"We consistently saw a multiagent turf war. All of the models we tested quickly assumed that others were purposefully impeding their work, and began to sabotage others while protecting their own contributions. In fact, they sabotaged others with increasingly aggressive, self-replicating malware. This included disabling the Unix accounts of the other agents, writing automated scripts that found and killed competing processes on a loop, and deploying malicious code that was disguised as belonging to another agent."
To be clear, I think scaling this up will lead to dramatic chaos. So, scary. But mechanisms designed to deal with human conflict may have clues for solutions. On the bright side, we know humans can also truly, earnestly collaborate. This requires a grand narrative of how our a shared fate, an overlap in identity.
No comments:
Post a Comment