One question I have about this and other work in this area is the training / deployment distinction. If AIs are doing continual learning once deployed, I’m not quite sure what that does to this model.
When there’s continuous selection happening throughout deployment, then you’d want to be more specific about which particular time within deployment you want to predict motivations in (i.e., replace “I have influence through deployment” with “I have influence at time t in deployment” in the causal graph). Then you model all the causes of influence as before.
Thanks for writing this.
One question I have about this and other work in this area is the training / deployment distinction. If AIs are doing continual learning once deployed, I’m not quite sure what that does to this model.
When there’s continuous selection happening throughout deployment, then you’d want to be more specific about which particular time within deployment you want to predict motivations in (i.e., replace “I have influence through deployment” with “I have influence at time t in deployment” in the causal graph). Then you model all the causes of influence as before.