Barrett, A. (2024) “Benchmark Early and Red Team Often: A Framework for Assessing and Managing Dual-Use Hazards of Ai Foundation Models”, AGI - Artificial General Intelligence - Robotics - Safety & Alignment, 1(1). Available at: https://agi-rsa.com/index.php/agi/article/view/10601 (Accessed: 18 October 2024).