Artificial Intelligence Clones

2025-01-28

AI Summary

This paper investigates the fundamental limitations of AI clones in accurately representing human personality for romantic matching and job recommendation. Method: We propose a k-dimensional Euclidean personality modeling framework, integrating noise-approximation analysis and stochastic matching game theory. Contribution/Results: We provide the first rigorous proof that, in high-dimensional personality spaces, the expected matching quality achieved through a finite number of face-to-face human interactions strictly surpasses that attainable by an infinitely large AI clone pool. Specifically, only two in-person meetings suffice to outperform the global search performance of state-of-the-art AI platforms. Our analysis reveals an intrinsic representational ceiling for AI clones—arising from irreducible personality ambiguity and contextual non-stationarity—and formally establishes the irreplaceability of direct human interaction in complex social matching. The work thereby delineates strict theoretical performance bounds for AI agents deployed in human relational domains.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Application Domains: Humanities & Computational Social Science
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large language models, trained on personal data, may soon be able to mimic individual personalities. This would potentially transform search across human candidates, including for marriage and jobs -- indeed, several dating platforms have already begun experimenting with training"AI clones"to represent users. This paper presents a theoretical framework to study the tradeoff between the substantially expanded search capacity of AI clones and their imperfect representation of humans. Individuals are modeled as points in $k$-dimensional Euclidean space, and their AI clones are modeled as noisy approximations. I compare two search regimes: an"in-person regime"-- where each person randomly meets some number of individuals and matches to the most compatible among them -- against an"AI representation regime"-- in which individuals match to the person whose AI clone is most compatible with their AI clone. I show that a finite number of in-person encounters exceeds the expected payoff from search over infinite AI clones. Moreover, when the dimensionality of personality is large, simply meeting two people in person produces a higher expected match quality than entrusting the process to an AI platform, regardless of the size of its candidate pool.

Problem

• AI Avatars
• Personality Representation
• Matchmaking Accuracy

Innovation

• AI Avatars
• Direct Interaction
• Personality Representation