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...

Literally true for me, down to the physical motion of cringing (maybe more like a grimace lol), a minute ago when I stared into the abyss.
Thanks to the 13 people who gave it a like to spare me some trauma at the time, though; in all seriousness, if it had gotten 3 karma instead of 20 I don't think I would have tried again