brypto

I’m now convinced if you need to run an LLM agent in a decentralized setup to control a large treasury, you can’t prevent griding to find a cooked prompt.

Andrew miller pointed out single TEE works but if we can’t allow that, then I don’t see a viable solution.

I’m not sure how you could prevent grinding a decentralized AI model.

if you run a deterministic model in consensus, the state has to be public (nodes have to be able to enter and exit the network), you can always grind a prompt outside of the protocol.

How do you prevent this…

EulerLagrange.eth - bank/acc (Hersh)

I’m now convinced if you need to run an LLM agent in a decentralized setup to control a large treasury, you can’t prevent griding to find a cooked prompt.

Andrew miller pointed out single TEE works but if we can’t allow that, then I don’t see a viable solution.

https://x.com/euler__lagrange/status/1873833137551069467?s=46

Pragmatism (Security) at OP Labs.
Prev: ConsenSys & Coinbase.

Attribs: Friendly, curious, introverted, mid-witted.
Chans: /eth-security /maurelian /stoicism




Working on building zkTLS infra/products. A ruthless empiricist and meme connoisseur.

/opacity
/eulerlagrange

IIUC, I suspect that TOS is a lot like any smart contract: if you’re gonna put it on chain, you can’t afford to have any bugs. Seems unrealistic in an LLM.