Tokenization's a winner, plus some administrative updates.| seantrott.substack.com
When we use LLMs as "model organisms", which humans are we modeling? And how can we overcome the problem of unrepresentative data?| seantrott.substack.com
Defining, operationalizing, and measuring readability is a challenge—can LLMs help?| seantrott.substack.com
Many researchers rely on survey data. How could LLMs like GPT-4 change that?| seantrott.substack.com