Sasha Rush Mocks Interpretability Blogs for burying the Point in Stories

ML researcher Sasha Rush criticized interpretability blog posts for reading like recipe blogs, where readers must wade through long personal stories before finding that the core method is simply "using gradients."

2026-10-16 ~ 2026-10-16 · 2 related posts

• Sasha Rush: interpretability blogs are the recipe blogs of ML — srush_nlp · 2026-10-16

1 near-duplicate retellings: srush_nlp