AI ALIGNMENT FORUMTags
AF

Coherence Arguments

•

Applied to The "Measuring Stick of Utility" Problem by Multicore at 16d

•

Applied to Understanding Selection Theorems by adamk at 1mo

•

Applied to Deriving Conditional Expected Utility from Pareto-Efficient Decisions by Thomas Kwa at 2mo

•

Applied to When Most VNM-Coherent Preference Orderings Have Convergent Instrumental Incentives by Alex Turner at 1y

•

Applied to Is there a "coherent decisions imply consistent utilities"-style argument for non-lexicographic preferences? by Multicore at 1y

•

Applied to Comment on Coherence arguments do not imply goal directed behavior by Multicore at 1y

•

Applied to Coherent behaviour in the real world is an incoherent concept by Multicore at 1y

•

Applied to Three ways that "Sufficiently optimized agents appear coherent" can be false by Multicore at 1y

•

Applied to Coherence arguments imply a force for goal-directed behavior by Multicore at 1y

•

Applied to Coherence arguments do not entail goal-directed behavior by Multicore at 1y

•

Applied to Coherent decisions imply consistent utilities by Multicore at 1y

•

Applied to Do incoherent entities have stronger reason to become more coherent than less? by Multicore at 1y

•

Created by Multicore at 1y