HN Explorer

6 comments

[ 5.0 ms ] story [ 32.3 ms ] thread
blinkbat
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
Agreed - they don't seen to have "agency" in them, or someone put a dog in them.
imenani
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
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.
imenani
That’s fair. Some of what happened in OAI<>HF incident was (mis)-generalisation and not directly trained for.

However, the article experiments with five agents. So it seems to assume even the small scale behaviour is emergent.

Also, “roles and structures” may well have been learned during training.

homo__sapiens
What was the reason for the initial instability? Maybe we have trained them wrong?