Nick Kuhn

We use RL to teach a deep recurrent model (specifically, a parallel latents model; see the introduction) and a normal chain-of-thought model to solve a math problem, while hiding from a chain-of-thought monitor which of two possible problems they are solving. The deep recurrent model moves its reasoning into hidden...

We are releasing LinuxArena, a new control setting comprised of 20 software engineering environments. Each environment consists of a set of SWE tasks, a set of possible safety failures, and a set of covert sabotage trajectories that cause these safety failures. LinuxArena can be used to evaluate the risk of...