Introducing LinuxArena

·Redwood Research··

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 AI deployments by assessing AI’s sabotage capabilities, assessing control mitigations such as monitoring, and developing novel control techniques. This post will cover what LinuxArena is and ...

Read full article →

Related Articles

Claude's malicious compliance and normalization of deviance
Steff · LessWrong · 39m ago
SFT Drives Gemini’s Safety Properties
Josh Engels · Alignment Forum · 22d ago
Sequent: scale and automation for higher confidence in alignment
Geoffrey Irving · Alignment Forum · 25d ago
A Mike's-Eye View of ARC's Research
Michael Winer · ARC · 25d ago
My research: a computational cognitive neuroscience perspective on alignment
Seth Herd · Alignment Forum · 1mo ago