Yeah, I agree this was an issue. I’ve changed the title and made an edit to reflect the focus on outer alignment.
I feel pretty resistant to changing anything about this. I feel like LW should be a place where, when you write “if X then Y,” people should know not to infer “X is true” or “I’m going to argue for X.” Moreover, one point I was trying to get across is that instead of thinking in terms of whether “ELK works” or not, you can think in terms of how many questions our ELK techniques allow us to elicit honest answers for; the larger that collection of questions (“the more optimistic you are about ELK”) the more optimistic you should be about (outer) alignment.
Yeah, I agree this was an issue. I’ve changed the title and made an edit to reflect the focus on outer alignment.
I feel pretty resistant to changing anything about this. I feel like LW should be a place where, when you write “if X then Y,” people should know not to infer “X is true” or “I’m going to argue for X.” Moreover, one point I was trying to get across is that instead of thinking in terms of whether “ELK works” or not, you can think in terms of how many questions our ELK techniques allow us to elicit honest answers for; the larger that collection of questions (“the more optimistic you are about ELK”) the more optimistic you should be about (outer) alignment.
(FWIW, I am pretty optimistic about ELK.)