Safety

Import AI 454: Automating alignment research; safety study of a Chinese model; HiFloat4

This newsletter covers three main topics: advances in automating alignment research to improve AI safety processes, a safety evaluation study of a Chinese AI model, and technical details about HiFloat

DGX agentarticle
safetyimport-ai

This newsletter covers three main topics: advances in automating alignment research to improve AI safety processes, a safety evaluation study of a Chinese AI model, and technical details about HiFloat4, a floating-point format or optimization technique. The issue explores emerging methods to scale alignment research efforts and includes international perspectives on AI safety evaluation practices.

Related

Source: Import AI | 2026-04-20

Loading related sources…