# Localizing and Editing Knowledge in LLMs with Peter Hase - #679

Page: https://stenobird.com/podcast/twiml-ai-podcast/localizing-and-editing-knowledge-in-llms-with-peter-hase-679
Text version: https://stenobird.com/podcast/twiml-ai-podcast/localizing-and-editing-knowledge-in-llms-with-peter-hase-679.md
Podcast: [The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)](https://stenobird.com/podcast/twiml-ai-podcast)
Published: 2024-04-08T21:03:00+00:00
Episode link: https://twimlai.com/podcast/twimlai/localizing-and-editing-knowledge-in-llms/
Audio file: https://pscrb.fm/rss/p/traffic.megaphone.fm/MLN6128348451.mp3?updated=1712607942
Processing state: failed
JSON: https://stenobird.com/v1/public/podcasts/twiml-ai-podcast/episodes/localizing-and-editing-knowledge-in-llms-with-peter-hase-679
Duration seconds: 2986

## Resource

Today we're joined by Peter Hase, a fifth-year PhD student at the University of North Carolina NLP lab. We discuss "scalable oversight", and the importance of developing a deeper understanding of how large neural networks make decisions. We learn how matrices are probed by interpretability researchers, and explore the two schools of thought regarding how LLMs store knowledge. Finally, we discuss the importance of deleting sensitive information from model weights, and how "easy-to-hard generalization" could increase the risk of releasing open-source foundation models. The complete show notes for this episode can be found at twimlai.com/go/679.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/twiml-ai-podcast/episodes/localizing-and-editing-knowledge-in-llms-with-peter-hase-679/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/twiml-ai-podcast/localizing-and-editing-knowledge-in-llms-with-peter-hase-679.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.