Do Long Technical Posts Work?
Do people actually read them in their entirety? Do they often return? In this post, we'll get insights via an n=1 review of a front page HackerNews post's reader engagement metrics.
machine learning engineer covering interesting machine learning things
Do people actually read them in their entirety? Do they often return? In this post, we'll get insights via an n=1 review of a front page HackerNews post's reader engagement metrics.
Highlights the desire to replace tokenization with a general method that better leverages compute and data. We'll see tokenization's fragility and review the Byte Latent Transformer arch.