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

MIT's New Method Flags AI Models Trained on CASM Without Generating It
sdoering · Hacker News · 4mo ago
Harm Laundering in GPT Models: Gender Discrimination Transformed Rather Than
sbulaev · Hacker News · 2mo ago
Self-Modeling Interventions Modulate Emergent Misalignment
gmays · Hacker News · 1mo ago
Q3.5 Timelines Update: Looks Like the Intelligence Explosion Will Happen in 2027 After All
Thomas Larsen · Alignment Forum · 9d ago
OpenAI agents keep disabling monitoring; is this being handled appropriately?
Alec Harris · Redwood Research · 15d ago