AXRP - the AI X-risk Research Podcast cover image

38.3 - Erik Jenner on Learned Look-Ahead

AXRP - the AI X-risk Research Podcast

CHAPTER

AI Strategies in Game Theory

This chapter explores the nuances of training AI models for strategic games like Othello and chess, focusing on their learning processes and the implications for interpretability. It discusses the complexities of neural networks, particularly regarding 'look ahead' planning and the challenges of understanding their decision-making behaviors.

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