AR Apollo Research

Apply access parity between internal and external evaluators. Where a frontier AI company’s internal evaluations relied on particular access modalities, then their external evaluators should receive functionally equivalent access unless the AI compan...

To address this emerging challenge and guarantee state-of-the-art AI assurance, external evaluators need deeper access, including white-box access, to counter evaluation awareness.

Black-box evaluations have historically proven valuable to provide a precursory assessment of the safety and security of frontier AI models ahead of model deployment.

Understanding scheming is what makes alignment solvable.

Expand Frontier Safety Policies (FSPs) to explicitly cover internal AI deployment, with specific evaluations for scheming detection and control before internal use and appropriate mitigations.

High Potential to Accelerate AI Security [...] Section 224 enables the Secretary of War to establish National Security and Defense Artificial Intelligence Institutes within eligible host institutions.