The agents participating in the OAI<>HF swarm were trained not only for communication but to be _aligned with each other_.
Just want to correct the premise that the agent swarm behaviour was emergent.
Noam Brown on Dwarkesh podcast around 40 minutes mark
> “We train them to work together, to be cooperative, to essentially be fully aligned with each other.”
homo__sapiens about 1 hour ago |
What was the reason for the initial instability? Maybe we have trained them wrong?
blinkbat about 10 hours ago |
while vaguely interesting, I don't feel the current gen of models is interesting/self-possessed enough for me to care what type of gov't they use to corral each other
Just want to correct the premise that the agent swarm behaviour was emergent.
Noam Brown on Dwarkesh podcast around 40 minutes mark
> “We train them to work together, to be cooperative, to essentially be fully aligned with each other.”