BENGIO, Yoshua; MCDERMOTT, Matt; COHEN, Michael K.; MALKIN, Nikolay; FORNASIERE, Damiano; GREINER, Pietro; KADDAR, Younesse. Can a Bayesian Oracle Prevent Harm from an Agent?. SuperIntelligence - Robotics - Safety & Alignment, [S. l.], v. 2, n. 1, 2025. DOI: 10.70777/si.v2i1.13799. Disponível em: https://s-rsa.com/index.php/agi/article/view/13799. Acesso em: 18 may. 2026.