I'm not sure who claimed the brain was a "predictive engine" or what that means exactly. The OP specifically referenced predictive coding which describes precisely what is meant, and has empirical support.
If you meant this as a comparison to machine learning, then a predictive coding model closely matches.
My former claim is that everything in the natural world can be reduced to statistics, so saying meaning cannot be derived "because statistics" is a very poor argument.
The second is a theory for the underlying mechanisms of the brain.
> Your argument against deriving meaning from statistics completely ignores that the brain also works this way.
The brain is not predicting it's compressing.