Will_Sawin comments on Values vs. parameters - Less Wrong

9 Post author: PhilGoetz 17 May 2011 05:53AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (65)

You are viewing a single comment's thread.

Comment author: Will_Sawin 18 May 2011 02:42:18AM 1 point [-]

Isn't this all about reflective equilibrium?

Define my real values to be the endpoint of the process in which I continually question my intuitions and self-modify until I have a single, coherent set of values and moral intuitions.

Define my used values to be the approximation that I use to make decisions on a day-by-day basis.

Define the discounting hypothesis to be the statement that there exists a utility function that takes a paramater f(p,U) such that:

  1. p can be interpreted as the amount of discounting

  2. f(0,U) closely approximates our real values.

  3. f(x,U) for some x>0 closely approximates our used values.

Then perhaps Eliezer is arguing for the discount hypothesis.