The Age of Agents: Can multiple LLM agents improve outputs? (sudoapps.substack.com) 2 points by sudoapps 3y ago ↗ HN
[–] sudoapps 3y 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 3y ago ↗ As in, a consensus network? IMO, yes. Is that scary? Yes. [–] sudoapps 3y ago ↗ Very similar to a consensus network. That is probably the future of LLM agents.
[–] sudoapps 3y ago ↗ Very similar to a consensus network. That is probably the future of LLM agents.
3 comments
[ 0.22 ms ] story [ 19.5 ms ] thread