# 915: How to Jailbreak LLMs (and How to Prevent It), with Michelle Yi

Page: https://stenobird.com/podcast/super-data-science/915-how-to-jailbreak-llms-and-how-to-prevent-it-with-michelle-yi
Text version: https://stenobird.com/podcast/super-data-science/915-how-to-jailbreak-llms-and-how-to-prevent-it-with-michelle-yi.md
Podcast: [Super Data Science: ML & AI Podcast with Jon Krohn](https://stenobird.com/podcast/super-data-science)
Published: 2025-08-19T11:00:00+00:00
Episode link: https://www.podtrac.com/pts/redirect.mp3/chrt.fm/track/E581B9/arttrk.com/p/VI4CS/pscrb.fm/rss/p/traffic.megaphone.fm/SUPERDATASCIENCEPTYLTD7520485641.mp3?updated=1755600063
Audio file: https://www.podtrac.com/pts/redirect.mp3/chrt.fm/track/E581B9/arttrk.com/p/VI4CS/pscrb.fm/rss/p/traffic.megaphone.fm/SUPERDATASCIENCEPTYLTD7520485641.mp3?updated=1755600063
Processing state: failed
JSON: https://stenobird.com/v1/public/podcasts/super-data-science/episodes/915-how-to-jailbreak-llms-and-how-to-prevent-it-with-michelle-yi
Duration seconds: 4173

## Resource

Tech leader, investor, and Generationship cofounder Michelle Yi talks to Jon Krohn about finding ways to trust and secure AI systems, the methods that hackers use to jailbreak code, and what users can do to build their own trustworthy AI systems. Learn all about “red teaming” and how tech teams can handle other key technical terms like data poisoning, prompt stealing, jailbreaking and slop squatting. This episode is brought to you by ⁠Trainium2, the latest AI chip from AWS⁠ and by the ⁠Dell AI Factory with NVIDIA⁠. Additional materials: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠www.superdatascience.com/915⁠⁠⁠⁠⁠ Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information. In this episode you will learn: (03:31) What “trustworthy AI” means (31:15) How to build trustworthy AI systems (46:55) About Michelle’s “sorry bench” (48:13) How LLMs help construct causal graphs (51:45) About Generationship

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/super-data-science/episodes/915-how-to-jailbreak-llms-and-how-to-prevent-it-with-michelle-yi/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/super-data-science/915-how-to-jailbreak-llms-and-how-to-prevent-it-with-michelle-yi.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.