I think it means that there is something which we value linearly, but that thing might be a complicated function of happiness, preference satisfaction, etc.
As a toy example, say that S(x) is some bounded sigmoid function, and my utility function is to maximize E[S(x)]; itâs always going to be the case that E[S(x1)]â„E[S(x2)]âx1â„x2 so I am in some sense scope sensitive, but I donât think Iâm open to Pascalâs mugging. (Correct me if this is wrong though.)
As a toy example, say that S(x) is some bounded sigmoid function, and my utility function is to maximize E[S(x)]; itâs always going to be the case that E[S(x1)]â„E[S(x2)]âx1â„x2 so I am in some sense scope sensitive, but I donât think Iâm open to Pascalâs mugging
This seems right to me.
I think it means that there is something which we value linearly, but that thing might be a complicated function of happiness, preference satisfaction, etc.
Yeah, I have no quibbles with this. FWIW, I personally didnât interpret the passage as saying this, so if thatâs whatâs meant, Iâd recommend reformulating.
(To gesture at where Iâm coming from: âin expectation bring about more paperclipsâ seems much more specific than âin expectation increase some function defined over the number of paperclipsâ; and I assumed that this statement was similar, except pointing towards the physical structure of âintuitively valuable aspects of individual livesâ rather than the physical structure of âpaperclipsâ. In particular, âintuitively valuable aspects of individual livesâ seems like a local phenomena rather than something defined over world-histories, and you kind of need to define your utility function over world-histories to represent risk-aversion.)
I think it means that there is something which we value linearly, but that thing might be a complicated function of happiness, preference satisfaction, etc.
As a toy example, say that S(x) is some bounded sigmoid function, and my utility function is to maximize E[S(x)]; itâs always going to be the case that E[S(x1)]â„E[S(x2)]âx1â„x2 so I am in some sense scope sensitive, but I donât think Iâm open to Pascalâs mugging. (Correct me if this is wrong though.)
This seems right to me.
Yeah, I have no quibbles with this. FWIW, I personally didnât interpret the passage as saying this, so if thatâs whatâs meant, Iâd recommend reformulating.
(To gesture at where Iâm coming from: âin expectation bring about more paperclipsâ seems much more specific than âin expectation increase some function defined over the number of paperclipsâ; and I assumed that this statement was similar, except pointing towards the physical structure of âintuitively valuable aspects of individual livesâ rather than the physical structure of âpaperclipsâ. In particular, âintuitively valuable aspects of individual livesâ seems like a local phenomena rather than something defined over world-histories, and you kind of need to define your utility function over world-histories to represent risk-aversion.)
That makes sense; your interpretation does seem reasonable, so perhaps a rephrase a would be helpful.