Redwood Research proposes NLS depth to measure opaque serial reasoning in AI models

Redwood Research defines NLS depth, a measure of how much unverbalized serial computation an AI system can perform, building on Brown-Cohen et al.'s opaque serial depth.

The proposal counts only nodes that output natural language initialized from a pre-training prior as interpretable bottlenecks. Standard transformers scale with their layer count, while latent reasoning architectures would raise NLS depth sharply.