
"(My understanding of) What Everyone in Technical Alignment is Doing and Why" by Thomas Larsen & Eli Lifland
LessWrong (Curated & Popular)
00:00
A G I Allignment Strategy
C h a i is an academic research organization affilited with u c berkeley. Stuart wrote the book human compatible, in which he outlines his a g i allignment strategy. The basic idea of c i r l is to play a co operative game where both the agent and the human are trying to maximize the human's reward. Since the a g i has uncertainty, it will defer to humans and be corrigible. Other work that i liked is cluster ability in neural networks. Try to measure the modularity of neural networks by thinking of the network as a graph and performing the n cut.
Play episode from 29:14
Transcript


