Tamsin Leake

i'm tammy, alignment researcher and founder of the Orthogonal alignment research organization.

i mostly work on the QACI alignment plan.

check out my alignment research here, as well as my blog and my twitter.

Wiki Contributions

Comments

one solution to this problem is to simply never use that capability (running expensive computations) at all, or to not use it before the iterated counterfactual researchers have developed proofs that any expensive computation they run is safe, or before they have very slowly and carefully built dath-ilan-style corrigible aligned AGI.

nothing fundamentally, the user has to be careful what computation they invoke.

an approximate illustration of QACI: