zlacker

>>davidb+(OP)
Security is impossible. Therefore, "AI alignment" is impossible.

I'm not sure that even AGI is possible, per Bostrom's Self-Sampling Assumption.

>>ablyve+e3
> I'm not sure that even AGI is possible, per Bostrom's Self-Sampling Assumption.

Can you explain more? I’ve found a definition for SSA, but unsure how it applies to AGI…