80,000 Hours Podcast cover image

#107 – Chris Olah on what the hell is going on inside neural networks

80,000 Hours Podcast

00:00

Unpacking Neural Networks: A Deep Dive into AI Safety

This chapter explores the complexities of AI safety, focusing on the interpretability of neural networks and the empirical research necessary for understanding their inner workings. It highlights the significance of reverse engineering to reveal how neural circuits function and their implications for high-stakes applications. Through various methodologies, the discussion illustrates how insights into neuron behavior enhance our comprehension of these systems and their potential safety issues.

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