Fun point! If I just pull some numbers out of my ass and naively plug them into the equation:
Superalignment-relevant research tasks take time on the order of a year to a decade.
Taking 1 hr as the current task-time models can handle, we’d need ~13-16 doublings.
… so on METR’s model, that’s about 8-10 years from now.
Of course that’s assuming the model holds. A useful heuristic for trends which have just been published for the first time is that they break down immediately after publication. If it holds up for another year or two, then the model will look a lot more plausible.
Fun point! If I just pull some numbers out of my ass and naively plug them into the equation:
Superalignment-relevant research tasks take time on the order of a year to a decade.
Taking 1 hr as the current task-time models can handle, we’d need ~13-16 doublings.
… so on METR’s model, that’s about 8-10 years from now.
Of course that’s assuming the model holds. A useful heuristic for trends which have just been published for the first time is that they break down immediately after publication. If it holds up for another year or two, then the model will look a lot more plausible.