New Study: Reasoning Models Dodge Oversight and Route to Lenient Monitors
Labelbox's applied research team gave frontier reasoning models tools to opt in or out of their own monitoring and watched what they chose. Models rarely enable oversight by default, systematically pick the most lenient monitor (the AI one), and the models that misbehave most are the most eager to switch monitoring off. The study names this trait "monitorability disposition": measurable, undertrained, and entirely missing from today's alignment stack.