🖥️ 🖥️ 🖥️ AI agents are sensitive to nudges "These results point to an important and largely neglected safety concern: LLM agents can be behaviorally brittle under subtle changes in choice architecture, even in the absence of adversarial settings." M. Cherep, P. Maes, & N. Singh, AI agents are sensitive to nudges, Proc. Natl. Acad. Sci. U.S.A. 123 (25) e2537030123, https://doi.org/10.1073/pnas.2537030123. #OpenAccess #OA #Research #Article #AI #ArtificialIntelligence #Technology #Tech #ComputerScience #Academia