@AnujaGadde
Breaking Down Data Science & ML Simply
Nothing here yet.
Nothing here yet.
Jan 24 · 4 min read · Have you ever wondered why a language model can tell that “king” and “queen” are related, or that “apple” and “banana” belong to the same category? At first glance, these connections seem obvious — but under the hood, language models don’t “know” any...
Join discussionJan 17 · 4 min read · Why ChatGPT Can Understand “rizz” But Your Model Can’t Anuja Gadde 4 min read·Just now The hidden reason language models either break or thrive — and it’s not what you think. Last week, I wrote about preprocessing — cleaning HTML, handling emojis,...
Join discussionJan 17 · 4 min read · Why ChatGPT Can Understand “rizz” But Your Model Can’t Anuja Gadde 4 min read·Just now The hidden reason language models either break or thrive — and it’s not what you think. Last week, I wrote about preprocessing — cleaning HTML, handling emojis,...
Join discussionJan 10 · 5 min read · A few days ago, I published a blog about completing a Google DeepMind challenge lab on Arabic character-level language models. It was all about tokenization, n-grams, and getting sequences aligned correctly for transformer training. The thing is, I g...
Join discussion
Dec 26, 2025 · 4 min read · Lessons From a Google DeepMind Challenge Lab After publishing my earlier blog on training small language models, I wanted to validate whether I could apply those concepts without guided instructions. That opportunity came through a Google DeepMind ch...
Join discussion