The "AI" being discussed is mainly competent data mining and machine learning. If we stay at that level, then there are easily bigger shifts that we've adjusted to in the past.
But self-improving AI is truly on a different level, as is AI with human-level 'general intelligence'.
I hear ya on the data mining observation. I have been digging into 'applied' ML for the last two years or so and its painfully obvious how many articles are based on science fiction and not the current state of things (which appears to be mostly reinforcement learning)
But self-improving AI is truly on a different level, as is AI with human-level 'general intelligence'.