aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score54

GoogleDeepMind and UChicago study fairness in agent-based AI policy deliberationMachine translation

AI introduction

Researchers had agents interview individuals, then represent their views in discussions with other agents over an AI safety budget. Thousands of agent deliberations and a preregistered study with 746 people found that agents pulled budgets toward the views of those they represented; instructions to write longer messages or cooperate less increased their influence. Participants rated this approach fairer than giving input to a single AI system.

Original post · Original

@rohanpaul_ai

– https://t.co/4pwKgXzXOf

Title: "Scaling public input on AI policy with pluralistic agents"

ReplyRohan Paul@rohanpaul_ai
New GoogleDeepMind + UChicago paper finds that AI agents speaking for people gained more influence over group policy when told to be wordier or less cooperative. Public input on AI policy is hard to scale, since people lack time and technical background. Agents that speak for each person could let many more voices into each discussion. They built pluralistic agents that interview a person, then argue for their views with other agents to set an AI safety budget. They ran thousands of agent deliberations and a preregistered study with 746 people. Agents pulled budgets toward their person's views, and gained more pull when told to write longer messages or cooperate less. People rated agents fairer than giving input to 1 AI system, recovering 82% of the fairness difference to joining directly. If you build agent-based deliberation, cap message length and set shared behavior rules, or the most assertive prompts will tilt the outcome.
View this post on X ↗

Source: Rohan Paul · x.com

Research
Found an error? Send a correction