I think selection theorems should be conceived of as theorems about artifacts (the products of constructive optimisation processes) and their constructors (the optimisation processes that created such artifacts).
That is, I am quite unconvinced that “agent” is the “true name” of such artifacts. There are powerful artifacts that do not match the agent archetype as traditionally conceived. I do not know that the artifacts that ultimately matter would necessarily conform to the agent archetype.
Agent selection theorems are IMO ultimately too restrictive, and the selection theorem agenda should be about optimisation processes and the kind of constructs they select for.
I am quite enamoured with John Wentworth’s selection theorems, but find myself somewhat dissatisfied. As Wentworth framed it, I think they are a bit off.
I think selection theorems should be conceived of as theorems about artifacts (the products of constructive optimisation processes) and their constructors (the optimisation processes that created such artifacts).
That is, I am quite unconvinced that “agent” is the “true name” of such artifacts. There are powerful artifacts that do not match the agent archetype as traditionally conceived. I do not know that the artifacts that ultimately matter would necessarily conform to the agent archetype.
Agent selection theorems are IMO ultimately too restrictive, and the selection theorem agenda should be about optimisation processes and the kind of constructs they select for.