causal

Real-time AI is the central bottleneck

Latency, measured as milliseconds to first token and time between subsequent tokens, is the key bottleneck for real-time AI applications such as conversation, translation, and robotics.

causalpending

Speaker

Gavin Uberti

Evidence Quote

“We measure it in 2 ways: first, the number of milliseconds between when you submit your response and when you get your first token back”

Source

Gavin Uberti - Real-Time AI & The Future of AI Hardware - [Invest Like the Best, EP.356]— Invest Like the Best
Created: 11/17/2026, 12:35:53 PM

Your notes

Loading notes...