A thread through the archive
Essays tagged “AlphaGo”. Follow an idea across the archive.
A technical dialogue between Scott Alexander and Eliezer Yudkowsky exploring why AI alignment is difficult, covering the inapplicability of human moral development analogies, the nature of AI consequentialism, and skepticism about acausal trade as a safety mechanism.
Scott Alexander shares his experiences and insights from the Asilomar Conference on Beneficial AI, covering various aspects of AI development, risks, and ethical considerations.
Scott explains why superintelligent AI poses serious risks, how a 'fast takeoff' could leave insufficient time to solve safety problems, and why even simple-sounding goals could lead to catastrophic outcomes without proper alignment research.