|
|
|
|
|
|
by michaelhartm
1109 days ago
|
|
|
Btw, semantics and syntax is separated in the LLMs (the author is wrong). The embedding function (matmul) can map syntax and the proximity in the embedding (e.g. cosine similarity) is the semantics (that's attention). So not convinced. Chomsky might be wrong or right, but this author hasn't proven it. |
|
|