New Paper Proposes "AI 45° Law" for Safe and Capable AGI

CFGeek · x · 2026-08-31

CFGeek cites a new paper, "Towards AI-45° Law," proposing a guiding principle to balance AI safety and capability. Inspired by Judea Pearl's "Ladder of Causation," it introduces the "Causal Ladder of Trustworthy AGI" framework with three layers (Approximate Alignment, Intervenable, Reflectable) and defines five levels of trustworthiness, aiming to provide a systematic roadmap for trustworthy AGI.

Related event: New Paper Proposes "AI 45° Law" for Balancing Safety and Capability(2 posts)→

Original post →

More from Safety

Safety channel →