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...
From The Wise Man's Fear by Patrick Rothfuss
We choose what thing we do and how we do them. I aspire to do good things in a good way.
By Eliezer Yudkowsky.
For me, it evokes the similar aesthetics of virtuousness as above.