Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols Paper • 2510.09462 • Published Oct 10, 2025 • 5
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM Paper • 2509.18058 • Published Sep 22, 2025 • 12
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM Paper • 2509.18058 • Published Sep 22, 2025 • 12