These examples seem related to the abstraction question: we want the model to know that it is splitting an agent into parts, and still believe it can’t influence the agent as a hole. If we could realize this, then the LCDT agent wouldn’t believe it could influence the neural net/the logic gates.
These examples seem related to the abstraction question: we want the model to know that it is splitting an agent into parts, and still believe it can’t influence the agent as a hole. If we could realize this, then the LCDT agent wouldn’t believe it could influence the neural net/the logic gates.