> This post is mostly AI generated, of course with significant guidance, feedback, iteration and some edits from me. I can tell, because it is garbage. AI's notion of PK is useless because of Blum's speedup theorem. Because the invariance theorem fails in PR (PR is not universal), description-length gaps between PR and Turing complete languages can grow without bound. Essentially a more expressive formalism can encod…
Since the author seems to be concerned about tractable inductive inference, and to be honest computability does not give you much, what do you think about the utility of notions like resource-bounded Kolmogorov complexity for that?