Cutting-Edge AI Hardware
George shares his skepticism on federated training due to bandwidth limitations, emphasizing the efficiency of inference over training. He envisions enterprise adoption of high-performance, cost-effective training hardware, aiming to outperform existing solutions like the H 100 box for most use cases.In this clip
From this podcast

Latent Space - The AI Engineer Podcast (Video Podcast)
Ep 18: Petaflops to the People — with George Hotz of tinycorp
Related Questions