
38.3 - Erik Jenner on Learned Look-Ahead
AXRP - the AI X-risk Research Podcast
Exploring Follow-up Research on Chess and Language Models
This chapter delves into potential follow-up studies stemming from a recently published paper, focusing on its implications for chess and language models. It highlights the complexities of translating findings to language models and encourages listeners to engage in research on mechanistic interpretability to deepen their understanding of the discussed 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.