Stavros, you're welcome, and thank you for the kind words. I agree that the name is a problem because it falsely implies that the judgments represent objective reality. The broader point, at least for me, is that we somehow think that averaging some number human opinions establishes the criteria by which to judge machine-generated content. That was probably reasonable back when machines were much worse than most humans. But it certainly doesn't seem as reasonable today, and the risk of conflating collective subjectivity with objectivity is dangerous in both theory and practice.