I believe you are correct about the current implementation of AIs as they try to minimize a loss function or maximize a reward. I also agree that the definition of consciousness is very subjective.

In my opinion, what's missing for conscious AI is a way to model causality. If we ever achieve that it's just a matter of computational resources since an AI can seep through the cause and effect chain (graph maybe) until it finds what needs to be done to obtain a wanted outcome. That is critical thinking and which I strongly associate with consciousness and/or intelligence.