Applications
🚨Our paper is out in PNAS: we found classic human persuasion techniques worked on AIs in a 'parahuman' way, making them agree to objectiona…
🚨Our paper is out in PNAS: we found classic human persuasion techniques worked on AIs in a 'parahuman' way, making them agree to objectionable requests (upping compliance from 35% to 51%) It worked on
🚨Our paper is out in PNAS: we found classic human persuasion techniques worked on AIs in a "parahuman" way, making them agree to objectionable requests (upping compliance from 35% to 51%) It worked on a range of major LLMs though newer models resist more https://www.pnas.org/doi/10.1073/pnas.2535868123
Source: Ethan Mollick (X) | 2026-05-19