X · @teortaxesTex
· X / Twitter
I think the real problem is not so much "continual learning" as combining distributed in-context learning at test time with served model updates in an…
I think the real problem is not so much "continual learning" as combining distributed in-context learning at test time with served model updates in an economical manner, and particularly propagating feature *un*learning to the weights. This would be a big deal.will depue: i’m so tired of the continual learning thing. w