All of claynaff's Comments + Replies

The greatest danger is that an arms race will lead to the creation of a superintelligence which will immediately be used to dominate all others. Speculative threats by an autonomous superintelligence are plausible but are less certain than the first-strike logic inherent in such an arms race. Here's what we know from recent history: a) the instinct for domination is alive and well in the human species, and where circumstances allow an intelligent psychopath to reach the pinnacle of power, all available means will be deployed to maintain his (usually his... (read more)

I think Christiano's idea sets us on the right path. One of the things that troubled me in reading Bostrom's book is the prospect that a superintelligence under human control could be at least as dangerous as an autonomous superintelligence. For example, if superintelligence were hatched by one of the competing military superpowers -- Russia, China, or the U.S., let's say -- as an oracle or genie, it might be used for short-sighted or selfish purposes with catastrophic consequences. With superintelligence on his side, the cartoon nightmare of a single ma... (read more)

The obvious problem is lack of human intelligence. Whether a majority of people on Earth will agree with some question the AI will ask them using the cell phone... it will depend on how specifically the question was framed. Does it invoke popular applause lights? The majority will say "yes". Is it complicated? The majority will say: "I do not understand the question." Now what? Does the majority of those who answered otherwise decide? Then, for sufficiently complicated questions the answers will be decided by people who are unable to see their own lack of understanding.

Unless it is deliberately or accidentally altered, an emulation will possess all of the evolved traits of human brains. These include powerful mechanisms to prevent an altruistic absurdity such as donating one's labor to an employer. (Pure altruism -- an act that benefits another at the expense of one's genetic interests -- is strongly selected against.) There are some varieties of altruism that survive: kin selection (e.g., rescuing a drowning nephew), status display (making a large donation to a hospital), and reciprocal aid (helping a neighbor in hope... (read more)

Note that the employer in question might well be your own upload clan, which makes this near-analogous to kin selection. Even if employee templates are traded between employers, this trait would be exceptionally valuable in an employee, and so would be strongly selected for. General altruism might be rare, but this specific variant would probably enjoy a high fitness advantage.
Language and conceptual systems are so complex, that communication (as in the replication of a concept from one mind to another) is often extremely difficult. The idea of altruism is one such thing. Like most terms in most languages, it has a large (potentially infinite) set of possible meanings, depending on context. If one takes the term altruism at the simplest level, it can mean simply having regard for others in choices of action one makes. In this sense, it is clear to me that it is actually in the long term self interest of everyone to have everyone having some regard for the interests of others in all choices of action. It is clear that having regard only for short term interest of self leads to highly unstable and destructive outcomes in the long term. Simple observation of any group of primates will show highly evolved cooperative behaviours (reciprocal altruism). And I agree, that evolution is always about optimisation within some set of parameters. We are the first species that has had choice at all levels of the optimisation parameters that evolution gets to work with. And actually has the option of stepping entirely outside of the system of differential survival of individuals. To date, few people have consciously exercised such choice outside of very restricted and socially accepted contexts. That seems to be exponentially changing. Pure altruism to me means a regard for the welfare of others which is functionally equal to the regard one has for one's own welfare. I distinguish this from exclusive altruism (a regard for the welfare of others to the exclusion of self interest) - which is, obviously, a form of evolutionary, logical, and mathematical suicide in large populations (and even this trait can exist at certain frequencies within populations in circumstances of small kin groups living in situations that are so dangerous that some members of the group must sacrifice themselves periodically or the entire group will perish - so is a form of rad

I’m grateful for these summaries and discussions. Having only just dived into the reading group, I ask forgiveness if I am overtracking some prior comment. It seems to me that “human values” and “oversight” often go unexamined as we consider the risks and utility of superintelligence. I mean no disrespect to Katja in saying that (she’s summarizing, after all), but to say “human values” is either to reduce to the common denominator of our evolutionary psychology or to ignore the vast cultural and ideological diversity of humanity. Either way, it’s a ... (read more)

I think that there is relevant discussion further on in the book (Chapter 13) regarding Coherent Extrapolated Volition. It's kind of an attempt to specify human values to the AI so it can figure out what the values are are in a way that takes everyone into account and avoids the problem of one individual's current values dominating the system (with a lot more nuance to it). If executed correctly, it ought to work even if the creators are mistaken about human values in some way.
Exactly! Bostrom seems to start the discussion from the point of humans having achieved a singleton as a species; in which case a conversation at this level would make more sense. But it seems that in order to operate as a unit, competing humans would have to work on the principle of a nuclear trigger where separate agents have to work in unison in order to launch. Thus we face the same problem with ourselves: how to know everyone in the keychain is honest? If the AI is anywhere near capable of taking control it may do so even partially and from there could wrangle the keys from the other players as needed. Competitive players are not likely to be cooperative unless they see some unfair advantage accruing to them in the future. (Why help the enemy advance unless we can see a way of gaining on them?) As long as we have human enemies, especially as our tools become increasingly powerful, the AI just needs to divide and conquer. Curses, foiled again!