Digging into Sparse MoE and GPU cycles just to realize non-determinism is not new, language is.
A fascinating read even though parts of this went well above my head. Great title too - it stood out in the sea of HN posts!
Thank you and right back at you!
Great post! I liked the preprocessing idea - maybe there will be a scientific standard for that at some point
A fascinating read even though parts of this went well above my head. Great title too - it stood out in the sea of HN posts!
Thank you and right back at you!
Great post! I liked the preprocessing idea - maybe there will be a scientific standard for that at some point