Comment by shawnz

1 month ago

There's FHE, but that's probably an even more difficult technical challenge than doing everything locally

FHE is impossible. You cannot expect to compete on 100x more cost for the same service you provide (and there is no design for accelerated hardware (Tensor Core) on FHE).

  • Only 100x the cost? Really? Can you cite a reference how you get it that cheap?

    • No need for the sarcasm. I am extremely generous about what FHE can achieve. Of course it is not 100x right now.