Makes sense. I think generalizing from “what gets karma on LW” to “what do the people thinking most about AI X-risk on LW is important” is pretty fraught (especially at the upper end karma is mostly a broad popularity measure).
I think using the results of the annual review is a lot better, and IMO the top alignment posts in past reviews have mostly pretty good takes in them (my guess is also by your lights), and the ones that don’t have reviews poking at the problems pretty well. My guess is you would still have lots of issues with posts scoring highly in the review, but I would be surprised if you would summarize the aggregate as “pretty bad takes”.
I was just refering to “what gets karma on LW”. Obviously, unclear how much we should care.
Makes sense. I think generalizing from “what gets karma on LW” to “what do the people thinking most about AI X-risk on LW is important” is pretty fraught (especially at the upper end karma is mostly a broad popularity measure).
I think using the results of the annual review is a lot better, and IMO the top alignment posts in past reviews have mostly pretty good takes in them (my guess is also by your lights), and the ones that don’t have reviews poking at the problems pretty well. My guess is you would still have lots of issues with posts scoring highly in the review, but I would be surprised if you would summarize the aggregate as “pretty bad takes”.