Tech · Alignment Forum
An operationalization of opaque serial depth
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Currently, chain-of-thought (CoT) is a valuable tool for overseeing AI models.
Key facts
- Natural language prior: The intermediate representation is directly optimized either (1) to imitate human-written text (e.g
- No expansion of the output space: The nodes only represent tokens from an output space in which virtually [8] all tokens have been initialized from the pre-training prior, or have individually
- To make this notion more precise, they define the concept of natural-language-rooted nodes (NL-rooted nodes) in a computation graph
- All of these techniques would be implemented by expanding the output space. [9]
Summary
Their measure is a specific instantiation of the notion of “opaque serial depth”, originally defined in a recent paper from GDM ( Brown-Cohen et al, 2026 ). To measure the opaque serial depth of a computation, Brown-Cohen et al. propose measuring the longest path in the computational graph which doesn’t pass through some form of “interpretable bottleneck”. Their main contribution in this document is a particular standard for what counts as an “interpretable bottleneck”. To make this notion more precise, they define the concept of natural-language-rooted nodes (NL-rooted nodes) in a computation graph. Given this definition of NL-rooted nodes, they call their corresponding notion of opaque serial depth “Natural-Language-rooted node”-Separated depth (NLS depth). Tracking the NLS depth of AI systems is not a replacement for tracking monitorability or no-CoT capabilities; it is an important complement.