However, in the case of LLMs, such istheir power, things can get a little blurry. Whenan LLM can be made to improve its performanceon reasoning tasks simply by being told to “thinkstep by step” (Kojima et al., 2022) (to pick justone remarkable discovery), the temptation to seeit as having human-like characteristics is almostoverwhelming.

The weird way you tap or push a whole image of a page to the side—it’s the uncanny valley of page turning, not a simulation or replacement of it.

I wondered about that. But as you mention, the control flow makes it tricky, because it's not really a template literal — it's a DSL. I thought perhaps it's better to have something that's explicitly different, than something a bit 'uncanny valley'.