Skip to content
Live
Trending storyPast story

Redwood Research releases simulation control evaluation method

1 reports1 outlets26 days agoUpdate

The story so far

AI overview

Redwood Research has released the Simulated Control Evaluation (SCEs) method, used to test whether AI monitors can intercept harm intentionally caused by models in an environment close to real deployment. The method involves using an LLM simulator to execute attack model tool calls and letting the LLM judge whether the attack is successful, with the gap to real-world testing being approximately the same as the gap between two independent real runs. SCEs perform faithfully in verifiable scenarios and can significantly improve the representativeness of control evaluations for deployment, but long-term multi-agent attacks remain a limitation.

AI-written from the reports · Updated 26 days ago

Coverage timeline

Follow the coverage to see every side of the story.

24 Oct
  1. Redwood Research
    Simulated Control Evaluations

    Redwood Research has released the Simulated Control Evaluation (SCEs) method, used to test whether AI monitors can intercept harm intentionally caused by models in an environment close to real deployment. The method involves using an LLM simulator to execute attack model tool calls and letting the LLM judge whether the attack is successful, with the gap to real-world testing being approximately the same as the gap between two independent real runs. SCEs perform faithfully in verifiable scenarios and can significantly improve the representativeness of control evaluations for deployment, but long-term multi-agent attacks remain a limitation.