About this session
What changes when intelligence becomes fast enough to sit inside an everyday interaction? Join Vercel, TypeSafe AI, and Cerebras for a conversation about inference speed, model behavior, and the experience of building responsive AI applications. The panel brings application infrastructure, model development, and compute into the same discussion.
What you’ll take away
- Connect inference latency to application design.
- Consider speed and model quality as complementary engineering decisions.
Speakers
Diogo Almeida
Co-Founder & CEO · TypeSafe AI
Diogo Almeida is co-founder and CEO of TypeSafe AI. He joins Ship's Fast AI panel to discuss Jev alongside Vercel and Cerebras, bringing a model-builder's perspective to the relationship between intelligence, latency, and useful application behavior.
Andrew Feldman
Founder and CEO · Cerebras
Andrew Feldman is founder and CEO of Cerebras. At Ship's Fast AI panel, he joins Vercel and TypeSafe AI for a conversation about inference speed and what faster intelligence can make possible for application developers.