Thread

1. est · 1790053066 · focus · HN ↗

   It seem that everyone is getting into details of how transformers work, but I am more interested in why other setups didn't work.

   Or is it?

   1. fithisux · 1790077125 · focus · HN ↗

      Because that is what experiments suggested and what current computational power can compute.

      There is not much theoretical explanation yet. Or why others do not work.

      Hand-waving mostly.

Unofficial Hacker News client; not affiliated with Y Combinator.