Latent Space: The AI Engineer Podcast cover image

Training a SOTA Code LLM in 1 week and Quantifying the Vibes — with Reza Shabani of Replit

Latent Space: The AI Engineer Podcast

00:00

Ghostwriter: Evolution and Evaluation

This chapter explores the development and optimization of the Ghostwriter code completion tool, including the challenges of fine-tuning a Salesforce-based model. It highlights the necessity for improved evaluation methods, such as 'Amjad eval,' to assess code quality in a more contextually aware manner.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app