Re:Elegant and powerful new result that seriously undermines...
by photonthug on Friday September 22, 2023 @08:20PM
(#37619448)
Idk, one obvious reason could be that emergence is a mirage ( https://arxiv.org/abs/2304.15004 ). Given two concepts of roughly equivalent complexity and representation in training, where one is successfully generalized and another is not, that would seem to support (but not prove) the mirage hypothesis.
I take your point about representational differences though.
Thinking more about this, the OP is basically talking about whether models understand that equality commutes, and I suppose even an LLM that can add may not have worked out that addition commutes.
I take your point about representational differences though.
Thinking more about this, the OP is basically talking about whether models understand that equality commutes, and I suppose even an LLM that can add may not have worked out that addition commutes.