News for hackers. Stuff that matters.

A comment on Transformer learning explained: Coinductive guide to inductive transformer heads. Parent comment

Re:Transformer learning explained: Coinductive guide to indu... by adamnemecek on Tuesday February 28, 2023 @01:24PM (#34972850)
I will, this is the first approximation.
[ Parent | on HN ]
Re:Transformer learning explained: Coinductive guide to indu... by algeber on Tuesday February 28, 2023 @05:41PM (#34975963)
by the way, I have already had shuffle products implemented for years, but you ironically blocked me the other day before telling you more about it, as you know science always works faster when you stop the conversation -- chakravala
[ Parent | on HN ]