Paper recorded by Signals 4 on 2026-09-29 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-29 on arXiv · recorded by Signals 4 on 2026-09-30
Category: cs.AI · 人工智能 · first seen 2026-09-30
Risk aversion in resources could prevent misaligned AI agents from causing catastrophic harm. Misaligned but risk-averse agents would tend to favor safer strategies like making deals with humans over riskier strategies like rebelling. We train agents to be risk averse through character training, finding that persona traits provide a robust mechanism for instilling risk preferences. To do this, we