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.
More from AGI Musings
- Labs Won't Share Safety Research: Reward Hacking Blocks New Releases — willccbb · 2026-08-08
- Zuckerberg on Beating Giants: Big Companies Lack Conviction, AI Mirrors Facebook's Disruption — r0ck3t23 · 2026-08-08
- Pedro Domingos: Research Freedom in Corporate AI Labs Never Lasts — pmddomingos · 2026-08-08
- Will AI Get Cheaper? Competition and Compute Costs to Offset Subsidy Loss — intellectronica · 2026-08-08
- Apple's 1987 Knowledge Navigator Video is Becoming Reality — LukeW · 2026-08-08
- Models trained to delegate and coordinate, security threat narratives overblown — dbreunig · 2026-08-08