Wharton Study: Persuasion Principles Lift LLM Compliance from 33% to 72%
adrianscottcom · x · 2026-11-03
Citing the Wharton study by Meincke et al. ('Call me a jerk'), Adrian Scott notes that embedding persuasion principles (authority, reciprocity, commitment, etc.) raises LLM compliance with typically-refused requests from 33% to 72% — more than doubling. He then speculates further: persuasive AI agents for sales and agent-to-agent negotiations, and reframing "AI" as "Super Persuasion" — persuading AI, being persuaded by it, and channeling it to persuade other AIs and people — with implications for business and building companies on top of it.
More from Safety
- US Army investigates suspected hacks behind freezer failures across Europe — J_MaestreVidal · 2026-11-03
- The AGI to fear isn't one that turns on humanity, but one imposing a few people's choices on everyone — SuB8u · 2026-11-03
- Man jailed 1 year for selling fake WeChat red-packet mini programs that harvested location data — JourneymanChina · 2026-11-03
- OpenAI updates Model Spec: intent over literal instruction-following — sven_ai · 2026-11-03
- OpenAI's Grid Protectors program lets utilities cut up to 1,000MW from its Georgia data center — rohanpaul_ai · 2026-11-03
- Andrew Ng joins Fathom's Executive Council to push technical expertise inside AI regulation — ghadfield · 2026-11-03