X-Message-Number: 15981 Date: Sat, 31 Mar 2001 10:38:08 -0800 From: Lee Corbin <> Subject: Re: Reliability of Friendly AI Eliezer Yudkowsky wrote [Lee wrote] >> I really don't think that "rights" in the abstract mean >> anything. Usually when someone forms a sentence "X has >> the right to do Y", it really means nothing more than >> "I approve of X being able to do Y". > "X has the right to do Y" means (1) "I approve of X > being able to do Y"; plus either (2a) "I believe that > society at large also approves of X being able to do Y", > or (2b) "I believe that society at large believes in moral > principles whereby I should be able to convince them that > they should approve of X being able to do Y, even if they > do not presently believe as such". At least, that's the > moral relativist's version. Well said, but it's still not worth it in my book. I will continue to avoid using the term myself, and continue to be suspicious and critical of sentences where others employ this tendentious term. >> So far as I can see, the infinite nosiness of the Sysop... > Could you *please* restrain your impulse to use terminology > like this and just concentrate on debating whether or not > the Sysop is, in fact, infinitely nosy? Thanks for the good laugh. Pardon me, but aren't we being a bit sensitive? :-) (That's not a serious question.) Okay, I'll try to remember. >> I am opposed to legal rights for animals, and do not believe >> that we actually need statutes on the books forbidding >> cruelty to animals (if we ever did need them), even >> though I base my beliefs on utilitarianism also. > Forgive me, but aren't you now talking about rights? No. Sorry, but I am sure that my statement is clear. I want to say that I don't approve of having statutes like that on the books. Understandably, the double usage of "need" may have confused you, but most people would react to me saying "We don't need that" as "Lee doesn't like that", or "Lee doesn't think it's a good idea". > If this entire conversation is phrased in terms of simple > cause and effect, then a Friendly AI comes into existence > which respects your rights and also the rights of any > citizens which you create. I understand that you wish to promulgate your ideas in terms of these "rights", but I have an observation and a suggestion. In my experience, people who rely too heavily on a single term or word aren't communicating as well as they might, and if it turns out that the word is indispensible---there are just no other ways that they can find to express something---then their ideas are not very clear. As an exercise, you may find it instructive to see (for a period of time) if you can communicate without using the term. For one thing, at least talking to me, as I said, I just don't know exactly what is meant. (Also, I studied under the double-plus-good writer George Orwell... :-) >> and how many would agree with me, that our >> government should exist only to enforce freely arrived-at >> contracts, and to protect private property? > A rather prejudiced way of phrasing it, don't you think? I'm honestly puzzled by some of your reactions. Prejudiced? Well, for sure, who ever is saying that is probably a libertarian, but, the statement has no hidden tendentiousness so far as I can see. Many people clearly disagree with it; many people understandably think that governments should do a lot more, like offer free education or health coverage. You ask what my answer would be to this scenario: > Mr. Smith creates a simulation of he doesn't like; say, > Mrs. Jones next door from Old Earth....Mr. Smith then > works up a recreation of a medieval torture chamber - > and keeps Mrs. Jones there for a thousand years. My nearest one would be > 3) "No, I hate it, and I'd [probably] do something about > it if I could get away with it, but I believe that > the morally optimal structure for society is such > that society would successfully prevent me from > interfering with Mr. Smith in any way." I would replace the phrase "morally optimal structure" with "best structure so far evolved". I've read Hayek and Sowell, and no longer believe we have the ability to design "morally optimal" governments), and probably not morally optimal AIs either. Really, though, I might be closer to your option number 6, wherein you provided for the possibility that I might find the scenario unrealistic. Indeed I do. In order to emulate someone (that is, I mean to say, simulate them to the point that someone is "really there"), you need to be vastly more complex than they are. For example, if I were Edward O. Wilson, it's conceivable that I could write a program that emulated an ant. I have thought for some time that you worry too much about ordinary human-level folks running simulations wherein trillions of people get tortured. What is more relevant is to consider that our mind-children may indeed have that power. Yet again, I'd maintain that it just doesn't figure that any but a tiny fraction of the entities living in the solar system ten thousand years from now, would waste their time on something like that. (How many people on Earth today deliberately torture insects, and how much does it matter anyway?) Lee Corbin Rate This Message: http://www.cryonet.org/cgi-bin/rate.cgi?msg=15981