0age
@0age
would love to learn more about the latest with deterministic / provable LLMs (is zkML the term?) LLMs as reproducible compilers, compression algos, embedded in smart contracts, proof that handlers aren’t larping as agents, etc etc who’s got the inside scoop here & can share some info to enlighten the rest of us?
5 replies
8 recasts
53 reactions
sam
@sam--
on unruggable agents: https://nousresearch.com/setting-your-pet-rock-free (nous x flashbots) https://phala.network/posts/truth-of-AI-Agent (prominent TEE infra shop) smol forum chat on the dstack framework used to impl that^ agent: https://collective.flashbots.net/t/dstack-speedrunning-a-p2p-confidential-vm/3876
1 reply
0 recast
3 reactions
sam
@sam--
as for leveraging inference on chain, this is still early but has a promising team (notably, anish) https://docs.ritual.net i admittedly haven't dug in here much yet to know what's solid & what's still handwavy
1 reply
0 recast
2 reactions
sam
@sam--
on zkml, there's not a tonnn of great info out there. mostly because it's not insanely practical today iiuc, but getting better as zk tech tree advances https://medium.com/@danieldkang/tensorplonk-a-gpu-for-zkml-delivering-1-000x-speedups-d1ab0ad27e1c worldcoin's the only ones in the scene I know of doing this stuff in prod. remco or dcbuilder would be good to talk to if you have specific ideas you wanna validate
0 reply
0 recast
1 reaction
