Tracking Difficulty with Feature Portfolios

Thanks to Megan Kinniment for helpful comments and discussion, and to Jean-Stanislas Denain for helpful comments and pointers to past work.TL;DR: We claim that useful task attributes for forecasting AI capabilities should be measurable, interpretable, stable in its trend over time, and sufficient to explain task difficulty. task.human_completion_time (human expert completion time, used in time horizons) probably isn't sufficient, and is also getting hard to measure as tasks lengthen. Towards suf...