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

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

Episode publish date
August 19, 2025 11:00 AM (UTC)
Last edit date
Aug 31, 2025 2:09 AM
Last snip date
August 31, 2025 3:08 AM (GMT+1)
Last sync date
August 31, 2025 3:08 AM (GMT+1)
Show

Super Data Science: ML & AI Podcast with Jon Krohn

Show notes link
Snips
5
Warning

⚠️ Any content within the episode information, snip blocks might be updated or overwritten by Snipd in a future sync. Add your edits or additional notes outside these blocks to keep them safe.

Episode show notes

Your snips

[03:40] Trust Needs Model And Data Defense

[04:39] Systematically Red Team Before Production

[10:16] Meta-Level Safeguards With Constitutional AI

[13:59] Agents Create Collective Failure Modes

[19:02] World Models Let Models Simulate Consequences