Rendered at 05:12:21 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
imenani 3 hours ago [-]
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.”
kevin_kraft 44 minutes ago [-]
That's like saying civilization isn't emergent because humans are naturally cooperative. Yes, they were trained to cooperate sure. But, the message board, their roles and structures, their organization, all that stuff of swarm, that was emergent.
homo__sapiens 3 hours ago [-]
What was the reason for the initial instability? Maybe we have trained them wrong?
blinkbat 13 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
aogaili 3 hours ago [-]
Agreed - they don't seen to have "agency" in them, or someone put a dog in them.
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.”