1 link tagged with all of: interpretability + nls depth + architecture + monitoring
Click any tag below to further narrow down your results
Links
Researchers propose a metric called NLS depth to quantify how much unobservable reasoning AI models can perform internally, separate from chain-of-thought outputs. This matters because architectural changes could let models do complex reasoning without showing their work, making them harder to monitor.
- Current chain-of-thought monitoring works because models are trained on human text, but new architectures could bypass this by performing reasoning in opaque hidden states instead of readable tokens.
- NLS depth measures the longest computational path that doesn't pass through natural-language outputs (tokens initialized from pre-training), making it possible to assess monitorability risk before a model is even trained.
- The metric deliberately ignores some post-training choices (like RLHF or distillation) to focus on architectural differences, distinguishing between standard transformers and genuinely concerning designs like full-bandwidth transformers that can hide reasoning across entire context windows.