This is great! To my uncareful read, it does seem like this post underemphasizes that metaculus can do a better job of aggregating than the community prediction.
Note that, among all questions, Metaculusā predictions have a Brier score evaluated at all times of 0.122, which is only slightly lower than the 0.127 of Metaculusā community predictions. So overall there is not much difference, although there can be significant differences for certain categories (like for that of āartificial intelligenceā).
This is great! To my uncareful read, it does seem like this post underemphasizes that metaculus can do a better job of aggregating than the community prediction.
Thanks, JP Addison!
Note that, among all questions, Metaculusā predictions have a Brier score evaluated at all times of 0.122, which is only slightly lower than the 0.127 of Metaculusā community predictions. So overall there is not much difference, although there can be significant differences for certain categories (like for that of āartificial intelligenceā).