A Reputation Game Simulation: Emergent Social Phenomena from Information Theory
This work addresses the challenge of simulating social reputation dynamics for designing safer AI systems, though it is incremental relative to existing trust network literature.
The authors tackled the problem of simulating reputation dynamics in social communications by proposing a novel information update approach that accounts for knowledge uncertainty, using agents with information compression in finite memories, which led to emergent phenomena like echo chambers and deception symbiosis, and studied malicious strategies such as sycophancy and pathological lying to provide insights for safeguarding non-abusive AI systems.
Reputation is a central element of social communications, be it with human or artificial intelligence (AI), and as such can be the primary target of malicious communication strategies. There is already a vast amount of literature on trust networks addressing this issue and proposing ways to simulate these networks dynamics using Bayesian principles and involving Theory of Mind models. The main issue for these simulations is usually the amount of information that can be stored and is usually solved by discretising variables and using hard thresholds. Here we propose a novel approach to the way information is updated that accounts for knowledge uncertainty and is closer to reality. In our game, agents use information compression techniques to capture their complex environment and store it in their finite memories. The loss of information that results from this leads to emergent phenomena, such as echo chambers, self-deception, deception symbiosis, and freezing of group opinions. Various malicious strategies of agents are studied for their impact on group sociology, like sycophancy, egocentricity, pathological lying, and aggressiveness. Even though our modeling could be made more complex, our set-up can already provide insights into social interactions and can be used to investigate the effects of various communication strategies and find ways to counteract malicious ones. Eventually this work should help to safeguard the design of non-abusive AI systems.