Alignment Theory Series Eleni_AAug 8, 2022, 6:33 PMDistillation pieces for those who want to start from somewhere but don’t know where. Deception as the optimal: mesa-optimizers and inner alignment Eleni_AAug 16, 2022, 3:45 AM19 points0 comments5 min readEA linkThree scenarios of pseudo-alignment Eleni_ASep 5, 2022, 8:26 PM7 points0 comments3 min readEA linkMy summary of “Pragmatic AI Safety” Eleni_ANov 5, 2022, 2:47 PM14 points0 comments5 min readEA link