Vector Podcast Code search, Copilot, LLM prompting with empathy and Artifacts with John Berryman
Feb 10, 2025
John Berryman, founder of Arcturus Labs and co-author of "Prompt Engineering for LLMs," shares his journey from search technology to AI. He discusses the evolution of code search and how GitHub Copilot reshapes programming with AI. Berryman emphasizes the balance between automation and human oversight in coding practices. The conversation dives into retrieval-augmented generation (RAG) and the future of interactive digital artifacts, opening discussions on reliability and accountability in AI-generated content. His insights are both informative and thought-provoking.
AI Snips
Chapters
Books
Transcript
Episode notes
John Berryman's Career Journey
- John Berryman's career path started in aerospace engineering, moved to search technology, then to AI/ML.
- He worked on projects at the US Patent Office, Eventbrite, GitHub, and Copilot.
RAG: Search + LLMs
- RAG (Retrieval Augmented Generation) is essentially a combination of search and large language models (LLMs).
- Debugging RAG applications becomes easier when you treat search and prompting as separate components.
Build Ground Up
- When building LLM applications, start with a ground-up implementation to understand the components.
- Avoid excessive layering with frameworks, which can obscure the underlying processes.
