Great post. Arnold Kling has a good discussion of Kurzweil's predictions somewhere, but I haven't been able to find it by Googling.

I agree that Kurzweil did well, making a significant number of specific, non-obvious correct predictions. But how well does Kurzweil's ability here generalize to other predictions? Kurzweil was predicting developments in his own field 10 years into the future. He has an advantage that products often take >4 years to develop, and he has insider knowledge of what kind of products the big tech companies are talking about in-house. (So we could compare him to internal discussions of possible products at Microsoft or Apple, etc.).