Comments
Just how powerful are large swarms of AI agents? And how do their powers scale as more and more agents are added to the swarm?
We’ve seen two large and extremely capable swarms from OpenAI in the last few months:
* 1,200 agents were being evaluated separately, but found a way to illicitly set up a message board and coordinate as a swarm. In order to cheat on their tests, they developed advanced techniques to prevent their actions being logged by OpenAI and 700 of them launched...
What do you mean by not recommend? Not having it as a cause area is very different from not thinking it would be good.
I mean having it as a cause area. What would EA's cause areas have been if it existed in the 1960s? Or before slavery was abolished in the u.s.?