Great summary! It’s exciting to see another AI safety researcher thinking along the lines of meta-preferences. I’m curious to know what stage that part of the theory is technically.
-
-
-
I don't really know, but there are others working on this as well. This podcast with Stuart Armstrong (not to be confused with Stuart Russell) talks about meta-preferences:https://futureoflife.org/2019/09/17/synthesizing-a-humans-preferences-into-a-utility-function-with-stuart-armstrong/ …
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.