
38.3 - Erik Jenner on Learned Look-Ahead
AXRP - the AI X-risk Research Podcast
Intro
This chapter delves into a research paper highlighting the intriguing capabilities of neural networks in chess, particularly their learned lookahead abilities. The discussion investigates whether their success is due to clever heuristics or a more sophisticated strategic approach similar to human players and established chess algorithms.
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.