Difference between revisions of "Iterated amplification"

From Issawiki
Jump to: navigation, search
 
(2 intermediate revisions by the same user not shown)
Line 6: Line 6:
 
* [[adequate oversight]]
 
* [[adequate oversight]]
 
* [[overseer]]
 
* [[overseer]]
* [[bandwidth of the overseer]]
+
* [[bandwidth of the overseer]], [[high bandwidth oversight]], [[low bandwidth oversight]]
 
* [[reward engineering]]
 
* [[reward engineering]]
 
* [[HCH]], [[Strong HCH]], [[Weak HCH]], [[Humans consulting HCH]]
 
* [[HCH]], [[Strong HCH]], [[Weak HCH]], [[Humans consulting HCH]]
Line 30: Line 30:
 
* [[universality]]
 
* [[universality]]
 
* [[narrow value learning]] vs [[ambitious value learning]]
 
* [[narrow value learning]] vs [[ambitious value learning]]
 +
* [[learning with catastrophes]], [[optimizing worst-case performance]]
  
 
==See also==
 
==See also==
Line 36: Line 37:
  
 
[[Category:Iterated amplification]]
 
[[Category:Iterated amplification]]
 +
[[Category:AI safety]]

Latest revision as of 03:58, 26 April 2020