Comment by Benjamin on All AGI safety questions welcome (especially basic ones) [Sept 2022] · 2022-09-09T01:33:15.878Z · LW · GW

Is there a way to measure agenticness? Or at least a relative measure. Like this: https://xkcd.com/2307/ but more objective.

Comment by Benjamin on AGI Safety FAQ / all-dumb-questions-allowed thread · 2022-06-07T23:39:59.040Z · LW · GW

It seems like instrumental convergence is restricted to agent AI's, is that true? 

Also what is going on with mesa-optimizers? Why is it expected that they will will be more likely to become agentic than the base optimizer when they are more resource constrained?