alt Hacker NewsHmm, could one instead of sending the model weights, send like, a merkle tree root for them, not exactly specifying the model, but at least demonstrating that the same model is used each time?
Hmm, could one instead of sending the model weights, send like, a merkle tree root for them, not exactly specifying the model, but at least demonstrating that the same model is used each time?
I feel like that'd have to be generated as a side effect of the computation somehow?