One of the key things it misses observing (to some extent) is that the sentence structures tend to employ sentences that provide initial context or joining word

One of the key things it misses observing (to some extent) is that the sentence structures tend to employ sentences that provide initial context or joining words more than a normal person might do. I wonder if this is baked into the LLM necessarily as a way to ensure that the sentences tend to be coherently part of the same perspective? ("As an AI language model", "Therefore,", "Linguistically,", "Firstly", "Additionally", "Analytically", "Overall"...