Data Brew by Databricks Secret to Production AI: Tools & Infrastructure | Data Brew | Episode 37
Jan 22, 2025
Julia Neagu, CEO and co-founder of Quotient AI and former leader of the GitHub Copilot data team, dives into the intricacies of deploying Generative AI. She shares insights on merging reinforcement learning with unsupervised methods for real-time optimization. The discussion touches on reducing biases in machine learning and implementing fairness in AI systems. Julia also highlights the importance of human-in-the-loop evaluations and effective AI pipeline management, emphasizing lessons learned from large-scale deployments.
AI Snips
Chapters
Transcript
Episode notes
Unexpected Copilot Journey
- Julia Neagu joined GitHub and unexpectedly became involved in GitHub Copilot's development.
- This happened due to increased LLM attention and Copilot's potential impact.
Infrastructure for Success
- Copilot's success stemmed from early infrastructure investments.
- These enabled rapid model testing, prompt experimentation, and production deployment with user feedback.
Vibe-Driven Development
- Initially, build products based on intuition and vibes.
- Later, incorporate statistics and data-driven analysis for refinement.