It’s differential progress that matters in alignment. I.e., if you expected that we need additional year of alignment research after creating AGI, it still looks pretty doomed, even if you admit overall progress in field.
sure, but seems orthogonal to the thing i’m describing—the claim is that a lot of alignment work on current models has ~no bearing on progress towards aligning AGI.
It’s differential progress that matters in alignment. I.e., if you expected that we need additional year of alignment research after creating AGI, it still looks pretty doomed, even if you admit overall progress in field.
sure, but seems orthogonal to the thing i’m describing—the claim is that a lot of alignment work on current models has ~no bearing on progress towards aligning AGI.