Why Not Try Build Safe AGI?

Copy-pasting from my one-on-ones with AI Safety researchers:

Why mechanis­tic in­ter­pretabil­ity does not and can­not con­tribute to long-term AGI safety (from mes­sages with a friend)

List #1: Why stop­ping the de­vel­op­ment of AGI is hard but doable

List #2: Why co­or­di­nat­ing to al­ign as hu­mans to not de­velop AGI is a lot eas­ier than, well… co­or­di­nat­ing as hu­mans with AGI co­or­di­nat­ing to be al­igned with humans

List #3: Why not to as­sume on prior that AGI-al­ign­ment workarounds are available