Shayne Longpre

0 recommended products

Everything Shayne personally uses, recommends, or has created — plus things they don't recommend — sourced from their own show and appearances on other podcasts.

Recent episodes

All →

Going In Deep On Data | YC Paper Club

Aug 20

Show: All 2 | uses recommends mentions

Showing 2 of 2 products

Clear filters

Madlad-400 mentions software

Mentioned in 1 episode

"In Madlad-400, a popular Common Crawl-based pre-training corpora, there are 0.6% the number of tokens in Thai as compared to English — less than a percent of the amount of English data that you have."

From: Going In Deep On Data | YC Paper Club • ▶ 43:17 • Aug 20, 2026

Chinchilla mentions media

Mentioned in 1 episode

"You have to fit scaling laws. Those of you that are familiar with Chinchilla probably remember this — you predict the loss based off of the model size and the amount of data you've trained on and you fit it using these parameters. However, if you have a multilingual data source, the thing that matters most is how much of the target language data you had."

From: Going In Deep On Data | YC Paper Club • ▶ 50:05 • Aug 20, 2026

0 recommended · 0 sponsored · 0 warned against · 0 episodes