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

Loss of Oversight: How AI Systems May Become Harder to Audit, Monitor, and Investigate
Jordan Taylor · LessWrong · 34m ago
The Case for Evaluating Model Behaviors
jsteinhardt · Alignment Forum · 20h ago
Mechanistic estimation for expectations of random products
Jacob Hilton · ARC · 5d ago
Multipolar Civilisation Depends on Maintaining an Attacker’s Dilemma
Naci Cankaya · LessWrong · 14d ago
Using Base-LCM to Monitor LLMs
Éloïse Benito-Rodriguez · LessWrong · 14d ago