Alignment has a Fantasia Problem

arxiv.org · 12,372 words · saved by 1 readers

Modern AI assistants are trained to follow instructions, implicitly assuming that users can clearly articulate their goals and the kind of assistance they need. Decades of behavioral research, however, show that people often engage with AI systems before their goals are fully formed. When AI systems treat prompts as complete expressions of intent, they can appear to be useful or convenient, but not necessarily aligned with the users’ needs. We call these failures Fantasia interactions. We argue that Fantasia interactions demand a rethinking of alignment research: rather than treating users as rational oracles, AI should provide cognitive support by actively helping users form and refine their intent through time. This requires an interdisciplinary approach that bridges machine learning, interface design, and behavioral science. We synthesize insights from these fields to characterize the mechanisms and failures of Fantasia interactions. We then show why existing interventions are insuf

Alignment has a Fantasia Problem Nathanael Jo, Zoe De Simone 1 1 footnotemark: 1 , Mitchell Gordon, & Ashia Wilson Massachusetts Institute of Technology {nathanjo, zoed, mlgordon, ashia07}@mit.edu Authors contributed equally. Abstract Modern AI assistants are trained to follow instructions, implicitly assuming that users can clearly articulate their goals and the kind of assistance they need. Decades of behavioral research, however, show that people often engage with AI systems before their goals are fully formed. When AI systems treat prompts as complete expressions of intent, they can appear

Alignment has a Fantasia Problem

related reading