this sub kills me

Modern-Day Oracles or Bullshit Machines?

Jevin West (@jevinwest.bsky.social) and I have spent the last eight months developing the course on large language models (LLMs) that we think every college freshman needs to take.

thebullshitmachines.com

Need some data science help: I’m looking for literature on the number of positive observations needed to communicate the model is “good”. If I’m modeling against 100 M observations with only 100 that are positive using any tree classification method with 100+ features, is that good? #statsky #mlsky