from Hacker News

The Age of Agents: Can multiple LLM agents improve outputs?

by sudoapps on 5/30/23, 5:14 PM with 3 comments

  • by sudoapps on 5/30/23, 5:14 PM

    This was a quick experiment on creating multiple LLM (GPT) agents with their own objective to see if outputs can be improved.
  • by scrum-treats on 5/30/23, 8:15 PM

    As in, a consensus network? IMO, yes. Is that scary? Yes.