Inference: The Recurring Cost
About this video
Training a model like GPT-4 costs tens of millions once. But every single query users send? That's a recurring cost, forever. Full video — Why AI Labs Are Obsessed With Inference Cost: https://www.youtube.com/watch?v=1HhONwIOHu8
From the video
More from The Tool Shelf
How Does DeepSeek Skip 98% of the COMPUTE?
Three Escape Routes From Nvidia. Which Lands FIRST?
Can DeepSeek Make the Export Ban IRRELEVANT?
AI's Newest Weapon: The Autonomous Data Center
Why Chinese Open Models Are Crushing AI Prices
DeepSeek Declares Independence from Nvidia: A New Era in AI Chip Innovation
Nvidia's Biggest Customers Are Plotting Their Escape
