AI Deconstructed podcast

EP21 - Large Language Models and The Power of Scale

0:00
32:10
Reculer de 15 secondes
Avancer de 15 secondes
This episode moves from the Transformer architecture to the models that define our era: Large Language Models (LLMs). We explore how the simple act of "next-word prediction," when combined with internet-scale data and massive compute, leads to the surprising "emergent abilities" of models like GPT-4, and we break down the crucial training paradigm of pre-training and fine-tuning.

D'autres épisodes de "AI Deconstructed"