
38.2 - Jesse Hoogland on Singular Learning Theory
AXRP - the AI X-risk Research Podcast
Understanding Model Complexity in SLT
This chapter examines model complexity through the lens of Singular Learning Theory, focusing on the local learning coefficient and its relationship with memorization across various tasks. Additionally, it introduces the refined restricted learning coefficient and the concept of a multigram circuit, illuminating how attention-based models process complex language structures.
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.