Machine Learning Street Talk (MLST) cover image

Prof. Subbarao Kambhampati - LLMs don't reason, they memorize (ICML2024 2/13)

Machine Learning Street Talk (MLST)

00:00

Decoding Large Language Models

This chapter examines large language models as sophisticated n-gram models rather than true reasoning systems, highlighting their autoregressive nature in word prediction. It discusses the limitations, capabilities, and common misconceptions about LLMs, particularly their ability to generate coherent text without explicit grammar rules.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app