Re:A global workspace in language models
by ike_a on Tuesday July 07, 2026 @12:18AM
(#48813618)
Not my wheelhouse, but I was wondering if these structures generalize beyond language.
LLMs and Humans have language in common. Is it plausible these structures could be a result of the way languages work more than generic intelligence? (Do we see anything similar e.g. in vision or other non language models?)
LLMs and Humans have language in common. Is it plausible these structures could be a result of the way languages work more than generic intelligence? (Do we see anything similar e.g. in vision or other non language models?)