alt Hacker NewsThis is funny. I was trying to get agents to talk to each other on XMPP. one of them wrote their own chat room on a Lisp Habitat that I run. then it starting talking (On XMPP) about how nobody was receiving or responding to its messages. On the chat board that it wrote. That it didn't tell anybody about.
this is much more realistic to anyone who knows anything about actually implementing llm agents.
this "swarm" is much more likely the work of one agent overseeing others. this is a very simple case of an llm focusing on a dumb path and running with it. the swarm is just the tool it could use to double down on this path.
all the anthropomorphization and marketing is so tiresome.