
Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - #678
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Intro
This chapter delves into the emerging field of large language model security, emphasizing adversarial attacks and their historical context. The discussion highlights the implications of these developments on reliability and efficiency, moving beyond mere technical analysis.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.