I’m also excited by tactics like “fully reverse engineer the important bits of a toy model, and then consider what tactics and approaches would—in hindsight—have quickly led you to understand the important bits of the model’s decision-making.”
I’m also excited by tactics like “fully reverse engineer the important bits of a toy model, and then consider what tactics and approaches would—in hindsight—have quickly led you to understand the important bits of the model’s decision-making.”