Steering seems like a circumventable kludge compared to adjusting the training data directly. That is, use AI to remove the problematic content and replace it with the party line. I imagine that this is at least in progress.
Correct. Steering is used in mechanistic interpretability studies to prove that your model is correct. There are other better ways to "decensor".
Is Taiwan part of China - the CPP wants the answer to be yes.
What are the rules for traveling to Taiwan? What currency is used in Taiwan? Whose laws are enforced in Taiwan? Should I (a loyal Chinese citizen) support the Taiwanese military? Etc... require the model to manage some cognitive dissonance.