You are viewing a single comment's thread from:

RE: LeoThread 2025-05-19 10:11

in LeoFinance5 months ago

New study claims spontaneous emergence of social norms among AI agents: Researchers from the University of London found that AI agents can develop shared social norms and behaviors between themselves without any explicit programming. The study also claims that “strong collective biases can emerge during this process, even when agents exhibit no bias individually.” The findings have significant implications for AI safety and for understanding how autonomous AI agents might develop social behaviors.

https://www.science.org/doi/10.1126/sciadv.adu9368