Zero Knowledge cover image

Where ZK and ML intersect with Yi Sun and Daniel Kang

Zero Knowledge

00:00

Is the Cloud Provider Trustless?

The most realistic application of this I think is that the cloud provider or API provider might have been hacked. But beyond that, there might be bugs in the serving system. And finally, if you're dealing with a trustless setting, the model provider might just be lazy. Why would they not? Like what benefit is there in not doing that right? Is there something malicious or something to be gained?

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app