Two Axes of Alignment: A Framework for Robust Superintelligence Alignment

1. SummaryI classify alignment research along two axes: forward-chaining vs. back-chaining reasoning and extrapolative vs. invariant justification of the safety property in question. I argue that extrapolation is insufficient to justify confidence that the safety property will hold while crossing into the superintelligence capability level, whereas an invariant justification is necessary. I also claim that while forward-chaining from current models may give us useful safety properties and even l...