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.

01:07:24

Creator website

Episode guests

John Berryman

AI Summary

AI Chapters

Episode notes

Podcast summary created with Snipd AI

Quick takeaways

John Berryman's diverse background in search and machine learning has significantly influenced the development of AI applications like GitHub Copilot.

Effective prompt engineering is essential for users to enhance the output quality and relevance of large language models during interactions.

The concept of 'artifacts' helps users maintain context within their dialogues with AI, leading to a more organized and efficient engagement.

Deep dives

John Berman's Journey in Tech

John Berman has had a diverse and extensive career in technology, beginning with aerospace engineering and transitioning into software development and search technologies. After co-authoring a book focused on search relevance, he worked with prominent companies like Eventbrite and GitHub, where he improved their search infrastructures and implemented Elasticsearch for code search. His move into machine learning and specifically GitHub Copilot involved building infrastructure to support large language models in production and enhancing features for the Copilot chat. Currently, he operates Arcturus Labs, focusing on consultancy work related to prompt engineering and large language model applications.

Intro

2min

Navigating the Evolution of Search Technology and Language Models

4min

Understanding Retrieval-Augmented Generation

4min

Navigating the Transition to AI: Challenges and Insights

20min

Evolving Code Search and LLM Integration

25min

The Future of Interactive Artifacts in AI and the Internet

3min

The Implications of Unverified Outputs in LLMs

2min

Navigating the New Frontier of Language Models and Consulting

6min

Vector Podcast website: https://vectorpodcast.com

Get your copy of John's new book "Prompt Engineering for LLMs: The Art and Science of Building Large Language Model–Based Applications": https://amzn.to/4fMj2Ef

John Berryman is the founder and principal consultant of Arcturus Labs, where he specializes in AI application development (Agency and RAG). As an early engineer on GitHub Copilot, John contributed to the development of its completions and chat functionalities, working at the forefront of AI-assisted coding tools. John is coauthor of "Prompt Engineering for LLMs" (O'Reilly).Before his work on Copilot, John's focus was search technology. His diverse experience includes helping to develop next-generation search system for the US Patent Office, building search and recommendations for Eventbrite, and contributing to GitHub's code search infrastructure. John is also coauthor of "Relevant Search" (Manning), a book that distills his expertise in the field.John's unique background, spanning both cutting-edge AI applications and foundational search technologies, positions him at the forefront of innovation in LLM applications and information retrieval.

00:00 Intro

02:19 John's background and story in search and ML

06:03 Is RAG just a prompt engineering technique?

10:15 John's progression from a search engineer to ML researcher

13:40 LLM predictability vs more traditional programming

22:31 Code assist with GitHub Copilot

29:44 Role of keyword search for code at GitHub

35:01 GenAI: existential risk or pure magic? AI Natives

39:40 What are Artifacts

46:59 Demo!

55:13 Typed artifacts, tools, accordion artifacts

56:21 From Web 2.0 to Idea exchange

57:51 Spam will transform into Slop

58:56 John's new book and Acturus Labs intro

Show notes:

- John Berryman on X: https://x.com/JnBrymn

- Acturus Labs: https://arcturus-labs.com/

- John's blog on Artifacts (see demo in the episode): https://arcturus-labs.com/blog/2024/11/11/cut-the-chit-chat-with-artifacts/

Watch on https://youtu.be/60HAtHVBYj8

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.

Vector Podcast

Code search, Copilot, LLM prompting with empathy and Artifacts with John Berryman

Episode guests

Podcast summary created with Snipd AI

Quick takeaways

Deep dives

John Berman's Journey in Tech

The Importance of Prompt Engineering

Understanding RAG and Search Techniques

User Experience and Predictability in AI

Innovative Uses of Artifacts in Conversations

Remember Everything You Learn from Podcasts