Thanks for answering, that makes sense. Also - your setup seems like it could greatly benefit from speculative decoding. Have you guys given any thought to how that might work in this system?
P.s. for #2, you can probably do something like RAFT-styled interleaved computation. But this could get tricky unless you commit to a sharding scheme that makes it easier.
Hey, this is a super cool project. It's great to see a lot of the IPFS stuff resurfacing again.
A few questions:
1.) How does this handle privacy? If you're distributing compute this way then all actors in the compute graph will also know the sequence being computed.
2.) Any safeguards against malicious actors poisoning model activations?
Shopping is a major one, I've found so many useful things from TikTok that no other platform has successfully been able to show me. It's also superior for viral growth and easily marketing new services in pretty much every way.
P.s. for #2, you can probably do something like RAFT-styled interleaved computation. But this could get tricky unless you commit to a sharding scheme that makes it easier.