Centre for the Governance of AI does alignment research and policy research. It appears to focus primarily on the former, which, as I’ve discussed, I’m not as optimistic about. (And I don’t like policy research as much as policy advocacy.)
I’m confused, the claim here is that GovAI does more technical alignment than policy research?
That’s the claim I made, yes. Looking again at GovAI’s publications, I’m not sure why I thought that at the time since they do look more like policy research. Perhaps I was taking a strict definition of “policy research” where it only counts if it informs policy in some way I care about.
Right now it looks like my past self was wrong but I’m going to defer to him because he spent more time on it than I’m spending now. I’m not going to spend more time on it because this issue isn’t decision-relevant, but there’s a reasonable chance I was confused about something when I wrote that.
I’m confused, the claim here is that GovAI does more technical alignment than policy research?
That’s the claim I made, yes. Looking again at GovAI’s publications, I’m not sure why I thought that at the time since they do look more like policy research. Perhaps I was taking a strict definition of “policy research” where it only counts if it informs policy in some way I care about.
Right now it looks like my past self was wrong but I’m going to defer to him because he spent more time on it than I’m spending now. I’m not going to spend more time on it because this issue isn’t decision-relevant, but there’s a reasonable chance I was confused about something when I wrote that.