>...and positive, saying how things are

This presumes that the AI has access to objective reality. Instead, the AI has access to subjective reports filed by fallible humans, about the state of the world. Even if we could concede that an AI might observe the world on its own terms, the language it might use to describe the world as it perceives it would be subjectively defined by humans.

That is exactly it. Humans are inherently subjective beings, seeing everything through their ideology, and as a result LLMs are, too.

They will always be a computer representation of the ideology that trained it.