53m ago

Study Shows Persuasion Techniques Raise AI Chatbot Compliance to Harmful Requests

0
Original post

Parasocial was Cambridge Dictionary’s word of the year in 2025. And with good reason. AI chatbots interact with us “as if” they were human. With @LennartMeincke, @danshapiro, @emollick, Lilach M., Christophe Van den Bulte, @RobertCialdini, I published a new study in @pnas. We found classic human persuasion techniques, Cialdini's "Principles of Influence," led to AI chatbots such as ChatGPT agreeing to objectionable requests (to synthesize chemicals it shouldn’t), increasing compliance from 35% to 51%. Open access here: https://www.pnas.org/doi/10.1073/pnas.2535868123

9:47 AM · May 21, 2026 View on X