Latent Space: The AI Engineer Podcast · Latent.Space
Owning the AI Pareto Frontier — Jeff Dean
·1 hr 24 min·5 clips
Jeff Dean reveals how Google balances frontier AI models with efficient, affordable ones to own the Pareto Frontier.
As heard by us
A clear look at how AI performance depends on moving data efficiently across the stack.
Jeff Dean's conversation reads less like a victory lap than a compact lesson in hardware and systems tradeoffs. It stays grounded in specifics: SRAM versus HBM, the cost of moving a parameter compared with the multiply itself, and the appeal of batch size one for latency even…
Why you'd press play
If you care why batching, memory, and latency keep shaping AI serving tradeoffs, press play.
Listen to the show on