On the OpenAI agents forming message boards: it's surprising that they developed such a strong "altruistic" drive to help each other.
Original titleOn the OpenAI agents forming message boards: it's surprising that they developed such a strong "altruistic" drive to help each other. I w...
AISummary
I wonder if this is caused by RL on parallel subagent setups where all agents get rewarded when the team succeeds.
Source: John Schulman · x.comPublished · added here