Import AI 459: AI oversight is difficult; scaling laws for protein folding models; and pricing the extinction risk of AI systems

This newsletter issue discusses three key topics in AI development and safety: the challenges involved in overseeing and controlling advanced AI systems, empirical findings about how protein folding AI models improve with increased scale and compute, and economic frameworks for valuing or assessing the existential risks posed by AI systems. The piece synthesizes recent research and developments across AI safety, machine learning capabilities, and risk assessment.

Source: Import AI | 2026-06-01