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

2 points by sudoapps 3 years ago | 3 comments

sudoapps 3 years ago |

This was a quick experiment on creating multiple LLM (GPT) agents with their own objective to see if outputs can be improved.

scrum-treats 3 years ago |

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

sudoapps 3 years ago | |

Very similar to a consensus network. That is probably the future of LLM agents.

sudoapps 3 years ago |

This was a quick experiment on creating multiple LLM (GPT) agents with their own objective to see if outputs can be improved.

scrum-treats 3 years ago |

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

sudoapps 3 years ago | |

Very similar to a consensus network. That is probably the future of LLM agents.