"Moment of Zen"  cover image

Balaji Srinivasan and Nathan Labenz on How AI Will Shape the Future & AI Gods

"Moment of Zen"

00:00

Lack of Robustness and Adversarial Attacks

This chapter explores the lack of proven robust architecture, including language models, and discusses the conjecture that open weights may allow for safety. It also examines the attack on the Alpha Go model and the limitations of current AI models in terms of sensory experiences. The chapter highlights the need for complementary architectures and explores the use of generative AI in various domains.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app