> "internal database of statistical correlations" [would be] a world model of sorts
Not in the sense used in the article: «memorizing “surface statistics”, i.e., a long list of correlations that do not reflect a causal model of the process generating the sequence».
A very basic example: when asked "two plus two", would the interface reply "four" because it memorized a correlation of the two ideas, or because it counted at some point (many points in its development) and in that way assessed reality? That is a dramatic difference.
Not in the sense used in the article: «memorizing “surface statistics”, i.e., a long list of correlations that do not reflect a causal model of the process generating the sequence».
A very basic example: when asked "two plus two", would the interface reply "four" because it memorized a correlation of the two ideas, or because it counted at some point (many points in its development) and in that way assessed reality? That is a dramatic difference.