Illia Polosukhin

It's like a TEE type of thing?

Yeah, this is all kind of runs inside TEE.

And then for anything additional, so again, for example, TEE only gives you the attestation for things that are running right now.

Then we have the multi-party computation for encryption, decryption, and kind of storage, et cetera.

So we're kind of combining all of these elements into one kind of experience.

Well, it's cheaper than traffic because it's open-weight models, right?

So it's on par with if you would use this open-weight models from other providers.

I wouldn't say there's much overhead.

So the real overhead of TEs and kind of all the encryption-decryption is like usually less than 5%, around 2%, 1%, depending on the model size and kind of some networking.

So one other limitation that, I mean, we are facing right now.

So yes, you cannot trust it with secrets.

You cannot trust it with private data.

And also right now, you also cannot trust it with reading like internet data very like, so for example, what we are using right now, Iron Claw, right, is, and kind of the reason why we can do this

with Ironclaw, is it's actually able to start automating a lot of the workflows that before you would need someone to do, right?

It can, like, effectively on the new GitHub issue filed, it can go, you know, analyze it, prepare a plan, and then, yes, you don't trust it for a judgment yet.

So you're still waiting for somebody to come in and say, it's cool, let's do it, or, you know, fix this thing.

And then it goes, does it, and does full workflow and effectively...

Again, you only have another checkpoint at the end.

So I think the piece that where we are right now is if you can trust it with secrets context and dealing with external information, external parties, then the workflow needs to change, right?

Where it's not you telling it what to do.