HackerTube / Video

GPT3: An Even Bigger Language Model - Computerphile

Computerphile

GPT3: An Even Bigger Language Model - Computerphile

Rob Miles discusses GPT-3 on Computerphile, covering how scaling parameters kept improving results over GPT-2 and how the model nearly learned arithmetic without anyone knowing exactly how.

HN commenters cite it as a concise explanation of GPT-3's scaling jump and surprising abilities at its release.

5 Hacker News mentions · 2020–2023

Topics

Watch on YouTube

Explore more videos