Deepwatch

Keyboard shortcuts

Space or k
Play or pause
j and l
Back or forward 10 seconds
Left and right arrows
Back or forward 5 seconds
f
Fullscreen
m
Mute or unmute
Shift and < or >
Slower or faster
?
Show or hide this list

How to Scale AI Application Inference 100x ft. Fireworks’ Lin Qiao

Sequoia Capital, 10 min, 8.5K views, May 19, 2025

Show description

Lin Qiao explains why inference is a three-dimensional optimization problem across quality, speed, and cost that can unlock 10-100x improvements in AI app economics. Companies can achieve sustainable scale by aligning models with their real-world use cases. Subscribe to our Substack, Inference, to stay on top of the latest developments in AI: https://inferencebysequoia.substack.com/

When you're done