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...
Hadn't seen it mentioned anywhere yet that Luigi Mangione (US person who killed a health insurance executive) was interested in EA. "He suggested I schedule group video calls as he really wanted to meet my other founding members and start a community based on ideas like rationalism, Stoicism, and effective altruism.”
https://www.nbcnews.com/news/rcna183996
Linking some prior discussion here -- the accused person's last name isn't spelled correctly in that quick take, so you may have missed it on search.
Ahhh got it, thanks! Funny how most of the comments there are trying to rationalize his affiliation with EA as "not EA" lol.