|
@rohinmshah | |||||
|
Alignment Newsletter #69: Stuart Russell's new book on why we need to replace the standard model of AI - mailchi.mp/59ddebcb3b9a/a…
|
||||||
|
||||||
|
June Ku
@metaethical_ai
|
20. lis |
|
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.
|
||
|
|
||
|
Rohin Shah
@rohinmshah
|
21. lis |
|
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: futureoflife.org/2019/09/17/syn…
|
||
|
|
||