BARNETT, Peter; THIERGART, Lisa. What AI evaluations for preventing catastrophic risk can and cannot do. SuperIntelligence - Robotics - Safety & Alignment, [S. l.], v. 2, n. 4, 2026. DOI: 10.70777/si.v2i4.17167. Disponível em: https://s-rsa.com/index.php/agi/article/view/17167. Acesso em: 21 may. 2026.