"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

The Adversarial Mind: Defeating AI Defenses with Nicholas Carlini of Google DeepMind

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

CHAPTER

Navigating AI Challenges: From Fact Editing to Adversarial Attacks

This chapter explores the intricate challenges of modifying large language models, focusing on fact editing and the unlearning process. It delves into adversarial attacks, revealing the dynamic between attackers and defenders, and highlights the complexities of AI interpretability and feature recognition compared to human cognition. The discussion emphasizes the implications of training methods and highlights the fragility of models in the face of adversarial examples.

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.
App store bannerPlay store banner