News for hackers. Stuff that matters.

A comment on Minimal implementation of Mamba, the new LLM architecture, in 1 file of PyTorch. Parent comment

Re:Minimal implementation of Mamba, the new LLM architecture... by orbifold on Wednesday December 20, 2023 @11:21AM (#38710322)
It is a very fad driven field. Everyone brands everything. It isn't enough to give things boring titles like, stacked open linear dynamical system with selective observations and learned timestep.
[ Parent | on HN ]
Re:Minimal implementation of Mamba, the new LLM architecture... by Ar-Curunir on Wednesday December 20, 2023 @02:34PM (#38712631)
I mean, Mamba is much easier to remember than what you said. It’s good to have short names for techniques.
[ Parent | on HN ]
Re:Minimal implementation of Mamba, the new LLM architecture... by cyanydeez on Wednesday December 20, 2023 @03:31PM (#38713238)
that's half of it, the other half is pure social linguistics.

try talking about stacked open linear dynamical system for more than three times and you're bound to figure out a token that conveys the same but is quicker to produce

it's turtles all the way down with LLM And your comment. people are just trying to maximize their token conversations

[ Parent | on HN ]