# LLMs: Internals, Hallucinations, and Applications | Data Brew | Episode 33

Page: https://stenobird.com/podcast/data-brew-by-databricks/llms-internals-hallucinations-and-applications-data-brew-episode-33
Text version: https://stenobird.com/podcast/data-brew-by-databricks/llms-internals-hallucinations-and-applications-data-brew-episode-33.md
Podcast: [Data Brew by Databricks](https://stenobird.com/podcast/data-brew-by-databricks)
Published: 2023-07-21T07:00:00+00:00
Episode link: https://www.buzzsprout.com/1370119/episodes/13261895-llms-internals-hallucinations-and-applications-data-brew-episode-33.mp3
Audio file: https://www.buzzsprout.com/1370119/episodes/13261895-llms-internals-hallucinations-and-applications-data-brew-episode-33.mp3
Processing state: processed
JSON: https://stenobird.com/v1/public/podcasts/data-brew-by-databricks/episodes/llms-internals-hallucinations-and-applications-data-brew-episode-33
Duration seconds: 2330

## Resource

Our fifth season dives into large language models (LLMs), from understanding the internals to the risks of using them and everything in between. While we're at it, we'll be enjoying our morning brew. In this session, we interviewed Chengyin Eng (Senior Data Scientist, Databricks), Sam Raymond (Senior Data Scientist, Databricks), and Joseph Bradley (Lead Production Specialist - ML, Databricks) on the best practices around LLM use cases, prompt engineering, and how to adapt MLOps for LLMs (i.e...

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/data-brew-by-databricks/episodes/llms-internals-hallucinations-and-applications-data-brew-episode-33/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/data-brew-by-databricks/llms-internals-hallucinations-and-applications-data-brew-episode-33.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.