I guess “steering abilities” wasn’t quite the right way to describe what I meant.
I’ll edit it to “desire to do anything other than predict”.
I’m referring to the very simple strategy of leaving out the “then do that thing”.
Training an AI to predict X normally doesn’t cause an AI to develop a desire to cause X.
Aside from feasibility, I’m skeptical that anyone would build a system like this and not use it agentically.
I guess “steering abilities” wasn’t quite the right way to describe what I meant.
I’ll edit it to “desire to do anything other than predict”.
I’m referring to the very simple strategy of leaving out the “then do that thing”.
Training an AI to predict X normally doesn’t cause an AI to develop a desire to cause X.
Aside from feasibility, I’m skeptical that anyone would build a system like this and not use it agentically.