Models, Evals, and Raptor Mini with Julia Kasper
from VS Code Insiders Podcast Hosted by Microsoft
In this episode of the VS Code Insiders podcast, James sits down with Julia to explore the fast-changing world of AI models inside VS Code. They dive into how developers can evaluate models, the role of fine-tuning, and why speed versus complexity matters. From Raptor Mini to Sonnet, this conversation reveals the behind-the-scenes work shaping your coding experience today. Follow VS Code: X: https://x.com/code Bluesky: https://bsky.app/profile/vscode.dev YouTube: https://youtube.com/code LinkedIn: https://www.linkedin.com/showcase/104107263 GitHub: https://github.com/microsoft/vscode Special Guest: Julia Kasper.
Embed this episode
Chapters
- 0:00 Welcome & introductions
- 0:51 Diving into models and evaluations
- 2:25 Choosing models: gut feel vs. science
- 4:47 Why models feel different week to week
- 7:17 Fine-tuning explained & checkpoints
- 9:49 The story behind Raptor Mini
- 12:21 When to use mini vs. larger models
- 15:12 Context, complexity, and developer workflows
- 16:47 Understanding evaluations (evals)
- 19:35 Benchmarks & VS Code’s own eval suite
- 21:15 How developers can give feedback
- 23:34 Closing thoughts & subscribe reminder
No transcript yet.