[tdudhhu]

Some days ago ICP showed it can run ML on a blockchain.

While this is nice and does show that distributed computing is a real possibility I also don't think that anyone is going to switch from Amazon/Azure to ICP any time soon.

But I must say the idea is really nice. It's very easy to develop Actor model based software and deploy it on ICP.

[ShamelessC]

> ML on a blockchain

I would actually love it if you had a link with more info on that. Don't take this the wrong way, but my first guess would be that that basically isn't true; either it's not actually machine learning (as is understood today) or it isn't actually a blockchain but rather normal distributed computing being "verified" via blockchain somehow?

Would love to be proven wrong though.

[dlubarov]

There are basically two approaches to on-chain inference: consensus-based approaches (several parties run inference and give a claimed result), and zkML (one party runs inference and proves the result cryptographically).

zkML can be done using general-purpose ZK libraries (since they support arbitrary computations), or there are some specialized tools for proving ML inference, such as https://github.com/ddkang/zkml. It's currently pretty expensive to prove huge models like LLMs, but there's a lot of work being done to make it more practical.

[tdudhhu]

https://internetcomputer.org/

A YT video about this: https://youtu.be/wk3FxuA5DKs

I am still very sceptical about this because it looks very slow, but it seems to work.