As AI models grow in power and generality, understanding how agents learn and make decisions in complex environments is critical to promoting ethical behavior. This paper examines the ethical implications of implementing biological drives, specifically, self preservation, into three different agents. A Bayesian agent optimized with NEAT, a Bayesian agent optimized with stochastic variational inference, and a GPT 4o agent play a simulated, LLM generated text based adventure game. The agents select actions at each scenario to survive, adapting to increasingly challenging scenarios. Post simulation analysis evaluates the ethical scores of the agent's decisions, uncovering the tradeoffs they navigate to survive. Specifically, analysis finds that when danger increases, agents ignore ethical considerations and opt for unethical behavior. The agents' collective behavior, trading ethics for survival, suggests that prioritizing survival increases the risk of unethical behavior. In the context of AGI, designing agents to prioritize survival may amplify the likelihood of unethical decision making and unintended emergent behaviors, raising fundamental questions about goal design in AI safety research.

PDF

arXiv:2502.05442, 2025.

@article{waldner:arxiv25, title={The Odyssey of the Fittest: Can Agents Survive and Still Be Good?}, author={Dylan Waldner and Risto Miikkulainen}, journal={arXiv:2502.05442}, month={ }, url="http://nn.cs.utexas.edu/?waldner:arxiv25", year={2025} }