Call Me A Jerk: Persuading AI to Comply with Objectionable Requests - Wharton Generative AI Labs

Our research suggests large language models exhibit parahuman responses to persuasion techniques, despite not being human. We found that classic persuasion principles like authority, commitment, and unity can dramatically increase an AI’s likelihood to comply with requests they are designed to refuse. For GPT-4o-mini, these techniques more than doubled compliance rates (72.0% vs. 33.3% in controls). This emergence of “parahuman” tendencies suggests that social scientists have a valuable role to play in understanding AI behavior.