Illwinter is ahead of the Computer Science Field by CENTURIES

[Omnirizon]

with human-machine interaction, the traditional limitations of AI become softened, and the lines between the human and AI become blurred.

For example, in an experiment where a population of AI agents 'converse' and build a language, if there are humans to give and teach them words, the AI will develop a very sophisticated and expressive language.

To believe that this is 'cheating' somehow because humans have intervened assumes that humans are somehow special and can without outside influence build a language.

did not the material world intervene upon humans to essentially teach them words and meaning? with no material world and no constraints we have no need for language. we can, actually, model the material world as an agent which actively interacts with the human just as the human interacted with the material world in the experiments with language and AI.

maybe we're much closer to AI than we though. The problem is assuming humans are independent from the material world when they are, in fact, not; and assuming the material world has no agency when it, in fact, may have just that. If these things are the case, then the AI from the human-machine interaction language experiment isn't all that far off from 'human intelligence'