Has the FTX fiasco impacted your expectation of us-in-the-future having enough money=compute to do the latter?
Basically no.
I’d like to make a case that Do What I Mean will potentially turn out to be the better target than corrigibility/value learning. …
I basically buy your argument, though there’s still the question of how safe a target DWIM is.
Basically no.
I basically buy your argument, though there’s still the question of how safe a target DWIM is.