Larry’s Reviews > Concepts: Where Cognitive Science Went Wrong > Status Update

And IF Pinker had gotten his data straight, he could only buy claim 2, but he did not even get his data straight!

Against Pinker (1989): if there is bootstrapping from semantics to syntax, the semantic concepts doing the work like agent, possession, etc, must be detectable by the child. But those concepts are ill-defined. Consider: “red” expresses a property; is that a semantic fact, or a byproduct of the fact that it’s a modifier of nouns? Contrast Gleitman (1990), who runs the bootstrapping argument the other way around

This is a very alienating experience because I really don’t like his views but I’m incapable of forming a coherent or convincing argument against them

Putnam: you have analyticity at the edge of the web of belief, where analyticity dissolves into one-criterionhood. But that presupposes analyticity (or synonymy—which are the same thing per Quine).

The doorknob argument: if doorknob is not innate (as a concept), then it has to be learned; learnability relies on nomic relations, but… seriously? Nomic relations about DOORKNOBS? Ok, then it’s innate. But… seriously?

It’s fun to read but he doesn’t know his Frege