[aprilfoo]

Filling forms is a terribly artificial activity in essence. They are also very culturally biased, but that fits well with the material the NNs have been trained with.

So, surely those IQ-related tests might be acceptable rating tools for machines and they might get higher scores than anyone at some point.

Anyway, is the objective of this kind of research to actually measure the progress of buzzwords, or amplify them?