LESSWRONG

[xpost from my blog] In discussions of existential risk from AI, it is often assumed that the existential catastrophe would follow an inte

Most planning around AI risk seems to start from the premise that superintelligence will come from de novo AGI before whole brain emulation

There are two different kinds of questions that could be considered to fall under the subject of population ethics: “What sorts of altruisti

Prerequisite: http://en.wikipedia.org/wiki/Mere_addition_paradox   The repugnant conclusion is the proposition that for any well-off pop

The prisoner's dilemma tournament is over. There were a total of 21 entries. The winner is Margaret Sy, with a total of 39 points. 2nd and 3

After the iterated prisoner's dilemma tournament organized by prase two years ago, there was discussion of running tournaments for several v

Summary: The VNM utility theorem only applies to lotteries that involve a finite number of possible outcomes. If an agent maximizes the expe

A Friendly AI would have to be able to aggregate each person's preferences into one utility function. The most straightforward and obvious w

Utility functions are only defined up to an additive constant and a positive multiplier. For example, if we have a simple universe with only

Response to: Universal agents and utility functions Related approaches: Hibbard (2012),  Hay (2005) Background   Here is the function