Algorithmic Reasoning Emergence
Hattie discusses how algorithmic reasoning can be shown through model outputs, emphasizing the importance of following the reasoning process. Tim marvels at the unexpected emergent behavior in large language models, attributing algorithmic reasoning capabilities to learning regularities in vast datasets.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#91 - HATTIE ZHOU - Teaching Algorithmic Reasoning via In-context Learning #NeurIPS
Related Questions