Sveriges mest populära poddar
The Data Exchange with Ben Lorica
NyheterTeknologi

The Evolution of Reinforcement Fine-Tuning in AI

46 min•13 mars 2025

Travis Addair is Co-Founder & CTO at Predibase. In this episode, the discussion centers on transforming pre-trained foundation models into domain-specific assets through advanced customization techniques.

Subscribe to the Gradient Flow Newsletter 📩  https://gradientflow.substack.com/

Support our work by leaving a small tip 💰 https://buymeacoffee.com/gradientflow

Subscribe: Apple · Spotify · Overcast · Pocket Casts · AntennaPod · Podcast Addict · Amazon ·  RSS.

Detailed show notes - with links to many references - can be found on The Data Exchange web site.

Fler avsnitt av The Data Exchange with Ben Lorica

Visa alla avsnitt av The Data Exchange with Ben Lorica
Can China Do to Robotaxis What It Did to Solar?
•55 min
Why Video Is AI's Next Great Frontier
•40 min
Your AI Safety Tests Are Lying to You
•26 min
Enterprise AI Is Moving Slower Than You Think
•37 min
Why Observability May Be AI’s Next Frontier
•51 min
AI Is Producing More Code, but Is It Producing More Value?
•56 min
Stop Renting Generic Intelligence for Your Business
•54 min
The Data Layer Enterprise AI Has Been Missing
•51 min
The Hidden Failure Modes of AI Agents
•52 min
The Data Stack Wasn't Built for AI — Here's What Comes Next
•40 min

The Data Exchange with Ben Lorica med Ben Lorica finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.