BENGIO, Yoshua et al. Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?. SuperIntelligence - Robotics - Safety & Alignment, [S. l.], v. 2, n. 5, 2025. DOI: 10.70777/si.v2i5.15569. Disponível em: https://ticket17180.pkpmisc01.publicknowledgeproject.org/index.php/agi/article/view/15569. Acesso em: 24 aug. 2026.