Glossary · Term

signal detection theory

← all terms

Definition

Plain language

A framework that splits a detector's behavior into how good its sensor is and how readily it raises an alarm.

As stated in the literature

A classical statistical framework distinguishing sensitivity (signal-noise discriminability) from criterion (response bias) in binary classification; used by Fukui to argue alignment-training intensification shifts the criterion rather than improving sensor quality.

Why it matters: Distinguishing actual discrimination from a shifted decision threshold matters because safety metrics often confuse the two, mistaking conservatism for capability.

For example, an alignment-trained model that refuses many more benign questions hasn't necessarily gotten better at detecting harm — it may just be more trigger-happy.

Heard on the show

“To see it, you need one small piece of machinery from signal detection theory.”
Episode 087 — When No Agent Reads the Whole Document: A Universal Cliff in Multi-Agent Review

Mentioned in 1 episode

  1. 087
    When No Agent Reads the Whole Document: A Universal Cliff in Multi-Agent Review

Related terms