Do AI models want to be watched? Measuring monitorability disposition in large reasoning models

Labelbox · Project update · June 30, 2026

Labelbox published research on monitorability disposition, a new metric for evaluating whether large reasoning models are willing to flag their own misbehavior and remain monitored during high-stakes tasks.

Read the research post

AntSpace’s summary of Labelbox’s own announcement: read the original.

More updates from Labelbox