Argmax

15: InstructGPT

Mar 28, 2023 · 57 min · Season 1 · Episode 15 · 41.4 MB
0:00-57:27

Streams straight from the publisher. podnod never proxies or re-hosts episode audio.

In this episode we discuss the paper "Training language models to follow instructions with human feedback" by Ouyang et al (2022). We discuss the RLHF paradigm and how important RL is to tuning GPT.