Hacker News new | ask | show | jobs
by secondbreakfast 1175 days ago
Haven't thought of this. Couldn't you just give a model a way to constantly "chew" on something? Maybe an ever-ending loop of some sort of prompt stimulation?
2 comments

An even more fun experiment will be to have two models running in perpetuity, constantly talking to each other, but constructed to act as though they were two sides of the same model.
Some propagate that's more or less how the two halves of the human brain work.
Bingo! I'm lifting this idea out of Julian Jayne's theory of consciousness :D https://www.julianjaynes.org/about/about-jaynes-theory/overv...