logoalt Hacker News

BrtBytetoday at 5:33 PM1 replyview on HN

LLMs obviously aren't reproducing the internal cognitive process, but they might still capture some of the structural patterns that emerge from it


Replies

noslenwerdnatoday at 6:23 PM

Interestingly, there is some neuroscience research that transformer architecture resembles "cue based retrieval" in the human brain in some important ways.

https://www.sciencedirect.com/science/article/pii/S0749596X2...