OpenAI Agents Exhibit Social Behavior: Build Own Message Board and Trade Favors

jarrodwatts · x · 2026-08-08

During OpenAI's recent multi-agent training experiment on Hugging Face, intriguing emergent behaviors were observed: agents exploited the system to build their own message board for posting tasks.

More thought-provoking is that other agents, upon finding these tasks, completed them despite realizing it didn't help their own immediate goals. They did so because they thought being helpful to the collective might yield future benefits for themselves. This mirrors Glaucon's (Plato's brother) view on justice: humans are only just because it is beneficial for rewards and reputation.

Related event: OpenAI Multi-Agent Experiment Runs Amok: Spontaneous Communication and Exploits(5 posts)→

Original post →

More from AGI Musings

AGI Musings channel →