Comment by layer8
16 hours ago
It’s nonzero, because they carry state while performing inference, and in the surrounding processes like chain-of-thought and mixture-of-experts.
16 hours ago
It’s nonzero, because they carry state while performing inference, and in the surrounding processes like chain-of-thought and mixture-of-experts.
I think they have working memory but not short term memory. I suppose that's pedantic or anthropomorphizing but it feels like I felt tbh