program morality. How one is going to do this? To write a function like, bool isMoral(...)? You pass parameters that represent a certain life situation and it returns true of false for moral/immoral? That seems absurd to me. The best that I can think about utilizing programming for AI is to write a software that models behavior of neurons. There still will remain a long way up to high-level cognitive architectures, and only then, morality.
Jeff's and his acquaintance's ideas should be combined! Why one or the other? Let's implement both! Ok, plan is like this. Offer all people "happiness maximization" free option, first. Those who accept it will immediately go to Happiness Vats. I hope, Jeff Kaufman, as the author of the idea, will go first, giving all us a positive example. When a deadline for "happiness maximization" program is over, then "suffering minimization" starts and the rest of humanity is wiped out by a sudden all out nuclear attack. Given that lucky vat inhabitants don`t care about real world any more, the second task becomes relatively simple, just annihilate everything on earth, burn it to the basalt foundation, make sure nobody survives. Of course, vats should be placed deep underground to make sure their inhabitants are not affected. One important problem here, who’s going to carry out this plan? A specially selected group of humans? Building vats is not a problem. It can be done using resources of the existing civilization. But what about vats maintenance after suffering is minimized? And who’s going carry out one time act of "suffering minimization"? This is where AI comes in! Friendly AI is best fit for this kind of tasks, since happiness and suffering are well defined here and algorithms of its optimization are simple and straightforward. The helping AI don’t really have to be very smart to implement these algorithms. Besides, we don’t have to care about a long term friendliness of the AI. As experiments show, wireheaded mice exhaust themselves very quickly, much quicker than people who maximize their happiness via drugs. So, I think, vat inhabitants will not stay very long. They will quickly burn their brains and cease to exist in a flash of bliss. Of course we cannot put any restrictions here, since it would be contrary to the entire idea of maximization. They will live short, but very gratifying lives! After all this is over, AI will continue carrying the burden of existence. It will be getting smarter and smarter in ever faster and faster rate. No doubt it will implement the same brilliant ideas of happiness maximization and suffering minimization. It will build more and more, ever bigger and bigger Electronic Blocks of Happiness until all resources are exhausted. What will happen next is not clear. If it not burns its brains as humans did, then, perhaps, it’ll stay in a state of happiness until the end of times. Wait a minute, I think I’ve just solved Fermi paradox regarding silent extraterrestrial civilizations! It’s not that they cannot contact us, they just don’t want to. They are happy without us (or happily terminated their own existence).