News for hackers. Stuff that matters.

A comment on Understanding Transformers via N-gram Statistics.

Re:Understanding Transformers via N-gram Statistics by bilsbie on Sunday May 18, 2025 @09:29AM (#44021292)
Interesting! Makes me wonder if you could replace transformers with some sort of fancy Markov chain. Maybe with a meta chain that acts as attention.
[ Parent | on HN ]

There are no comments on this comment yet.