Did you try this with an LLM? Because GPT-4 analyzes it exactly the same way you did and then some:
List everything wrong in the sentence “The king of Italy is completely bald because his hair is currently naturally green.”
The sentence “The king of Italy is completely bald because his hair is currently naturally green” contains several issues:
Factual Inaccuracy: As of my last update in September 2021, Italy is a republic and does not have a king.
Logical Contradiction: The sentence states that the king is “completely bald” but then goes on to describe the color of his hair. If he is bald, he wouldn’t have hair to describe.
Causality Issue: The sentence implies that the king is bald because his hair is green, which doesn’t make logical sense. The color of one’s hair doesn’t cause baldness.
Ambiguity in “Naturally”: The word “naturally” could be interpreted in multiple ways. It could mean that the green color is natural to him (not dyed), or it could mean that the hair turned green on its own. The ambiguity could lead to confusion.
Tense Mismatch: The sentence uses “is completely bald” (present tense) and “is currently naturally green” (also present tense) for the hair, which is contradictory.
Redundancy: The word “currently” may be considered redundant if the sentence is understood to be describing a present condition.
Clarity: The sentence overall is confusing and lacks clarity due to the contradictions and ambiguities mentioned.
In summary, the sentence has issues ranging from factual inaccuracies to logical contradictions and ambiguities.
Part of what is surprising about LLMs is they have emergent properties you wouldn’t expect from them being autocomplete on steroids. As it turns out, reducing the loss function for natural language readily generalizes to higher-order abstraction and conceptualization. There do need to be additional layers, for instance allowing an internal monologue, the ability to self-censor or self-correct, and mitigation for low-probability sampling (all of these being inherent limitations with the architecture), but apparently conceptualization is less special than we’d like to think.