Thanks, yeah that list looks interesting!
nikos
Karma: 263
Contra papers claiming superhuman AI forecasting
Unit economics of LLM APIs
Mirror, Mirror on the Wall: How Do Forecasters Fare by Their Own Call?
The audio quality is incredible! How automated is the process vs. how much manual work are you putting in? Really appreciate what you’re doing, thanks a lot!
Comparing Two Forecasters in an Ideal World
Predictive Performance on Metaculus vs. Manifold Markets
Creating a database for base rates
This looks really cool! And it would be nice to get some version of this (or at least a link to it) on the Forecasting Wiki.
Agreed. I think a strong reason why this might work at all is that forecasters are primarily judged by some other strictly proper scoring rule—meaning that they wouldn’t have an incentive to fake calibration if it makes them come out worse in terms of e.g. Brier or log score.