This is a special post for quick takes by abhayesian. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
Your explanation: "The steering vector makes the model pay attention to the stylistic constraints instead of the actual question". What would be very useful here is also an "accuracy tax": how much accuracy on the actual question goes down when the model puts all its attention into constraint-following?
I want to see the "accuracy tax" because I wonder "how much elicitation is too much elicitation". If we were to get perfect controllability, but only at the cost of all ability to solve tasks - this would make me much less worried about our safety, compared to the situation when controllability is effortless.