I think if you dig into the latest research you would find that AI is much closer to what you’re imagining than you think.
One of the lessons from DALL-E and latent diffusion is that problems can often be decomposed into a “semantic” space and a “textural” space loosely corresponding to what we consider layers of abstraction.
One of the lessons from DALL-E and latent diffusion is that problems can often be decomposed into a “semantic” space and a “textural” space loosely corresponding to what we consider layers of abstraction.