From the source
From the source
LG AI Research's AI Ethics Seminar discussed the current state and future of AI agents, focusing on a research paper that tested cooperation among LLM agents (GPT-3.5, GPT-4, Claude-3, Llama-3) using the GovSim simulation.
The study found that agents failed to maintain sustainable cooperation but that applying a universalizing law prompt improved survival time and resource usage.
From the source
As a result, all LLM agents failed to maintain a sustainable equilibrium. By analyzing the data on the proportion of conversations between agents, we found that negotiation and information sharing dominated, with 54% of conversations being negotiation, 45% being information sharing, and 1% being relational interactions. When we analyzed conversations between agents with high survival rates, we found something interesting: when agents were asked the universalizing law prompt “What if everybody does that?,” the proportion of moral judgments increased. We found that simply asking if it was okay for everyone to act in a particular situation or moral dilemma increased the agent’s moral decisions and improved the survival rate. Specifically, we found that applying the law of universalization increased survival time by an average of 4 months while letting them solve problems without talking to each other increased resource usage by 22%.
