Analysis: from 2019 to 2025, gains in pretraining compute efficiency came mostly from data improvements rather than model improvements (Dwarkesh Podcast)
Techmeme
Analysis: from 2019 to 2025, gains in pretraining compute efficiency came mostly from data improvements rather than model improvements (Dwarkesh Podcast)
From Dwarkesh Podcast. View the full context on Techmeme.
0 comments
No comments yet.